AI News

How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference? (arxiv.org)

Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models (arxiv.org)

Markov Chain Convergence in Kernel-Induced Geometry (arxiv.org)

SLICE: Sequential Likelihood-Free Inference via Conformal E-Values (arxiv.org)

SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire (arxiv.org)

Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM (arxiv.org)

SelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular Data (arxiv.org)

Model-agnostic Knowledge Augmented Machine Learning for Weakly Annotated Bioimaging Data (arxiv.org)

SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle (arxiv.org)

COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering (arxiv.org)

LeWAM: End-to-End World and Action Modeling with JEPAs (arxiv.org)

Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search (arxiv.org)

REDaCT: Collapse-Free Unlearning in Large Reasoning Models (arxiv.org)

Meta-Reflective Evolution Effectively Improves Production AI Systems (arxiv.org)

Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries (arxiv.org)

Trajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving Data (arxiv.org)

KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting (arxiv.org)

Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR (arxiv.org)

Unsupervised Multimodal Reward Modeling (arxiv.org)

AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits (arxiv.org)

Energy-Efficient Spiking Neural Networks for Sensing-Aided Beam Prediction (arxiv.org)

Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination (arxiv.org)

Critical Mass: Structure-Disjoint Splits Drift With the Libraries They Are Built On (arxiv.org)

Expert-level detection of low-voltage intervals in EEG as a robust biomarker of neonatal encephalopathy (arxiv.org)

Recurrent Harness for Agentic Continual Learning (arxiv.org)

Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization (arxiv.org)

Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study (arxiv.org)

Can Language Models Play the Wikipedia Game? (arxiv.org)

RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics (arxiv.org)

X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems (arxiv.org)

Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga (arxiv.org)

Primal-Dual Flow Matching for Sample-Wise Constrained Generation (arxiv.org)

SynAct: Synergistic Active Feedback Learning for LLM Agents (arxiv.org)

Machine Learning and Time-Series Foundation Models for Day-Ahead Electricity Forecasting in a University Building (arxiv.org)

STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules (arxiv.org)

DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models (arxiv.org)

UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes (arxiv.org)

A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning (arxiv.org)

Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy (arxiv.org)

A Baseline Assessment for the Agentic Web Technology Stack (arxiv.org)

A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO (arxiv.org)

An all-transistor physical-learning transformer can be trained to perform in-context learning (arxiv.org)

Sample-Adaptive Zeroth-Order Post-Training (arxiv.org)

CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration (arxiv.org)

GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer (arxiv.org)

Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights (arxiv.org)

LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management (arxiv.org)

Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents (arxiv.org)

EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents (arxiv.org)

Provenance-Aware Belief Updating in Human-AI Feedback Loops (arxiv.org)