AI News

Value-Aware Stochastic KV Cache Eviction for Reasoning Models (arxiv.org)

Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein Embedding (arxiv.org)

PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization (arxiv.org)

Finding Needles in the Haystack: Transductive Active Labeling in Ecology (arxiv.org)

PHASE: Physiology-Aware Hyperspectral Reconstruction via Object-to-Human Domain Adaptation (arxiv.org)

Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation (arxiv.org)

Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference (arxiv.org)

Causal Evidence of Stack Representations in Modeling Counter Languages Using Transformers (arxiv.org)

Reproducibility is the New Copyleft: Defining AGI-oriented Reproducible Builds (arxiv.org)

NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense (arxiv.org)

Resource-Constrained Adaptive Inference for Sequential Pricing (arxiv.org)

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward (arxiv.org)

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

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs (arxiv.org)

Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics (arxiv.org)

PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy for Spiking Vision Transformers (arxiv.org)

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning (arxiv.org)

Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering (arxiv.org)

PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion (arxiv.org)

The Epi-LLM Framework: probing LLM behavioral priors through epidemiological agent-based models (arxiv.org)

Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It) (arxiv.org)

Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic (arxiv.org)

Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition (arxiv.org)

WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents (arxiv.org)

LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems (arxiv.org)

RobotValues: Evaluating Household Robots When Human Values Conflict (arxiv.org)

From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models (arxiv.org)

Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation (arxiv.org)

Easy-to-Use Shielding for Reinforcement Learning (arxiv.org)

Learning to See via Epiretinal Implant Stimulation in silico with Model-Based Deep Reinforcement Learning (arxiv.org)

FlashbackCL: Mitigating Temporal Forgetting in Federated Learning (arxiv.org)

TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching (arxiv.org)

FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data (arxiv.org)

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

Constitutional On-Policy Safe Distillation (arxiv.org)

The DeepSpeak-Agentic Dataset (arxiv.org)

Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making (arxiv.org)

Glass Box at Orbit: A Constitutional AI Verification Framework for Trustworthy Autonomous CubeSat Intelligence (arxiv.org)

Dynamic Short Convolutions Improve Transformers (arxiv.org)

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

EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents (arxiv.org)

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning (arxiv.org)

Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs (arxiv.org)

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

Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching (arxiv.org)

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

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

FederatedSkill: Federated Learning for Agentic Skill Evolution (arxiv.org)

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

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