AI Research

Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle

Generative AI

Computer Vision: SIFT algorithm (Scale Invariant Feature Transform)

Elegant object matching from several viewpoints The post Computer Vision: SIFT algorithm (Scale Invariant Feature Transform) appeared first on Towards Data Science.

What the Kyoto Vision Means for AI-Powered Science

Seventeen countries have endorsed the Kyoto Vision for AI-powered science. Its push toward autonomous discovery raises questions about computing access and how governments will turn policy ambitions into research…

What If AI Is a Phase in Earth’s Evolution?

Philosopher Benjamin Bratton has a much bigger way of thinking about AI: as the newest step in a billions-of-years process where matter produced life, life produced intelligence, and intelligence learned to build…

How to Build a Cheap, Yet Reliable Model Router With Jev

Model routing can finally be a design choice rather than a system enhancement The post How to Build a Cheap, Yet Reliable Model Router With Jev appeared first on Towards Data Science.

😺 Trump named an AI czar

What Nvidia and AMD’s AI Acquisitions Say About the Next Chip War

Nvidia’s planned Hugging Face acquisition and AMD’s World Labs deal bring both chipmakers closer to the developers and researchers shaping future AI workloads, giving them an earlier view of how compute requirements may…

Recursive Agent Optimization

arXiv:2605.06639v2 Announce Type: replace Abstract: We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to new…

Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens

arXiv:2610.03001v1 Announce Type: new Abstract: Extracellular electrophysiology records a different set of neurons in every session. Neural foundation models embed each neuron and each session into their tokens, so…

CRISP: A Framework for Clause-Reconstructed Interpretable NeuroSymbolic Propositions

arXiv:2610.02431v1 Announce Type: new Abstract: Deep neural networks achieve high accuracy through layered numerical transformations, yet their decisions remain difficult to audit because decision evidence is encoded in…

Divergence controls entropy in distillation

arXiv:2610.03529v1 Announce Type: new Abstract: Distillation has become a core primitive of large language model training, but its properties are not yet well understood. We take an entropic perspective, studying how…

BaCP: Backbone Contrastive Pruning for Preserving Representations in Extremely Sparse Neural Networks

arXiv:2610.02524v1 Announce Type: new Abstract: Unstructured pruning at extreme sparsity often suffers from representational collapse, causing sharp drops in accuracy. To address this, we study Backbone Contrastive…

VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation

arXiv:2505.13439v2 Announce Type: replace-cross Abstract: Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps…

ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing

arXiv:2610.02808v1 Announce Type: cross Abstract: Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, information…

Autonomous Robotic Navigation for Endovascular Brain-Computer Interface Access

arXiv:2610.03537v1 Announce Type: cross Abstract: Endovascular brain-computer interfaces (BCIs) avoid craniotomy but require precise device delivery through anatomically variable cerebral veins. This work presents the…

Unifying Distributional Training for One-Step Visual Generation

arXiv:2609.35763v4 Announce Type: replace Abstract: Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representation spaces. We…

Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRA

arXiv:2610.00610v2 Announce Type: replace-cross Abstract: Explainable suicide-risk assessment requires models not only to estimate risk severity, but also to identify supporting language and the risk and protective…

HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents

arXiv:2610.03574v1 Announce Type: cross Abstract: We introduce HyperBrowseComp, a multilingual and multimodal browsing benchmark comprising 423 manually authored and human-validated questions across 13 languages,…

What Does a ProcGen Generalization Gap Measure? Action Rules, Residual Entropy, and the Missing Random Floor

arXiv:2609.32532v2 Announce Type: replace Abstract: A generalization gap in reinforcement learning, return on training levels minus return on held-out levels, is usually reported without a reference point. We argue that…

Inner Momentum for Differentially Private Muon

arXiv:2610.02738v1 Announce Type: new Abstract: Differentially private training clips each per-example gradient before adding noise. This clipping is radial for each example, yet unequal clipping factors can distort the…