TILens Daily Edition
2026-10-03
Filters: github=hidden

Stats: 560 articles, 12 sources, 500 research papers
Top topics: AI, AI Research, General

## News

- Four working tools on our marketing site, and not one request leaves the browser
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/daniel_pertu/four-working-tools-on-our-marketing-site-and-not-one-request-leaves-the-browser-11p

- JavaScript Interview Questions Explained: Concepts Every Developer Should Know
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/ansh_sheladiya/javascript-interview-questions-explained-concepts-every-developer-should-know-ndi

- The Hidden Cost of Speed: Understanding Documentation Debt
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/saurav_tb_pandey/the-hidden-cost-of-speed-understanding-documentation-debt-337h

- BeeEngine 2.9: plugins are here, starting with BeeLocale 🌍
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/antonioprosperi2svg/beeengine-29-plugins-are-here-starting-with-beelocale-3bji

- Vue-Select and Vue-Treeselect never got a stable Vue 3 release, so we replaced them
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/szwn/vue-select-and-vue-treeselect-never-got-a-stable-vue-3-release-so-we-replaced-them-d47

- I built 59 free browser-based dev tools in vanilla JS — here's what I learned
  Source: devto-javascript
  Topic: JavaScript (+AI, React)
  URL: https://dev.to/yuvaraj_radhakrishnan_224/i-built-59-free-browser-based-dev-tools-in-vanilla-js-heres-what-i-learned-5cn5

- I built a Vue directive that turns your real component into its own skeleton
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/navidjaberi/i-built-a-vue-directive-that-turns-your-real-component-into-its-own-skeleton-3853

- Chrome on an M3 says it is an Intel Mac, so our download page has three buttons and no guessing
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/daniel_pertu/chrome-on-an-m3-says-it-is-an-intel-mac-so-our-download-page-has-three-buttons-and-no-guessing-3dmc

- JavaScript Debouncing Explained: A Must-Know Interview Concept 🚀
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/webtechnology_tutorials_f/javascript-debouncing-explained-a-must-know-interview-concept-1h9b

- Implementando la huella SHA-256 de VeriFactu: 6 detalles que rompen el hash (y uno que rompe la cadena)
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/a_molina_b9d7a17c33863229/implementando-la-huella-sha-256-de-verifactu-6-detalles-que-rompen-el-hash-y-uno-que-rompe-la-1d82

- A laptop lid is not a restart: seven ways our app stops, and what each one is allowed to forget
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/daniel_pertu/a-laptop-lid-is-not-a-restart-seven-ways-our-app-stops-and-what-each-one-is-allowed-to-forget-3l5d

- Electron cookies say "unspecified", Playwright only knows "Lax", and the mapping logged everyone out
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/daniel_pertu/electron-cookies-say-unspecified-playwright-only-knows-lax-and-the-mapping-logged-everyone-out-1777

- Istio 1.31 Adds Agentgateway Waypoints and Moves Release Artifacts off Google Cloud
  Source: infoq-architecture
  Topic: Architecture
  URL: https://www.infoq.com/news/2026/10/istio-1-31-agentgateway/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design

- Palantir's fondness for French food cooked up tech's latest fad – forward-deployed engineers
  Source: theregister
  Topic: General
  URL: https://www.theregister.com/channel/2026/10/03/palantirs-fondness-for-french-food-cooked-up-techs-latest-fad-forward-deployed-engineers/5300360

- That’s No Moon… That’s an Exoplanet!
  Source: hackaday
  Topic: Hardware
  URL: https://hackaday.com/2026/10/03/thats-no-moon-thats-an-exoplanet/

- AI Agents Are Disrupting Open Source Security Disclosure
  Source: infoq-architecture
  Topic: Architecture
  URL: https://www.infoq.com/news/2026/10/open-source-ai-security/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design

- Is This The Smallest Internet Radio?
  Source: hackaday
  Topic: Hardware
  URL: https://hackaday.com/2026/10/02/is-this-the-smallest-internet-radio/

- Five Frameworks, One Page, Zero Runtime Tax — Micro-frontends in Web Workers
  Source: devto-javascript
  Topic: JavaScript (+React)
  URL: https://dev.to/jwhenry3/five-frameworks-one-page-zero-runtime-tax-micro-frontends-in-web-workers-4ia4

- UUNA TEK iAuto review – A professional handwriting and drawing machine
  Source: cnx-software
  Topic: Hardware
  URL: https://www.cnx-software.com/2026/10/03/uuna-tek-iauto-review-a-professional-handwriting-and-drawing-machine/

- Check a parsed JSON response before rendering demo items
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/stavleak-hackathons/check-a-parsed-json-response-before-rendering-demo-items-4n21

- Preserve plus signs and ampersands in demo search URLs
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/stavleak-hackathons/preserve-plus-signs-and-ampersands-in-demo-search-urls-2ejb

- Keep an older search response from replacing the latest results
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/stavleak-hackathons/keep-an-older-search-response-from-replacing-the-latest-results-29ae

- JavaScript Modules Explained: ES Modules, Imports, Exports, and Best Practices
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/ansh_sheladiya/javascript-modules-explained-es-modules-imports-exports-and-best-practices-3j0g

- Your Next.js App Feels Slow, but Lighthouse Says It’s Fast. Why?
  Source: devto-javascript
  Topic: JavaScript (+React)
  URL: https://dev.to/ioan_flaviuzsoldos_a3bf4/your-nextjs-app-feels-slow-but-lighthouse-says-its-fast-why-39ci

- Cancel a demo request when the user leaves its screen
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/stavleak-hackathons/cancel-a-demo-request-when-the-user-leaves-its-screen-47c7

- Handle partial failures in optional widgets with Promise.allSettled()
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/stavleak-hackathons/handle-partial-failures-in-optional-widgets-with-promiseallsettled-153d

- 2026 Retrocomputing Challenge: Lunar Lander on the PDP-1
  Source: hackaday
  Topic: Hardware
  URL: https://hackaday.com/2026/10/02/2026-retrocomputing-challenge-lunar-lander-on-the-pdp-1/

- How to Deobfuscate JavaScript in One API Call (No Local Tooling)
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/gia_lybui/how-to-deobfuscate-javascript-in-one-api-call-no-local-tooling-4idf

- Chainalysis
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/rosarioam/chainalysis-2222

- 2.2 cat Codes With Omitted cattax Validate. OpenRTB Defaults to Taxonomy 1.0.
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/aleksuix/22-cat-codes-with-omitted-cattax-validate-openrtb-defaults-to-taxonomy-10-16kp

- A game portal rejected my game with one line - "The WASD keys aren't working". They were right, and all my tests were green.
  Source: devto-javascript
  Topic: JavaScript
  URL: https://dev.to/nightdrivelabs/a-game-portal-rejected-my-game-with-one-line-the-wasd-keys-arent-working-they-were-right-and-3p11

- Meta wants your next gadget to be Muse-infused
  Source: techcrunch
  Topic: General
  URL: https://techcrunch.com/2026/10/02/meta-wants-you-to-build-your-own-muse-gadget/

- Sanders introduces bill to ban the federal government from using Flock
  Source: techcrunch
  Topic: General
  URL: https://techcrunch.com/2026/10/02/sanders-introduces-bill-to-ban-the-federal-government-from-using-flock/

## Research

- ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00906

- Mixture-Trained Merging for Unified Multi-Objective Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01238

- Transferable Graph Metanetworks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00420

- Towards Fast and Disentangled Counterfactuals for Visual Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00895

- Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI, Information Retrieval)
  URL: https://arxiv.org/abs/2608.12573

- Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.23135

- Cost-augmented Schr\"odinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02195

- Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01399

- ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00328

- From Redundancy to Minimality: Fixed-Point-Guided Hierarchical Reduction of Learned Piecewise-Linear Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01369

- STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00377

- Information propagation dynamics in Deep Graph Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2410.10464

- Multi-Resolution Feature Fusion U-Net for Magnetic Resonance Imaging Segmentation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00279

- FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00385

- Fusion techniques of time frequency-based images to predict the outcome of rTMS depression therapy
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00380

- Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01846

- Uncertainty-Aware RL-Controlled Adaptive 3D Mapping
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00188

- On Evaluating Quantum Kernel Robustness for Low-Resource Cross-Corpus Audio Deepfake Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00649

- Learned End-to-End Guidance Schedules for Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01502

- Faynt: Scaling and Optimizing Policies for Competitive Melee
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02144

- Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00767

- Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02081

- Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02173

- Inference for stochastic differential equations driven by weighted sub-fractional Brownian motion using neural networks and the Euler approximation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00793

- Completion Aware Guidance for World Action Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01559

- StoCFL: A Stochastically Clustered Federated Learning Framework for Non-IID Data with Dynamic Client Participation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2303.00897

- Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01984

- The Curvature of Regret in Contextual Linear Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01980

- Hierarchical Continuous Diffusion Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02193

- Learning to Predict Distributions over Weight Updates for Test-Time Adaptation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01934

- Verification Pulses and the Cost of Escaping Wrong Consensus
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00256

- Generation Provenance Before Behavior Attribution: Auditing Synthetic Speech Research Objects
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01378

- Auto-Formalizing Neuro-Symbolic Predictors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01519

- Benchmarking System One decision models against trained classifiers and language models for automated decision gates
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00346

- FairSSL: Fair Multimodal Self-Supervised Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.16748

- Interpreting Reasoning of Large Language Models via Partial Information Decomposition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00571

- Comedic Fool's Gold: Reward Exploits and Countermeasures in Conversational Humor
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00197

- Flow-Transformed Implicit Processes for Function-Space Variational Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.01954

- On the Escaping Efficiency of Distributed Adversarial Training Algorithms
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.11337

- Function-Structured Reinforcement Learning with Executable Verifiers for Mathematical Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01729

- Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00661

- Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01947

- MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01819

- Capabilities Ain't All You Need: Measuring Propensities in AI
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.18182

- ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00431

- EvoGen-Harness: Learning Where and How to Evolve Image-Generation Harnesses
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00383

- Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01375

- Polylogarithmic Sparsity of Randomly Reweighted NPMLEs for Gaussian Mixtures
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01088

- Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02117

- When Do Biological Reasoning Models Use Their Biological Inputs?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00898

- Neural Fourier Surrogates for Data Reuploading Quantum Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00841

- Model validation in machine learning: A scenario-based guide from hold-out splits to nested group cross-validation in biomedical and applied research
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01284

- Degree-Corrected Joint Matrix Factorization for Multilayer Community Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01361

- One Mastery Threshold Does Not Fit All Knowledge Tracing Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00095

- Coupling Perception and Reasoning in Federated Multimodal Graph Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00277

- Designing for Interpretation Uncertainty: Architecture and Principles for Topological Learning Analytics Dashboards
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01749

- The hidden advantage of mask resampling: a theory of masked autoencoders
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01578

- PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00451

- EP-Flow: Disordered Crystal Structure Prediction without Site-Level Annotations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01315

- A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01949

- Beyond Affine Transformations: A Soft Dominance Layer for Coordinate-Wise Neural Computation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00563

- SeedFlood: A Step Toward Scalable Decentralized Fine-Tuning of LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.18181

- ibUMAP: Coherent and Scalable Field Evaluation for UMAP Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01445

- Managing Context and Communication in Distributed Agentic UAV Swarms
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01569

- TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00899

- Initial condition recovery in nonlinear damped viscous photoacoustic tomography using a convolutional neural network-guided gradient-free optimization framework
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01015

- Geometry-Aware Adaptation for Pretrained Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2307.12226

- Learning from the Near Future: Temporal Self-Distillation for RLVR
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.20733

- SoftServe: A Scalable Quasi-Newton Method for Deep Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02182

- The Conflict Between Logic and Memory: Learning Higher-Order Interactions in Shallow MLPs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00403

- Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01835

- Large Language Bayes Is Not Reparameterisation-Invariant
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00265

- End-to-End Historical Music Restoration in Latent Space
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00607

- Higher-Order Molecular Grammars for Generative and Foundation Models in Chemistry
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02186

- Beyond Pointwise Error: A Multi-Metric Evaluation of Spatial Climate Downscaling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01579

- Learnt Attacks on Quantum Key Distribution under Channel Noise and Device Drift
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01792

- INDEQS: Informed Neural controlled Differential EQuationS
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.19138

- Constant-Memory Recall: Learned Associations in a Fixed Matrix State
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00232

- Sequential Capacity of Quantum Processes with Finite Memory
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02068

- OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00381

- Open Vocabulary Word Recognition From Transcribed Bangla Texts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01134

- Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Serving
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00499

- ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00592

- Graph Hierarchical Recurrence for Long-Range Generalization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.18387

- Integrating Fairness and Explainability in a Multiple Instance Reinforcement Learning System
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00035

- The Price of Correlated Tests: How Strict Should a Model Release Gate Be?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00993

- Random Recursive Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00541

- Universal Approximation of Nonlinear Operators and Their Derivatives
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.15285

- CommunityKV: Efficient Long-Context Decoding via Graph Partitioning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00418

- Spatial Lifting for Dense Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00017

- Kolmogorov-Arnold Networks for Free-Boundary Partial Differential Equations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02084

- Ontology-Grounded, Reasoner-Verified Benchmarks for Evaluating LLM Reasoning in Scientific AI
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00682

- "very likely" Means "uncertain"? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00083

- Beyond Diagonal State Space Models: Exact Non-Abelian Group Tracking, Solvability Barriers, and Geometric Physical Manifolds
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00329

- SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01962

- BG4Sea: Biogeochemical Seasonal Forecastability via Progressive Information Scaling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.16731

- ScaffoldM3C: A Multimodal Sequential Monte Carlo Framework for Generative Stable Construction Planning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00487

- Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00729

- Prediction-powered Neural Architecture Search
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01317

- Attention Kernels for Learning Maps Between Heavy-Tailed Measures
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00564

- Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01670

- Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02189

- LAST: Looped Audio Spectrogram Transformer
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01926

- Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00424

- Generalization in Neural Networks Through the Lens of Magnitude Potential
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01633

- Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00574

- Anomaly Detection and Localization for the Pantograph-Catenary System
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01721

- CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02039

- Exact information accounting for SGD methods
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00446

- Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01318

- A Structured State Space Sequence Model for Multi-Class Classification of Malware
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01893

- Every Batch Is Its Own Validation Set: Leave-One-Out Gradient Matching for Online Data Selection in LLM Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00436

- CAGE-NAS: Certified Functional Descent for Efficient Model Growth
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01173

- Artifact Annotations Partially Substitute for Per-User Calibration: SAFE-EDA and a Normalization-Controlled Evaluation of Wrist-EDA Affect Recognition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01692

- SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00838

- Actions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00327

- CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00727

- ReHoPER: Receding-Horizon Planning for Enhanced Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00940

- Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00233

- Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01896

- Stochastic Optimal Control for Continuous-Time fMRI Representation Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.04892

- Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00558

- FourierQK: Filter Shape, Admissibility and the Leakage-Coverage Law
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00009

- Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01177

- Posterior sampling by source-space MCMC via prior-based few-step transport maps
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01034

- Exact Distinguishability in Non-Markovian Decision Processes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01527

- Multi-User mmWave Beam and Rate Adaptation via Combinatorial Satisficing Bandits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.14908

- ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.00341

- Evidence-Gated Research: Statistically Controlled Model Adoption in Adaptive Search
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01751

- Sharpening Tax in Post-Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01509

- CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.05378

- FERPO: Forward Entropy-Regularized Policy Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02198

- Sim+Real: Joint Simulation - Experiment Training Improves Balanced Prediction in Physical Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01974

- TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02199

- Optimal Stochastic Bilevel Optimization with First-Order Oracles
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01843

- SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00050

- Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01165

- Sharp Oracle-Regret Tradeoffs for Projection-Free Online Convex Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00254

- One pool, many targets: a conservation layer and what archival data can identify
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00445

- How Far is Adam from Natural Gradient Descent?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00004

- Misalignment of Low-Loss Regions Causes Grokking
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00620

- High-Value Synthetic Supervision for Parameter-Efficient Adaptation of a Compact Japanese Speech Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00026

- Embedding Prediction Helps Image Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02203

- EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00412

- ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.10793

- The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00332

- XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00432

- Beyond Unimodal Bases: Pullback Geometry for Multimodal Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00708

- Training-Aware Target Coverage for Synthetic Data Selection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00814

- On the Relationship between Model Quantization and Model Inversion Attacks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00382

- AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00706

- Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.07579

- Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01882

- Pepti-drift: Scalable Safe-Active Peptide Generation Without Inference-Time Guidance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.27824

- Tight Transition Time Bounds for Separable Logistic Regression at the Edge of Stability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01459

- Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00991

- Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02012

- Uncertainty-Aware Learning from Multi-Expert Interval Targets
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00102

- Adaptive and oblivious statistical adversaries are equivalent
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2410.13548

- SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00851

- Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01128

- AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01560

- Latent Information Sharing for Accelerating Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01126

- Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01005

- Grand Canonical Generators
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00683

- MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00604

- Why Does Train-Validation Separation Emerge? Update-Pressure Density Dynamics in Pretrained Backbones
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01425

- Generative Modeling of Stochastic Dynamics for Long-Time Evolution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00546

- Fixing a Model That Learned Worse Cancer Means Lower Risk: Monotonic Constraints in Bladder Cancer Recurrence Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00858

- MOVE: Multimodal Open-world Verification and Expansion for Graph Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00268

- Generalized Engression Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01823

- Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01889

- Benchmarking Prompt Optimization of Large Language Models With Chess
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00416

- Same Reward, Different Skills: When Multimodal RL Learns to Look
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01908

- Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01892

- GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR Events
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01076

- Backdoor Containment via Expert Quarantine and Shutdown in LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00663

- Exposing the Cost of Deep Learning Audio Development
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01619

- Initialization Improves LLM-Driven Discovery
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00707

- Distributionally Robust Schr\"odinger Bridge
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02043

- Interpretable Synthetic Medical Tabular Data Generation for Clinical Decision Support Using Fuzzy Cognitive Maps
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00391

- Q-MINO: A Minimal-Norm Method for Quantization-Aware Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00738

- Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.08944

- Understanding Latent Diffusability via Fisher Geometry
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.02751

- From Knowledge Access to Source Learning: Developing Source-Specific Competence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02150

- Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00497

- Classification Based on Association Rules Algorithm for Breast Cancer
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00174

- Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01028

- Symmetry Discovery in Quantum Learning: Observable-Level and Task-Level Inference from Finite Measurements
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00157

- Model Merging via Data-Free Covariance Estimation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.01329

- Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00678

- Fractional Laplace Neural Operators: Exact Architectures, an Expressivity Frontier at Criticality, and Certified Stability for Memory-Driven Network Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00515

- One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02207

- SyntheticHLS: Building Diverse Synthetic High-Level Synthesis Datasets using LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00106

- LESS: Lightweight Evolutionary Supernet Search in Minutes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01468

- Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00320

- STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00003

- Let the Heads Talk: Beyond Diagonal Graph Attention
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01494

- BranchIP: Learning Adaptive Equivariant Computation for Interatomic Potentials
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02013

- Deep Learning for Anomaly Detection in Railway Systems: A Structured Survey
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00363

- Learning the identity: a case study of how SGD selects among functional decompositions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00615

- Crossing the Cyber Divide: Sim-to-Sim and Sim-to-Real Transfer for RL Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00759

- A Large Scale Investigation of Scaling Limits in Chemical Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.13408

- Signal-Noise Factorization Isolates Nuisance Variation into Removable Subspaces
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00751

- Permutation-Robust Decision Modeling with Candidate-Independent Block-Causal Attention
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01601

- AnyJev Technical Report
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00831

- Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01224

- Emergent Object Binding Has a Finite Spatial Horizon
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00006

- Convergence Analysis of STORM Under Different Geometries
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01599

- Towards Optimal Policy Improvement
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01566

- Improving scoring functions for protein-protein docking with LambdaLoss
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00191

- Smoother Flow Matching via Contrastive Trajectory Repulsion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01408

- Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01572

- Don't Waste the Noise: Importance-Guided Perturbation Allocation under Joint Global and Local Constraints
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00861

- A First Glance at Jev for Network Traffic Classification: Accuracy, Processing Time, and Cost
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00376

- Generalized Biomedicine Discovery
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00120

- CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00321

- Weighted Data Selection: Sharp Upper-Half and Five-Dimensional Laws
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00101

- On Reliability of Membership Inference Vulnerability Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.25819

- Meta-reinforcement learning with minimum attention
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.16741

- Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01513

- Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00524

- Zero-shot generalization of transformer neural operators to larger domains
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.14597

- Score the Update, Not the Token: Descent-Aligned Routing for Combinatorial LoRA Experts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00493

- TRACE: Tackling Real-World Resource Assignment Problems via Agentic Heuristic Design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01887

- Low-Budget Active Learning through Entropic Optimal Transport
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01199

- TANGO: Treating Tokens as Operators
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.22117

- Useful to Whom? Sample Value Is Defined Only Relative to the Learner
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00221

- Neither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01533

- Constitutional Value Potentials: reading and steering internal priority margins in language models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.15420

- STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00907

- Mean Spatial Frequency Decoupling for Learning-Based Uplink-to-Downlink Covariance Conversion in FDD Massive MIMO
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00596

- Capturing In-Context Learning Dynamics with Task Operators
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01054

- Learning PDE Dynamics between Submanifolds Using Green's Observation Operators
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01697

- Repurposing Obsolete Representations for Post-Deployment Adaptation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01453

- Partial AUC Maximization from Positive-unlabeled Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00284

- Causal-Aware Tabular GANs with Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.24046

- PhaseAT: Fourier Phase Adversarial Training for Medical Image Domain Generalization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01807

- VANDAM: Viewing a nucleotide sequence with DNA molecular priors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00411

- Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01046

- Geometry-Dependent Bounds for Online Non-Monotone DR-Submodular Maximization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00545

- QK-Wanda: Coupling Queries and Keys for Unstructured Pruning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01554

- RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00405

- Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01951

- Learning Rate Transfer for Hybrid Transformer-SSM Architectures
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01172

- OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01497

- Calibrating Prediction Timeliness Through Multi-Objective Hyperparameter Optimization for Remaining Useful Life Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01530

- Video Generation Models: A Survey of Post-Training and Alignment
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00812

- The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00423

- Scalable Multi-Task Inverse Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00758

- AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00465

- SimplexUQ: An Evaluation Framework and Benchmark for Conformal Uncertainty on Simplex-Valued Predictions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00523

- TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00835

- Increasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00753

- Reliability-aware short-term roll prediction for unmanned surface vehicles via multi-task learning and adaptive centralization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00996

- Decoding Looped Transformers Better for (Almost) Free
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02185

- Benchmarking Generative Models for Weather Data Assimilation on Real Station Observations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00728

- Which LLM to pick? Online Active Model Selection for Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01592

- Relative Transitions, Not Absolute Destinations: A Transfer-and-Ground Framework for Target-Trajectory-Free Human Mobility Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02033

- dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.09291

- FedMAD: Modulation-Aware Directional Aggregation for Federated Learning in Remote Sensing Image Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00693

- How Divergence Becomes Decision Flips in Compressed Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00694

- REALM: Retrospective Encoder Alignment for LFP Modeling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.14867

- Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00680

- MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Tabular Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.02221

- VERITYGATE: A Four-Gate Schema-Level Faithfulness Framework and Paired Benchmark for Grounded LLM Narrations over Structured Evidence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00833

- Loading history and window geometry bound compact-state slip ranking during granular shear startup
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00124

- Lower Bounds for Stochastic First-Order Algorithms with Variance Reduction in Nonconvex--Concave Minimax Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01662

- Learning Linear Systems under Heavy-Tailed Noise: A Non-Asymptotic Analysis from A Single Trajectory
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00637

- Removing spurious minima for planar features by skip connections
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01728

- Weather-Aware Domain Adaptation for Street-View Weather Recognition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02000

- The Null Is the Hard Part: Exact Tests for Memorization in Generative Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00251

- Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02098

- Auditable Algebraic Counting Field for Cryptic-Pocket Detection from Apo Structures
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00988

- Iterative Policy Refinement through Semantic Rollout Analysis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01652

- Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.14895

- Adaptive Conformal Prediction for Image Regression Models with Application to an Inertial Confinement Fusion Emulator
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00535

- Not All Is Lost: Repairing Lossy User Preference States of Personalization Encoders
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01270

- Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01143

- Counterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01963

- How Much Can Language Models Gain from Test-Time Computation?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01110

- FedMIX-P: Mixing Local and Global Preconditioners for Federated Vision and Language Model Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01515

- Fixed-point neural samplers on discrete spaces
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01739

- SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02201

- Fast Polynomial Transcendentals for LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00049

- When Do Intrinsic Rewards Lead to Exploration?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02159

- MCIR: A Feature Dependence-Aware Explainability Method with Reliability Guarantees
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01641

- Learning to Cover Locally: Graph Neural Combinatorial Optimization under a Hard Information Horizon
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00422

- Neural scaling laws and evolution of learnable activation functions of Kolmogorov-Arnold networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00985

- Reverse Item Response Theory for Sparsity-Robust Ranking in Fragmented Cancer Drug-Response Matrices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00002

- Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02092

- Do Better Scores Mean Better Physics? Physics-Grounded Explanations for Sim2Real Neural Operators
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00415

- FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01638

- Continual Reinforcement Learning with Neuroevolution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01583

- WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00713

- Effective Resistance and Graph Neural Network Reliability in Tissue-Specific Interactomes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02175

- SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00686

- System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00253

- Scaling Collider Event Generation with Residual-Quantized Tokens
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00569

- StabilityArc: Decoding Protein Sequence Embeddings into Generalizable Stability Landscapes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00742

- Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00562

- PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.19145

- Classical Hardness of Learning Functions of Hamiltonians
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01141

- Generalist Representation, Specialist Detection: TS-Router for Time-Series Anomaly Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00978

- SLIM: Simplex-Lattice Interpolation Merging
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01037

- Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2410.23660

- Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01821

- Right In-Place (RiP) Convolution: A Simple, General, and Near-Optimal Strategy for Memory-Efficient CNN Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00586

- Training-Free Diffusion Planning with Analytical Local Scores
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01959

- Reachability-Informed Reinforcement Learning for Multi-Impulse Interplanetary Transfers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01344

- LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00675

- A foundation for systematic analysis of transformers and RNNs for tractography
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01894

- Robust Evidential Learning Through Latent Consistency
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01384

- MatrixReward: Reward from Rubric Matrix for Open-Ended Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00389

- How Many Categories Are Enough? Distribution-Free Certification Limits for Few-Shot Anomaly Thresholds
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00236

- M$^2$Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00370

- Range-GRPO: Policy Optimization via Pairwise Relations among Reward Intervals
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01548

- Learning ab initio phase-field models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01432

- Integrable Elasticity via Neural Demand Potentials
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.22820

- PI-AMFM: Permutation-Invariant Learning for Variable-Cardinality AM-FM Mode Decomposition in Biomedical Signal Analysis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00819

- Dataset Identity, Not Novelty: The Source of an Inflated OOD Detection Gain
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01096

- PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01260

- Code Owns the Simulation, Jev Owns the Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01834

- From Task Mixtures to Specialized Experts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00580

- Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01933

- Context-Aware Error Mitigation Orchestration for Hybrid Quantum Reinforcement Learning on NISQ Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01253

- Reshape and Recur: Improving SSMs with Input Reshaping and Depth Recurrence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.16048

- Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01765

- HADRec: A Hierarchy-Aware Drug Recommendation Framework by Fusing Molecular Knowledge and Electronic Health Record
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00984

- Metacognitive Reasoning in Energy Based Models using Instance Based Learning Theory
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00399

- SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01788

- Roto-translated Local Coordinate Frames For Interacting Dynamical Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2110.14961

- Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00400

- New Snake-in-the-Box Records via Snakepit Surgery and Learned Construction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.15270

- Port-Hamiltonian Neural Networks for Systems with Multiple Asymptotically Stable Equilibria
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01356

- Poincar\'e Meets Bellman: Revisable Memory, Operational Quotients, and Evidence-Supported Learning in Changing Environments
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.05990

- One-Step Generative Modeling via Training Dynamics Action
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00518

- Two Routes to the Middle: Placement Search and Brain Readouts Converge on Where Continual Learners Should Specialize
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01590

- Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01301

- The Innocent Courier: Covert Exfiltration Through Legitimate LLM Web Fetching
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01768

- AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.16067

- Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00651

- SupraTITO: Transferable Generative Molecular Dynamics for Supramolecular Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01381

- LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00333

- A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Risk
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05995

- Leto: Fast In-Place Recovery for LLM Training on Surviving Hardware
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00687

- Distillation of Tabular Foundation Models into Efficient Predictors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01435

- The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02191

- Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00903

- R-GroundBench: A Diagnostic Benchmark for R-Group Groundingin Markush Molecular Editing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00700

- Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01153

- Source Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00417

- MiLoop: Selective Memory Propagation for Neural Combinatorial Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01685

- Discrete Wasserstein Flows for One-Step Generative Modeling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01355

- Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programming
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01546

- Bellman-Certified Rounding for Sparse Policy Deployment in MDPs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00325

- Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01428

- Variational Streaming Flow: Probabilistic Forecasting in Physical Time
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00976

- When More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00654

- Platonic Task Arithmetic
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00929

- Structured-Noise Masked Modeling for Video, Audio and Beyond
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2503.16311

- Heteroskedastic Canonical Polyadic Tensor Decomposition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00498

- Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.07631

- Linear Programming Representations and Strongly Polynomial Algorithms for Robust Markov Decision Processes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02131

- FastCI: Efficient GPU-Intensive CI for LLM Training Frameworks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01967

- Retrieval from Within: An Intrinsic Capability of Attention-Based Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.05806

- EyeTAG: Eye Trajectory-Aware Gaze Estimation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00922

- The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.23191

- WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00398

- Does Scaling Reinforcement Learning Really Require More Training?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01133

- RPTune: Learned Context Curation for LLM Catalog Search
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00964

- Least-time Gradient Flow
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01426

- Rethinking the Information Bottleneck: Structured Decomposition under Label-Induced Partitions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01175

- A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01801

- Analysis of Quantized and Efficiently Adapted Protein Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00665

- NEUROTOKEN: Joint Source and Directional AAD with Envelope Decoding via Conditional Flow Matching
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00397

- Autoregressive Drillhole Modelling Under Distribution Shift
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01204

- Compute Aligned Training: Optimizing for Test Time Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.24957

- Graph Representation via Elements of Discrete Morse and Cobordism Theories
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01937

- Compositional Embedding Architecture for Physical Field Prediction in Componentized Aerospace Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00237

- AI Emulation of Stochastic Sudden Stratospheric Warming with Interpretable Latent Structure
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02069

- Debias Anything: Fairness with Diversity without Supervision in Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01815

- Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01522

- Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02067

- End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01746

- Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02190

- Towards a Cloud Fog Edge System for Smart Building
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01647

- Streaming algorithms for robust max-min diversification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01456

- In-context Learning of Single-index Targets: Comparing Kernel and Feature Learners
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01712

- CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01649

- Cross-Benchmark Transfer from RL on Agentic Coding Tasks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00890

- Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00685

- Geometric Data Perturbation with Noisy-Anchor Alignment for Privacy-Preserving Collaborative Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18749

- Evaluating Memory Structure in LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.11243

- Energy Time-Series Imputation with Differentially Private Diffusion Models via Clipping-Aware Objective Conditioning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00209

- Optimal Transport Meets Reinforcement Learning: A Survey
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01413

- EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.18967

- Finetuning with Sampling: SFT Learns Better Than You Think
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02140

- Format-Aware Fusion for Fast FP4 Pretraining
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00053

- Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00395

- Verify Claims, Not Scores: Evidence-Based Verification of Modular Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01348

- ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.04535

- Beyond Pixel Reconstruction: Retrieval-Guided Glyph-Aware Restoration for Low-Resource Manchu Historical Documents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00315

- Fully Online Decentralized Learning in Stochastic Games with Unknown Independent Chains
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01181

- A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00926

- Clock Diffusion: Efficient Semi-Autoregressive Continuous Diffusion Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00894

- Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00778

- MoRA: MoE Pruning via Router Bias Learning and Expert Approximation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00367

- Sample complexity bounds for categorical Markov random fields via Discrete Diffusions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02128

- From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02179

- When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00373

- pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01663

- Clifford Sheaf Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01322

- IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00426

- ReForge: Refining Merged Models with Anchor-Regularized Regression
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.12843

- From Order to Distribution: An Exact Operator Framework for Forgetting in Continual Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.13460

- Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02058

- Kernelized Activation Steering
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01062

- CompMat-Bench: Benchmarking AI Agents for Computational Materials Science
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00636

- Nous: Learning and Certifying Memory Decisions Before Source Calibration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00094

- Invent a Dataset: Measuring dataset generation abilities with zero seed
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01674

- Evaluating Hybrid Quantum-Classical Models for Reduced-Order Brain Deformation Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00554

- Rate-Optimal Algorithm for Adversarial Linear CMDPs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00927

- Beyond Demographic Balance: Multi-Metric and Intersectional Evaluation of Fairness in MIMIC-IV Mortality Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01645

- Learning to Price Electricity for Optimal Demand Response
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00755

- Attention Manifolds: Steering or Blocking Language Models by Editing Learned B-Spline Surfaces
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00257

- Forking: Sudden Overfitting Under Replay
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00394

- JEPA-Bisim: Learning Robust Visual Representations for Planning with Joint-Embedding Predictive World Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.18639

- GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00948

- Reformulation-Contrastive Learning for Mixed Integer Programs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00730

- IQS-BO: In-Context Query Selection for Bayesian Optimisation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01269

- Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01472

- Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00348

- RelICL: Training-free Relational Learning with Tabular Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01725

- Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.11030

- DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00317

- Comparing a gradient boosting algorithm to the GOES FDC for wildfire detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01994

- LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.03651

- MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01102

- Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00025

- Multi-Task Anti-Causal Learning for Reconstructing Urban Events from Residents' Reports
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.11546

- Learning Transferable Skills using Goal-Conditioned Bisimulation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00676

- T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00388

- On Language Drift during RLVR Post-Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02015

- When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00202

- CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20468

- Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02158

- ORBIT-FMIB: Tracking Order-Resolved Epistatic Information Through ESM-2
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00672

- Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01006

- Quantifying the Impact of Ambulance Ramping: A Multi-Year Analysis of Victorian Emergency Medical Services Cases
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00818

- Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01168

- Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01377

- iADD: Improving Alignment and Diversity in Diffusion Policy Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01789

- Localizing Transfer Between Memorization Tasks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00771

- Reason in Style: Discovering and Controlling Style in Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00724

- Learning Commute-Time-Preserving World Models for Planning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01373

- Robust Non-Clairvoyant Scheduling with Classification Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01343

- Progressive-Resolution Secure Aggregation for Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00695

- Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRA
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00610

- Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01786

- Encoded but Disconnected: Decomposing Vision-Language Model Failures under a Patching Null
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00024

- Manifold-Constrained Initial Noise Optimization for Efficient Generative Model Alignment
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00365

- Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01193

- Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.28228

- Four Ways to Grow a Classifier and Why One of Them Cannot Learn
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00180

- Pooling Helps, Learned Weighting Hurts In-Context: Decomposing Group Attention
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01831

- FedFit: Federated Fine-Tuning of LLMs via Vector-Bank Parameterization and Quantization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01537

- GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.14841

- A Typed Tensor Language for Shared-State Federated Computation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.21103

- On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00820

- Scientific Discovery under Validation Congestion via Multi-Fidelity Pairwise Rankings
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01827

- The Hidden Costs of 99% Accuracy: A Trustworthiness Audit of the Telco Customer Churn Benchmark
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00118

- Adam at the Edge of Stability: Adaptive Feedback, Provable Oscillation, and Gradient Reversal
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20638

- AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01395

- TRIAGE: Dialectical LLM Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.09030

- Distilling Directional Verification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00997

- Higher-Order Positional Encodings for Graph Representation Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01903

- Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01223

- Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.03155

- SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00704

- Hob-VL: A Benchmark for Visually Grounded Boolean Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01605

- Contingent Exposure Routing for Financial AI: Outage Risk and the Cost of Indivisible Decisions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00239

- Rethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype Reweighting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00873

- JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00722

- Q-Learning for Reachability in MEC-Free MDPs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01781

- SkillEvoLean: Mutation-enhanced skill evolution for Lean provers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01799

- Explainability of Complex AI Models with Correlation Impact Ratio
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.06701

- Local Support Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02126

- Aligning Inductive Bias for Data-Efficient Generalization in State Space Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.20789

- Universal interpolation for deep residual self-attention networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01981

- Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00647

- Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00888

- In CEM, a World Model Is Also a Proposal Mechanism
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00921

- Evasion Attacks: How Adversarial Noise Bypasses ML Classifiers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00136

- Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.15682

- Do Your Own Research: Learning to Forecast by Learning to Search
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01955

- Structure-agnostic Causal Representation Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00968

- Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01738

- Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00280

- Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00911

## Community

- Christophe Pettus: All Your GUCs in a Row: min_parallel_index_scan_size and min_parallel_table_scan_size
  Source: planet-postgresql
  Topic: PostgreSQL
  URL: https://postgr.es/p/9wW

- U.S. may have overthrown Venezuela due to chat with Grok
  Source: hacker-news
  Topic: General
  URL: https://www.thedailybeast.com/jaw-dropping-way-trump-80-got-talked-into-a-war-is-leaked/

- Why should I have to pay more for buses if I don't use a smartphone?
  Source: hacker-news
  Topic: General
  URL: https://www.theguardian.com/money/2026/oct/02/why-should-i-have-to-pay-more-for-buses-if-i-dont-use-a-smartphone

- Understanding Frontier Artificial Intelligence
  Source: hacker-news
  Topic: General
  URL: https://casp.ac/reports/intelligence-explosion

- Memory-Safe WebP Decoding
  Source: hacker-news
  Topic: General
  URL: https://halide.cx/blog/wpd/

- An Update on Orion for Linux and Windows
  Source: hacker-news
  Topic: General
  URL: https://blog.kagi.com/update-orion-linux-windows

- Rust for CPython (Python Language Summit 2026)
  Source: lobsters
  Topic: General (+Python, Rust)
  URL: https://blog.python.org/2026/09/language-summit-2026-rust-for-cpython/

- Grow and control a swarm
  Source: lobsters
  Topic: General
  URL: https://nohope.io

- Extra Big Ass Intelligence
  Source: hacker-news
  Topic: General
  URL: https://www.extrabigassintelligence.com/

- Problems and solutions to the modern desktop (Make tmux the OS)
  Source: lobsters
  Topic: General
  URL: https://matduggan.com/what-does-my-dream-os-ui-look-like/

- Cloudflare OHTTP gateway
  Source: hacker-news
  Topic: General
  URL: https://blog.cloudflare.com/announcing-cloudflare-ohttp-gateway/

- Is Claude Conscious?
  Source: hacker-news
  Topic: General (+AI)
  URL: https://www.nytimes.com/2026/09/29/us/anthropic-claude-morals-ai.html

- Do Less, So You Can Do Better
  Source: hacker-news
  Topic: General
  URL: https://www.indiehackers.com/post/do-less-so-you-can-do-it-better-3ea77e92b4

- IINA 1.5.0
  Source: hacker-news
  Topic: General
  URL: https://github.com/iina/iina/releases/tag/v1.5.0

- Introversion DEFCON 20th anniversary edition
  Source: hacker-news
  Topic: General
  URL: https://store.steampowered.com/news/app/1520/view/685264724715111073

- Hair Loss Was Just the Start. Ozempic Users Are Also Reporting Nail Trouble
  Source: hacker-news
  Topic: General
  URL: https://gizmodo.com/hair-loss-was-just-the-start-ozempic-users-are-also-reporting-nail-trouble-2000820821

- NTSB Preliminary Report: Prime Air 767 Runway Overrun [pdf]
  Source: hacker-news
  Topic: General
  URL: https://www.ntsb.gov/investigations/Documents/DCA26MA352%20Prelim.pdf

- Newgrounds.com – A community of games, music, and art
  Source: hacker-news
  Topic: General
  URL: https://www.newgrounds.com/

- Show HN: Timeline of the Far Future
  Source: hacker-news
  Topic: General
  URL: https://rivendell.dmitrybrant.com/farfuture/

- Epilepsy and multidimensional time:a perspective inspired by theoretical physics
  Source: hacker-news
  Topic: General
  URL: https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2026.1884775/full

- From Civic Tech to DOGE: The Role of Tech Movements in the American Admin State
  Source: hacker-news
  Topic: General
  URL: https://onlinelibrary.wiley.com/doi/10.1111/padm.70094

- Where Is the Planet
  Source: hacker-news
  Topic: General
  URL: http://whereistheplanet.com

- Things that apparently cause cancer
  Source: hacker-news
  Topic: General
  URL: https://www.breakthroughjournal.org/p/things-that-apparently-cause-cancer

- Cloudflare opens more Enterprise-only features to all customers
  Source: hacker-news
  Topic: General
  URL: https://blog.cloudflare.com/enterprise-for-all-update/

## Media

- black haired Hayley is terrifying 💇🏻‍♀️
  Source: youtube-docker
  Topic: DevOps
  URL: https://www.youtube.com/shorts/LGrSOQkwhZ8

- 2026 Season Recap | Rounds 9-16
  Source: youtube-docker
  Topic: DevOps
  URL: https://www.youtube.com/watch?v=3VMWDJ4bSgQ

- Replay: Open Source Friday with Mastra
  Source: youtube-github
  Topic: Open Source (+General)
  URL: https://www.youtube.com/watch?v=I541TmZiV2Q