7 papers
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…
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…
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…
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…
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…
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…