AI News

DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data (arxiv.org)

Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction (arxiv.org)

When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning (arxiv.org)

Proof-Refactor: Refactoring Generated Formal Proofs into Modular Artifacts (arxiv.org)

LAP: An Agent-to-Instrument Protocol for Autonomous Science (arxiv.org)

From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework (arxiv.org)

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis (arxiv.org)

Bayesian Tensor Decomposition with Diffusion Model Prior (arxiv.org)

Learning Temporal Causal Structure via Smooth Differentiable Optimization (arxiv.org)

GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond (arxiv.org)

IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension (arxiv.org)

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning (arxiv.org)

SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents (arxiv.org)

Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria (arxiv.org)

Calibrating Urban Traffic Simulation from Sparse Road Observations via Genetic Optimization (arxiv.org)

BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents (arxiv.org)

EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management (arxiv.org)

Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression (arxiv.org)

When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming (arxiv.org)

EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs (arxiv.org)

Let There Be Light: Reflection, Refraction and Scattering for Neural Operators (arxiv.org)

Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles (arxiv.org)

A Geometric Lens on Physics-Aligned Data Compression (arxiv.org)

scTranslation: A Comprehensive Benchmark for Single-Cell Multi-Omics Modality Translation (arxiv.org)

Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning (arxiv.org)

Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection (arxiv.org)

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models (arxiv.org)

TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches (arxiv.org)

Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective (arxiv.org)

Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis (arxiv.org)

A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation (arxiv.org)

Validation-Gated Multi-Agent Governance for Online Adaptation of Thermal-Hydraulic Surrogate Models under Operating-Regime Shift (arxiv.org)

Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs (arxiv.org)

IdiomX A Multilingual Benchmark for Idiom Understanding, Retrieval, and Interpretation (arxiv.org)

Lean-GAP: A Dataset of Formalized Graduate Algebra Problems (arxiv.org)

Tracking Urban Atmospheric Pollutants using Sentinel-5P Satellite Data (arxiv.org)

Samudra 2: Scaling Ocean Emulators across Resolutions (arxiv.org)

Margin Play: A Multi-Agent System For Public Policy Analysis In The Brazilian Equatorial Margin (arxiv.org)

FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations (arxiv.org)

Closed-Loop Molecular Design with Calibrated Deference (arxiv.org)

Oscillatory State-Space Models as Inductive Biases for Physics-Informed Neural PDE Solvers (arxiv.org)

TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering (arxiv.org)

DXA-Derived Skeletal Phenotypes and Hip Fracture Risk: A Backdoor-Adjusted Causal Analysis (arxiv.org)

DMF: A Deterministic Memory Framework for Conversational AI Agents (arxiv.org)

Calibration Data Trade-offs Across Capability Dimensions: Why Multi-Source Mixing Matters for High-Sparsity LLM Pruning (arxiv.org)

MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety (arxiv.org)

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences (arxiv.org)

Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals (arxiv.org)

SegTune: Structured and Fine-Grained Control for Song Generation (arxiv.org)

Sparse-View Lung Nodule Volumetry from Digitally Reconstructed Radiographs via AReT: Anatomy-Regularized TensoRF (arxiv.org)