Measuring the Creativity Potential of LLM Agents
Trying to answer the question of "Can LLM agents discover?" through the lens of creativity The post Measuring the Creativity Potential of LLM Agents appeared first on Towards Data Science.
Topic - Edition
AI Research
How to Use a PINN for a Navier-Stokes Inverse Problem
A from-scratch PyTorch build that recovers blood flow, viscosity, and wall shear stress in a narrowed artery from 40 noisy velocity readings The post How to Use a PINN for a Navier-Stokes Inverse Problem appeared first…
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a frozen or EMA version of…
Polylogarithmic Sparsity of Randomly Reweighted NPMLEs for Gaussian Mixtures
arXiv:2610.01088v1 Announce Type: cross Abstract: The nonparametric maximum likelihood estimator (NPMLE) of a Gaussian location mixture maximizes the likelihood over the infinite-dimensional space of mixing…
Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
arXiv:2610.01375v1 Announce Type: new Abstract: A user's movie, news, and dialogue histories differ in their native actions and outputs, yet each interaction supplies evidence that can update user memory. We study…
EvoGen-Harness: Learning Where and How to Evolve Image-Generation Harnesses
arXiv:2610.00383v1 Announce Type: new Abstract: Modern text-to-image (T2I) systems can be improved without modifying generator parameters by adapting the external system around frozen generators. However, existing…
ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs
arXiv:2610.00431v1 Announce Type: cross Abstract: Continual parameter-efficient fine-tuning for large language models (LLMs) must balance retention of previously acquired knowledge, adaptation to new tasks, and strict…
Capabilities Ain't All You Need: Measuring Propensities in AI
arXiv:2602.18182v5 Announce Type: replace Abstract: AI evaluation has primarily focused on measuring capabilities, with formal approaches inspired from Item Response Theory (IRT) being increasingly applied. Yet…
MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection
arXiv:2610.01819v1 Announce Type: new Abstract: Benchmark gains are often mechanism-ambiguous: reproducing an improvement does not by itself identify why it occurs. We study finite-library mechanism discrimination,…
Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry
arXiv:2610.01947v1 Announce Type: new Abstract: Large language models offer a promising foundation for chemical reasoning, bringing together chemical knowledge and multistep problem solving. Chemical intuition can…
Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models
arXiv:2610.00661v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel. Reinforcement…
Function-Structured Reinforcement Learning with Executable Verifiers for Mathematical Reasoning
arXiv:2610.01729v1 Announce Type: new Abstract: Algorithmic mathematical reasoning requires reliable decomposition, computation, and aggregation. Final-answer rewards provide limited guidance on intermediate errors,…
On the Escaping Efficiency of Distributed Adversarial Training Algorithms
arXiv:2509.11337v2 Announce Type: replace Abstract: Adversarial training has been widely studied in recent years due to its role in improving model robustness against adversarial attacks. This paper focuses on comparing…
Flow-Transformed Implicit Processes for Function-Space Variational Inference
arXiv:2606.01954v2 Announce Type: replace Abstract: Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling.…
Comedic Fool's Gold: Reward Exploits and Countermeasures in Conversational Humor
arXiv:2610.00197v1 Announce Type: cross Abstract: We investigate automated rewards for training language models in conversational humor, focusing on reward exploits and countermeasures. Two approaches aim to capture…
Interpreting Reasoning of Large Language Models via Partial Information Decomposition
arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive, or erroneous…
FairSSL: Fair Multimodal Self-Supervised Learning
arXiv:2508.16748v2 Announce Type: replace Abstract: Prevalent multimodal self-supervised learning (SSL) methods rely on the redundancy assumption: that different views share substantial task-relevant information. We…
Benchmarking System One decision models against trained classifiers and language models for automated decision gates
arXiv:2610.00346v1 Announce Type: new Abstract: Software that hands branching decisions to a model needs a declared option and a probability it can threshold. Typed decision models, also called System One models, return…
Auto-Formalizing Neuro-Symbolic Predictors
arXiv:2610.01519v1 Announce Type: new Abstract: Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified constraints, making…
Generation Provenance Before Behavior Attribution: Auditing Synthetic Speech Research Objects
arXiv:2610.01378v1 Announce Type: cross Abstract: Attributing model behavior to synthetic training data requires knowing what produced each training item before estimating what that item caused. A waveform-label pair…
Loading more...
502 items available