Mingli Song

Incentivizing LLM Reasoning via Reinforcement Learning with Functional Monte Carlo Tree Search

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking

CASPO: Confidence-aware Step-wise Preference Optimization for Reliable Reasoning in Large Language Models

Towards Enhanced Image Generation via Multi-Modal Chain of Thought in Unified Generative Models

Token-level Inference-Time Alignment for Vision-Language Models

Activation with Intrinsic-Extrinsic Consensus

Reinforcement Learning with Missing Context to Mitigate Reward Hacking from Training Only on Golden Answers

PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency

L-Diffusion: Laplace Diffusion for Efficient Pathology Image Segmentation

Dataset Ownership Verification in Contrastive Pre-trained Models

SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data

Association-Focused Path Aggregation for Graph Fraud Detection

Tree of Preferences for Diversified Recommendation

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater

STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification

From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks

Revisiting Differentially Private Algorithms for Decentralized Online Learning

A Large-scale Universal Evaluation Benchmark For Face Forgery Detection

Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

Tri-Comparison Expertise Decision for Drug-Target Interaction Mechanism Prediction

PruningBench: A Comprehensive Benchmark of Structural Pruning

Odyssey: Empowering Minecraft Agents with Open-World Skills

Is the Fairness Metric Truly Fair?