AI News

⚡ 1 minute ago
1
1
In Defense of Information Leakage in Concept-based Models (arxiv.org)
2
1
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs (arxiv.org)
3
1
It\^o maps for any-step SDEs (arxiv.org)
4
1
ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs (arxiv.org)
5
1
Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations (arxiv.org)
6
1
SpenseGPT: Practical One-shot Pruning Enabling Sparse and Dense GEMMs for LLM Inference (arxiv.org)
7
1
Parallel Causal Associative Fields: Gated Sparse Memory for Long-Context Language Modeling (arxiv.org)
8
1
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration (arxiv.org)
9
1
Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing (arxiv.org)
10
1
Fast Exact Nearest-Neighbor Learning for High-Frequency Financial Time Series (arxiv.org)
11
1
A Source Domain is All You Need: Source-Only Cross-OS Transfer Learning for APT Anomaly Detection via Semantic Alignment and Optimal Transport (arxiv.org)
12
1
Automated Pronunciation Evaluation for Korean Toddler Speech using Speech Diarization and Self-Supervised Learning (arxiv.org)
13
1
KG-SoftMAP: Soft Knowledge-Graph Priors for Bayesian Network Structure Learning from Sparse Discrete Data (arxiv.org)
14
1
Beyond Explaining Predictions: Logic-Based Explanations for Confidence in Machine Learning Models (arxiv.org)
15
1
Privacy-Preserving Credit Risk Prediction with Alternative Data (arxiv.org)
16
1
Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks (arxiv.org)
17
1
Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning (arxiv.org)
18
1
Making Time Editable in Video Diffusion Transformers (arxiv.org)
19
1
Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs (arxiv.org)
20
1
Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI (arxiv.org)
21
1
Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community (arxiv.org)
22
1
Failure Modes of Deep Multi-Agent RL in Asynchronous Pricing: Reproducible Triggers, Trace Diagnostics, and a Partial Fix (arxiv.org)
23
1
Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS (arxiv.org)
24
1
CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks (arxiv.org)
25
1
Agentic Social Affordance Framework (ASAF): Agent Identity Design as a Collaboration Interface in Multi-Agent Systems (arxiv.org)
26
1
AI-Driven Analytics of Team-Teaching Talk: Acoustic Patterns across Experience, Cohorts and the Learning Design (arxiv.org)
27
1
TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition (arxiv.org)
28
1
Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding (arxiv.org)
29
1
Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows (arxiv.org)
30
1
SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning (arxiv.org)
31
1
Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output (arxiv.org)
32
1
Machine Learning Methods for Studying Latent Neural Activity Dynamics (arxiv.org)
33
1
Flexible Flows for Biological Sequence Design (arxiv.org)
34
1
Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners (arxiv.org)
35
1
Towards Diverse Scientific Hypothesis Search with Large Language Models (arxiv.org)
36
1
Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting (arxiv.org)
37
1
Embedding Hybrid Systems into Continuous Latent Vector Fields (arxiv.org)
38
1
Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting (arxiv.org)
39
1
Geometry-Aware Reinforcement Learning for 2D Irregular Nesting (arxiv.org)
40
1
Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agents (arxiv.org)
41
1
Exploratory Responsiveness and Adaptive Rigidity under AI-Assisted Optimization (arxiv.org)
42
1
Predictive Assistance and the Temporal Dynamics of Exploratory Compression (arxiv.org)
43
1
From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs (arxiv.org)
44
1
IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts (arxiv.org)
45
1
Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning (arxiv.org)
46
1
Is Fairness Truly Fair? Towards Reliable Lipschitz Fairness in Multi-Task Learning via Fixed-\texorpdfstring{$\delta$}{delta} Alignment (arxiv.org)
47
1
PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models (arxiv.org)
48
1
From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models (arxiv.org)
49
1
Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization (arxiv.org)
50
1
Event-Driven Reinforcement Learning Enables Long-Horizon Control in Semiconductor Fabrication (arxiv.org)