Kehai Chen

Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment

HiPO: Self-Hint Policy Optimization for RLVR

Evaluating and Steering Modality Preference in Multimodal Large Language Model

Multi-Token Policy Gradient Optimization

LoCoT2V-Bench: A Benchmark for Long-Form and Complex Text-to-Video Generation

Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness

HURST: Learning Heterogeneity-Adaptive Urban Foundation Models for Spatiotemporal Prediction via Self-Partitional Mixture-of-Spatial-Experts

The Hidden Link Between RLHF and Contrastive Learning

VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metrics

SpikingLLM: Spiking Large Language Models with Causal Spiking Self-Attention and Spike-Form Knowledge Distillation

Unifying Reinforcement Learning and Distillation via Distribution Matching for Video Generation

From Bias to Balance: Exploring and Mitigating Spatial Bias in LVLMs

XBOUND: Exploring Capability Boundaries of Device-Control Agents at the State Level

Adaptive Mixing of Non-Invariant Information for Generalized Diffusion Policy

Exploring the Translation Mechanism of Large Language Models

Unified Transferability Metrics for Time Series Foundation Models

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning

MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching