Dawei Yin

CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval

GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication

Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents

Surgical Trimming: Minimal Sufficient Chain of Thought with RazorReward-RL

Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation

Long-Attention Weaving: Synthesizing Long-Context Data with High-Quality Short Data

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization

Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning

JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework

Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering