AI News

⚡ 9 minutes ago
1
1
A Resilience-as-a-Service assessment framework for coordinated disruption response in interdependent urban transit systems (arxiv.org)
2
1
ZIPP:Zero-shot Image Personalization from Personas (arxiv.org)
3
1
Beyond Pass Rate: A Multilingual, Execution-Grounded Evaluation of Open Code LLMs (arxiv.org)
4
1
Constraint-Aware Optimization for Robust Protein Stability Prediction (arxiv.org)
5
1
ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning (arxiv.org)
6
1
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination (arxiv.org)
7
1
Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense (arxiv.org)
8
1
When Behavioral Safety Evaluation Fails: A Representation-Level Perspective (arxiv.org)
9
1
Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models (arxiv.org)
10
1
Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization (arxiv.org)
11
1
STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning (arxiv.org)
12
1
Q-Delta: Beyond Key-Value Associative State Evolution (arxiv.org)
13
1
Semantic Quorum Assurance: Collective Certification for Non-Deterministic AI Infrastructure (arxiv.org)
14
1
Instrumental convergence and power-seeking (arxiv.org)
15
1
Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization (arxiv.org)
16
1
CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning (arxiv.org)
17
1
Bridging Expert Knowledge and Automated Feature Engineering via Self-Evolution (arxiv.org)
18
1
RAILS: Verification-Native Clearing For Agentic Commerce (arxiv.org)
19
1
SafeECGMatch: Calibration-Aware Joint Frequency and Time Space Semi-Supervised Learning for Open-Set ECG Classification (arxiv.org)
20
1
Evaluating the Impact of Task Granularity on Catastrophic Forgetting in Continual Learning (arxiv.org)
21
1
Enhancing AI Interpretability and Safety through Localised Architectures (arxiv.org)
22
1
Overcoming the Limits of Finite Difference Method; Physics-Informed Neural Network for Noisy High-Dimensional Heat Diffusion (arxiv.org)
23
1
ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems (arxiv.org)
24
1
Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning (arxiv.org)
25
1
Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery (arxiv.org)
26
1
Minibatch Selection via Partition Matroid Constrained Gradient Matching (arxiv.org)
27
1
The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning (arxiv.org)
28
1
CAAL: Contextual Bandits based Online Hand-Craft Active Learning Strategy Selection (arxiv.org)
29
1
Layer-wise Derivative Controlled Networks Achieve Competitive Accuracy and Gradient Stability Across Data Regimes (arxiv.org)
30
1
InA-Probe: Instruction-Aware Active Probing for Time Series Forecasting with LLMs (arxiv.org)
31
1
Distilling LLM Reasoning into an Interpretable Policy Tree for Human-AI Collaboration (arxiv.org)
32
1
Quantitative Promise Theory: Intentionality and Inference in Autonomous Agents (arxiv.org)
33
1
PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR (arxiv.org)
34
1
AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions (arxiv.org)
35
1
DN-Hypo-Pipeline: An AI-Driven Workflow for Hypothesis Generation via Large Language Models and Scientific Explanations (arxiv.org)
36
1
A Regret Minimization Framework on Preference Learning in Large Language Models (arxiv.org)
37
1
Temporal Coverage over Density: Parsimonious Training-Set Design for ML Climate Downscaling (arxiv.org)
38
1
Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories (arxiv.org)
39
1
Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight Inconsistency (arxiv.org)
40
1
Still: Amortized KV Cache Compaction in a Single Forward Pass (arxiv.org)
41
1
Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation (arxiv.org)
42
1
Frequency-based Constrained Sampling for Interval Patterns (arxiv.org)
43
1
VESTA: A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents (arxiv.org)
44
1
Scaffold Effects on GAIA: A Controlled Comparison (arxiv.org)
45
1
Standpoint Logics with Defeasible Beliefs (arxiv.org)
46
1
Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets (arxiv.org)
47
1
Prescriptive Scaling Reveals the Evolution of Language Model Capabilities (arxiv.org)
48
1
On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage (arxiv.org)
49
1
More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD) (arxiv.org)
50
1
Self-Supervised Dynamical System Representations for Physiological Time-Series (arxiv.org)