14 papers
EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
Tianwei Xiong, Jun Hao Liew, Zilong Huang +3
Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancin…
Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs
Haochen Wang, Yuhao Wang, Tao Zhang +13
While Multimodal Large Language Models (MLLMs) excel at holistic understanding, they struggle in capturing the dense world with complex scenes, requiring fine-grained analysis of i…
Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
Haochen Wang, Xiangtai Li, Zilong Huang +9
Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate…
SuperCLIP: CLIP with Simple Classification Supervision
Weiheng Zhao, Zilong Huang, Jiashi Feng +1
Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent find…
Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos
Haobo Yuan, Xiangtai Li, Tao Zhang +8
This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, whic…
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
Tianwei Xiong, Jun Hao Liew, Zilong Huang +2
In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for…