Yongliang Shen

MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task

Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models

VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models

Label-free GUI Grounding via Confidence-guided Negative Reinforcement Learning

IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models

mGRPO: Unlocking LLM Reasoning through Multilingual Thinking

GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts

EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes

UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization

Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning

TimeHC-RL: Temporal‑aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence

Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning

Chain-of-Model Learning for Language Model

Let LRMs Break Free from Overthinking via Self-Braking Tuning

Entering Real Social World! Benchmarking the Theory of Mind and Socialization Capabilities of LLMs from a First-person Perspective