AI News

LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models (arxiv.org)

Spatiotemporal Multi-Task Graph Transformer for Trip-Level Transit Prediction (arxiv.org)

On the Limits of Token Reduction for Efficient Unified Vision Language Training (arxiv.org)

FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors (arxiv.org)

Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems (arxiv.org)

Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery (arxiv.org)

SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems (arxiv.org)

ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment (arxiv.org)

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback (arxiv.org)

Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation (arxiv.org)

On the Difficulty of Learning a Meta-network for Training Data Selection (arxiv.org)

On the Recoverability of Causal Relations from Bulk Gene Expression Data (arxiv.org)

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models (arxiv.org)

Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics (arxiv.org)

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning (arxiv.org)

Interpretable Policy Distillation for Power Grid Topology Control (arxiv.org)

Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction (arxiv.org)

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain (arxiv.org)

Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures (arxiv.org)

The Assistant as a Privileged Persona: A canonical reference in cross-persona self-recognition (arxiv.org)

WildCat: Near-Linear Attention in Theory and Practice (arxiv.org)

Collaborative and Efficient Fine-tuning: Leveraging Task Similarity (arxiv.org)

Universal One-third Time Scaling in Learning Peaked Distributions (arxiv.org)

Independent Component Discovery in Temporal Count Data (arxiv.org)

Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients (arxiv.org)

Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear $q^\pi$-Realizability and Concentrability (arxiv.org)

Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\"om Approximation (arxiv.org)

Human in the Loop Adaptive Optimization for Improved Time Series Forecasting (arxiv.org)

Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation (arxiv.org)

Advancing Local Clustering on Graphs via Compressive Sensing: Semi-supervised and Unsupervised Methods (arxiv.org)

Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models (arxiv.org)

Targeted Data Fusion for Region-Specific Survival Effects in the AMP HIV Prevention Trials (arxiv.org)

VERA: Variational Inference Framework for Jailbreaking Large Language Models (arxiv.org)

Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings (arxiv.org)

Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters (arxiv.org)

Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity (arxiv.org)

Dynamic Proxy-Mixing: Transferring Replay Controllers from Small to Large Models for Continual Instruction Tuning (arxiv.org)

TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection (arxiv.org)

Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation (arxiv.org)

Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Submissions (arxiv.org)

Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach (arxiv.org)

Subliminal Learning Is Steering Vector Distillation (arxiv.org)

Quantum Reservoir Computing and Risk Bounds (arxiv.org)

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning (arxiv.org)

Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization (arxiv.org)

CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs (arxiv.org)

How Much Orthogonalization Does Muon Need? (arxiv.org)

Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support (arxiv.org)

Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States (arxiv.org)

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition (arxiv.org)