HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit
Research
Research News
New papers, breakthroughs and academic AI research
Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM Agents
Research
DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues
Research
TempCore: Are Video QA Benchmarks Temporally Grounded?
Research
$t_0$: A Time-Series Foundation Model for Forecasting with Context
Research
GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers
Research
Information-Geometric First-Passage Monitoring of Distributional Stability in Stochastic Systems
Research
Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure
Research
PAOLI: Pose-free Articulated Object Learning from Sparse-view Images
Research
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
Research
Lifted Bellman Linear Programming for Offline Reinforcement Learning
Research
Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
Research