23 citations · 60 across the 20 of their papers we have counts for
21 papers · 1 filter
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…
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…
Depth Anything 3: Recovering the Visual Space from Any Views
Haotong Lin, Sili Chen, Junhao Liew +5
We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of…
Trace Anything: Representing Any Video in 4D via Trajectory Fields
Xinhang Liu, Yuxi Xiao, Donny Y. Chen +4
Effective spatio-temporal representation is fundamental to modeling, understanding, and predicting dynamics in videos. The atomic unit of a video, the pixel, traces a continuous 3D…
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…
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
Xiangtai Li, Tao Zhang, Yanwei Li +13
Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack t…
Seed1.5-VL Technical Report
Dong Guo, Faming Wu, Feida Zhu +194
We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter v…
Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding
Tao Zhang, Xiangtai Li, Zilong Huang +6
Multimodal Large Language Models (MLLMs) achieve remarkable performance for fine-grained pixel-level understanding tasks. However, all the works rely heavily on extra components, s…
The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer
Weixian Lei, Jiacong Wang, Haochen Wang +4
This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architect…
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…
4th PVUW MeViS 3rd Place Report: Sa2VA
Haobo Yuan, Tao Zhang, Xiangtai Li +5
Referring video object segmentation (RVOS) is a challenging task that requires the model to segment the object in a video given the language description. MeViS is a recently propos…
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
Sili Chen, Hengkai Guo, Shengnan Zhu +4
Depth Anything has achieved remarkable success in monocular depth estimation with strong generalization ability. However, it suffers from temporal inconsistency in videos, hinderin…
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…
Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
Haotong Lin, Sida Peng, Jingxiao Chen +7
Prompts play a critical role in unleashing the power of language and vision foundation models for specific tasks. For the first time, we introduce prompting into depth foundation m…
Image Understanding Makes for A Good Tokenizer for Image Generation
Luting Wang, Yang Zhao, Zijian Zhang +3
Abstract Modern image generation (IG) models have been shown to capture rich semantics valuable for image understanding (IU) tasks. However, the potential of IU models to improve I…
Classification Done Right for Vision-Language Pre-Training
Zilong Huang, Qinghao Ye, Bingyi Kang +2
We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text…
How Far is Video Generation from World Model: A Physical Law Perspective
Bingyi Kang, Yang Yue, Rui Lu +5
OpenAI's Sora highlights the potential of video generation for developing world models that adhere to fundamental physical laws. However, the ability of video generation models to…
Depth Anything V2
Lihe Yang, Bingyi Kang, Zilong Huang +4
This work presents Depth Anything V2. Without pursuing fancy techniques, we aim to reveal crucial findings to pave the way towards building a powerful monocular depth estimation mo…
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
Lianghui Zhu, Zilong Huang, Bencheng Liao +4
Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT)…
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Lihe Yang, Bingyi Kang, Zilong Huang +3
This work presents Depth Anything, a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerfu…
Harnessing Diffusion Models for Visual Perception with Meta Prompts
Qiang Wan, Zilong Huang, Bingyi Kang +2
The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable profic…