12 papers
Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation
Chuyao Fu, Xiaowei Chi, Yuhan Rui +14
A common approach to world-model simulation for vision-language-action (VLA) systems is to predict future RGB observations and then re-encode them into policy inputs, introducing a…
WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT
Zezhong Qian, Xiaowei Chi, Yu Qi +3
Recent World-Action (WA) models demonstrate strong generalization ability and data efficiency, but they typically rely on expert trajectories for training. This reliance limits the…
When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance
Jinjin Cao, Zhiyang Chen, Zijun Wang +3
Vision-Language Models (VLMs) have shown solid ability for multimodal understanding of both visual and language contexts. However, existing VLMs often face severe challenges of hal…
Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models
Zemin Huang, Yuhang Wang, Zhiyang Chen +1
Mask-based Diffusion Language Models (DLMs) struggle to revise incorrect tokens: once a token is generated, it typically remains fixed. The key challenge is to identify potential e…
C-Evolve: Consensus-based Evolution for Prompt Groups
Tiancheng Li, Yuhang Wang, Zhiyang Chen +3
Prompt evolution algorithms offer a powerful paradigm for enhancing AI systems based on closed-source models, while few work explores whether aggregating results from multiple prom…
SLOT: Sample-specific Language Model Optimization at Test-time
Yang Hu, Xingyu Zhang, Xueji Fang +4
We propose SLOT (Sample-specific Language Model Optimization at Test-time), a novel and parameter-efficient test-time inference approach that enhances a language model's ability to…
InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO
Xueji Fang, Liyuan Ma, Zhiyang Chen +2
Recent advances in text-to-video generation, particularly with autoregressive models, have enabled the synthesis of high-quality videos depicting individual scenes. However, extend…
Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
Zemin Huang, Zhiyang Chen, Zijun Wang +2
We introduce the Diffusion Chain of Lateral Thought (DCoLT), a reasoning framework for diffusion language models. DCoLT treats each intermediate step in the reverse diffusion proce…
Self-Guidance: Boosting Flow and Diffusion Generation on Their Own
Tiancheng Li, Weijian Luo, Zhiyang Chen +2
Proper guidance strategies are essential to achieve high-quality generation results without retraining diffusion and flow-based text-to-image models. Existing guidance either requi…
Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation
Zilyu Ye, Zhiyang Chen, Tiancheng Li +3
Diffusion and flow matching models have achieved remarkable success in text-to-image generation. However, these models typically rely on the predetermined denoising schedules for a…
SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment
Jie Wang, Yichen Wang, Zhilin Zhang +3
With strong expressive capabilities in Large Language Models(LLMs), generative models effectively capture sentiment structures and deep semantics, however, challenges remain in fin…
Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling
Zilyu Ye, Jinxiu Liu, Ruotian Peng +9
Recent image generation models excel at creating high-quality images from brief captions. However, they fail to maintain consistency of multiple instances across images when encoun…