activity
20242026
collaborators

7 papers

cs.CL2026

Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models

Yawen Shao, Jie Xiao, Kai Zhu +6

Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constraine…

cs.CV2026

Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model

Pingyu Wu, Kai Zhu, Yu Liu +6

Autoregressive image generation aims to predict the next token based on previous ones. However, this process is challenged by the bidirectional dependencies inherent in conventiona…

cs.LG2025

Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment

Yawen Shao, Jie Xiao, Kai Zhu +4

Group Relative Policy Optimization (GRPO) has proven highly effective in enhancing the alignment capabilities of Large Language Models (LLMs). However, current adaptations of GRPO…

cs.CV2025

WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens

Jian Yang, Dacheng Yin, Xiaoxuan He +6

Recent progress in multimodal large language models (MLLMs) has highlighted the challenge of efficiently bridging pre-trained Vision-Language Models (VLMs) with Diffusion Models. W…

cs.CV2025

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning

Fan Lu, Wei Wu, Kecheng Zheng +7

Generating detailed captions comprehending text-rich visual content in images has received growing attention for Large Vision-Language Models (LVLMs). However, few studies have dev…

cs.CV2025

VanGogh: A Unified Multimodal Diffusion-based Framework for Video Colorization

Zixun Fang, Zhiheng Liu, Kai Zhu +5

Video colorization aims to transform grayscale videos into vivid color representations while maintaining temporal consistency and structural integrity. Existing video colorization…