Qiguang Chen

Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models

AutoPR: Let's Automate Your Academic Promotion!

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks

On the Measurement and Efficient Mitigation of Length Generalization Gaps in Large Language Models

Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation

Agent2World: A Unified LLM-based Multi-Agent Framework for Symbolic World-Model Generation

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

SciDA: Scientific Dynamic Assessor of LLMs

COIG-Writer: A High-Quality Chinese Creative Writing with Thought Process Dataset

Boundary-to-Region Supervision for Offline Safe Reinforcement Learning

Efficient Process Reward Model Training via Active Learning

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions

Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought

What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices

In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks

KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing