Showing 1–20 of 22 results
/ Date/ Name
Apr 15, 2026Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and BottlenecksApr 5, 2026Can LLMs Learn to Reason Robustly under Noisy Supervision?Feb 24, 2026VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-EvaluationFeb 23, 2026LAD: Learning Advantage Distribution for ReasoningFeb 23, 2026How Retrieved Context Shapes Internal Representations in RAGFeb 8, 2026Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged AgentsFeb 4, 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and OpportunitiesJan 27, 2026How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic InterpretabilityJan 7, 2026Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMsJan 5, 2026ModeX: Evaluator-Free Best-of-N Selection for Open-Ended GenerationOct 8, 2025When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent ReasoningOct 5, 2025LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon InteractionsOct 1, 2025How Well Can Preference Optimization Generalize Under Noisy Feedback?Sep 28, 2025Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM AlignmentSep 27, 2025Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language ModelsSep 27, 2025General Exploratory Bonus for Optimistic Exploration in RLHFSep 27, 2025Understanding Language Prior of LVLMs by Contrasting Chain-of-EmbeddingSep 26, 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge SignalsSep 4, 2025GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language ModelsMay 25, 2025MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems