AI News

ChartEvo: Self-Evolving Agent Harnesses for Long-Tail Chart Reasoning (arxiv.org)

Is Sycophancy a Form of In-Context Updating? (arxiv.org)

Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere? (arxiv.org)

Dissecting the Impact of Model Misspecification in Data-driven Optimization (arxiv.org)

PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models (arxiv.org)

Federated Learning: From Theory to Practice (arxiv.org)

Accelerating Optimization via Differentiable Stopping Time (arxiv.org)

Rethinking Generalization in Knowledge Graph Embedding: An Empirical Study and Sparse Peak Regularization (arxiv.org)

S-Agent 2.0: Spatial Reasoning with a General Coding Agent (arxiv.org)

FALCA: Falsification-Aware Reinforcement Learning with Hierarchical Credit Assignment for Long-Horizon Deep Search Agents (arxiv.org)

RACE: RoPE-Aligned Attention Compression Based on Query-Key Activation Energies (arxiv.org)

DIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous Streams (arxiv.org)

Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity (arxiv.org)

Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization (arxiv.org)

Beyond Trajectory Statistics: Community-Consistent Human Mobility Generation via Evolving User-Location Graphs (arxiv.org)

Claims of emergence in AI should be grounded in information decomposition (arxiv.org)

Robust Residual Correction via Selective Deployment for Time Series Forecasting (arxiv.org)

Evaluating utility of clinical prediction models: A comparison of decision curve analysis and cost curves (arxiv.org)

Curriculum-Augmented GFlowNets For mRNA Sequence Generation (arxiv.org)

Exploring Temporal Context-Aware Physical Grounding in Latent World Models (arxiv.org)

Proof-Carrying Contracts: Commitments AI Agents Cannot Break (arxiv.org)

An LLM-Based Agent for Legal Compliance Assessment: Architecture, Memory, and Evaluation in a Canadian and Quebec Context (arxiv.org)

Selecting the Best Few with Human Evaluators: Adaptively Combining Ratings and Pairwise Comparisons (arxiv.org)

A Jointly Efficient and Near-Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions (arxiv.org)

What Does the Rank Buy? A Spectral and Distributional Analysis of Low-Rank Adaptation (arxiv.org)

Certifiably Correct Fr\'echet Means in Orbit Spaces (arxiv.org)

Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation (arxiv.org)

A Simple and General Approach to top-$k$ Selection (arxiv.org)

LocaLeJEPA: Maximum Entropy Representations under Geometric Priors (arxiv.org)

Geometry-Agnostic Data-Driven Discovery of Extreme Scenarios (arxiv.org)

Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks (arxiv.org)

Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs (arxiv.org)

ECG for laboratory values:A comprehensive physiological and technical analysis (arxiv.org)

GraphCast-Mamba: Learning Non-Markovian Corrections for Weather Forecasting (arxiv.org)

From Crawled to Published: A Publisher-Controlled Web Architecture for an AI-Native Internet (arxiv.org)

When does Subgroup Balance Matter? Predicting Performance Sensitivity from Latent Separability (arxiv.org)

Efficient Edge-aware Attention Network for Graph Generation (arxiv.org)

Discount Yourself: Self-inclusive Freshness-weighted Gossip for Decentralised Learning under Client Outages (arxiv.org)

Learning Computational Structure for Sample-Efficient Prediction (arxiv.org)

When Do LLMs Help with Feature Selection? A Systematic Empirical Study (arxiv.org)

Convergence of stochastic gradient descent for learning linear neural networks (arxiv.org)

Asymmetric Bidirectional Predictive Dynamics in Google Search and COVID-19 Time Series: A Multi-Horizon Forecast-Error Analysis (arxiv.org)

OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction (arxiv.org)

Reinforced Linear Genetic Programming (arxiv.org)

Activation Sensitivity as a Unifying Principle for Post-Training Quantization (arxiv.org)

Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling (arxiv.org)

TTCS: Test-Time Curriculum Synthesis for Self-Evolving (arxiv.org)

The Dynamics of Collapse and Recovery in Clustered Federated Learning (arxiv.org)

The Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per Token (arxiv.org)

Continuous-Time Policy Gradient from Discrete Data: Convergence Analysis and Model-Free Algorithms (arxiv.org)