14 papers
: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training
Nan Qiao, Yebin Yang, Weinong Wang +10
Reinforcement mid-training lets language models learn internal thoughts from unlabeled text, but efficient token-level credit assignment remains challenging. Existing group-relativ…
WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
Yubo Zhu, Yawen Shao, Ziyun Dai +27
Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 seconds and faithfully follow…
VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision
Zhehan Kan, Yubo Zhu, Xinghua Jiang +10
While Vision-Language Models (VLMs) demonstrate strong capabilities, they continue to suffer from a critical limitation: insufficient fine-grained visual perception, which fundamen…
UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
Zhehan Kan, Xinghua Jiang, Yubo Zhu +10
Despite remarkable advancements in multimodal large language models (MLLMs), their fine-grained visual understanding is constrained by a primary reliance on sparse textual supervis…
When Does Visual Generation Help Visual Understanding in Unified Multimodal Models?
Yubo Zhu, Zhehan Kan, Jingyi Yang +6
Unified multimodal models (UMMs) can perform both understanding and generation, raising a central question: can visual generation improve understanding? Existing evaluations provid…
MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation
Dongxia Liu, Jie Ma, Xiaochen Yang +7
The creation of cinematic-quality animal effects necessitates the precise modeling of muscle and fur dynamics, a process that remains both labor-intensive and computationally expen…
ActFER: Agentic Facial Expression Recognition via Active Tool-Augmented Visual Reasoning
Shifeng Liu, Zhengye Zhang, Sirui Zhao +7
Recent advances in Multimodal Large Language Models (MLLMs) have created new opportunities for facial expression recognition (FER), moving it beyond pure label prediction toward re…
Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
Zhixiang Wei, Yi Li, Zhehan Kan +38
Despite the significant advancements represented by Vision-Language Models (VLMs), current architectures often exhibit limitations in retaining fine-grained visual information, lea…
TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs
Zhehan Kan, Yanlin Liu, Kun Yin +8
DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs). While recent methods have attempted to replicate R1's reasoning capabilities in multimoda…
Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
Ce Zhang, Zifu Wan, Zhehan Kan +7
While recent Large Vision-Language Models (LVLMs) have shown remarkable performance in multi-modal tasks, they are prone to generating hallucinatory text responses that do not alig…
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
Zhehan Kan, Ce Zhang, Zihan Liao +7
Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing sig…
Learning Visual Conditioning Tokens to Correct Domain Shift for Fully Test-time Adaptation
Yushun Tang, Shuoshuo Chen, Zhehan Kan +3
Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradat…
Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation
Zhehan Kan, Shuoshuo Chen, Ce Zhang +2
A central challenge in human pose estimation, as well as in many other machine learning and prediction tasks, is the generalization problem. The learned network does not have the c…
Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation
Zhehan Kan, Shuoshuo Chen, Zeng Li +1
We observe that human poses exhibit strong group-wise structural correlation and spatial coupling between keypoints due to the biological constraints of different body parts. This…