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…
Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
arXiv:2610.00911v1 Announce Type: cross Abstract: We study an endogenous nonstationary stochastic bandit problem with latent linear dynamics, where actions affect both immediate rewards and the future evolution of an…
Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics
arXiv:2610.00280v1 Announce Type: new Abstract: A world model learns to forecast how a physical system evolves from recorded trajectories, yet the systems it imitates obey physical laws that are neither fully supplied…
Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses
arXiv:2610.01738v1 Announce Type: cross Abstract: Asynchronous online learning offers temporal flexibility at a structural cost: learning communities tend to fragment rather than cohere. $\beta_0$, the number of…
Structure-agnostic Causal Representation Learning
arXiv:2610.00968v1 Announce Type: new Abstract: Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods require specifying the…
Do Your Own Research: Learning to Forecast by Learning to Search
arXiv:2610.01955v1 Announce Type: new Abstract: Outcome-based reinforcement learning can train language models to forecast real-world events, but prior forecasting work either freezes research context before training or…
Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling
arXiv:2607.15682v3 Announce Type: replace Abstract: Learned dynamical proposals can generate configurations without providing a tractable endpoint density. Nonequilibrium path probabilities offer a way to correct such…
Evasion Attacks: How Adversarial Noise Bypasses ML Classifiers
arXiv:2610.00136v1 Announce Type: cross Abstract: This paper presents a reproducible, educational study of evasion attacks in image classification and text classification. A compact convolutional network trained on…
In CEM, a World Model Is Also a Proposal Mechanism
arXiv:2610.00921v1 Announce Type: new Abstract: The cross-entropy method (CEM) uses world-model scores to select action sequences and fit the distribution sampled in its next iteration. A scoring error can therefore…
Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads
arXiv:2610.00888v1 Announce Type: new Abstract: Multi-token prediction (MTP) improves the throughput of autoregressive generation by enabling the language model to draft multiple next tokens per forward pass, while a…
Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky
arXiv:2610.00647v1 Announce Type: new Abstract: The representations that language models learn for concepts such as months, weekdays, and places display consistent geometric structure: circles and saddle-shaped…
Universal interpolation for deep residual self-attention networks
arXiv:2610.01981v1 Announce Type: new Abstract: Universal approximation is a necessary qualitative property of learning architectures to benefit from scaling laws. While it is generically verified on a variety of neural…
Aligning Inductive Bias for Data-Efficient Generalization in State Space Models
arXiv:2509.20789v5 Announce Type: replace Abstract: The remarkable success of modern AI has been closely tied to scaling laws, yet the finite supply of high-quality data makes data efficiency--learning more from…
Local Support Learning
arXiv:2610.02126v1 Announce Type: new Abstract: We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometric problem in the input space of each weight matrix,…
Explainability of Complex AI Models with Correlation Impact Ratio
arXiv:2601.06701v2 Announce Type: replace Abstract: Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment. Common post hoc AI explainers,…
SkillEvoLean: Mutation-enhanced skill evolution for Lean provers
arXiv:2610.01799v1 Announce Type: new Abstract: Skill evolution offers a promising way to improve large language model agents without updating their parameters, but its use in formal theorem proving remains…
Q-Learning for Reachability in MEC-Free MDPs
arXiv:2610.01781v1 Announce Type: cross Abstract: Reinforcement learning (RL) for reachability specifications is fundamental to sequential decision-making. Prior work establishes asymptotic convergence to optimal…
JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
arXiv:2610.00722v1 Announce Type: new Abstract: World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those…
Rethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype Reweighting
arXiv:2610.00873v1 Announce Type: new Abstract: In many industrial applications, 1) tabular data is scarce and imbalanced and thus requires synthetic expansion; 2) input distributions drift between training and…
Loading more...
502 items available