2 citations · 3 across the 22 of their papers we have counts for
22 papers
Beyond the Single Camera: Agentic Multi-View Reasoning in Sports Video Understanding
Kerui Chen, Jinglu Wang, Xiaoyi Zhang +1
Recent Multimodal Large Language Models (MLLMs) achieve strong performance on single-view video understanding benchmarks. However, sports videos involve dense occlusion, rapid moti…
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Senqiao Yang, Kaichen Zhang, Zhaoyang Jia +20
Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process…
Generative Video Compression with Adaptive Score Distillation
Naifu Xue, Zhaoyang Jia, Haosen Li +7
Diffusion models provide strong generative capabilities for video compression at ultra-low bitrates. Existing diffusion-based video codecs adapt base models originally developed fo…
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Xinjie Zhang, Peng Zhang, Shicheng Zheng +21
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to…
Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft
Juheon Yi, Jinglu Wang, Xiaoyi Zhang +1
We present TickingCollabBench, a Minecraft-based multi-agent benchmark for a novel class of time-sensitive complementary collaboration tasks. Our benchmark reflects four core chara…
From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations
Yuchen Guan, Xiao Li, Zongyu Guo +4
We propose a new paradigm for long video understanding by treating a long video as a Neural Knowledge Representation (NKR). NKR represents video contents neither as a stream of tok…
Ultra-Fast Neural Video Compression
Jiahao Li, Wenxuan Xie, Zhaoyang Jia +4
While neural video codecs (NVCs) have demonstrated superior compression ratio, their prohibitive computational complexity remains a critical barrier to real-world deployment. This…
An Efficient Streaming Video Understanding Framework with Agentic Control
Jinming Liu, Jianguo Huang, Zhaoyang Jia +7
Streaming video requires handling dynamic information density under strict latency budgets. Yet, existing methods typically employ static strategies, such as fixed memory compressi…
CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
Zhaoyang Jia, Naifu Xue, Zihan Zheng +7
Recent advanced diffusion methods typically derive strong generative priors by scaling diffusion transformers. However, scaling fails to generalize when adapted for real-time compr…
Generative Video Compression with One-Dimensional Latent Representation
Zihan Zheng, Zhaoyang Jia, Naifu Xue +7
Recent advancements in generative video codec (GVC) typically encode video into a 2D latent grid and employ high-capacity generative decoders for reconstruction. However, this para…
Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
Zongyu Guo, Jiajun He, Zhaoyang Jia +6
Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external…
From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation
Zezhou Wang, Ziyun Zhang, Xiaoyi Zhang +2
Vision-language models are increasingly deployed as computer-use agents (CUAs) that operate desktops and browsers. Top-performing CUAs are framework-based systems that decompose pl…
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
Ziyun Zhang, Zezhou Wang, Xiaoyi Zhang +4
GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the…
CoD: A Diffusion Foundation Model for Image Compression
Zhaoyang Jia, Zihan Zheng, Naifu Xue +6
Existing diffusion codecs typically build on text-to-image diffusion foundation models like Stable Diffusion. However, text conditioning is suboptimal from a compression perspectiv…
Generative Latent Video Compression
Zongyu Guo, Zhaoyang Jia, Jiahao Li +3
Perceptual optimization is widely recognized as essential for neural compression, yet balancing the rate-distortion-perception tradeoff remains challenging. This difficulty is espe…
VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models
Tianci Bi, Xiaoyi Zhang, Yan Lu +1
The performance of Latent Diffusion Models (LDMs) is critically dependent on the quality of their visual tokenizers. While recent works have explored incorporating Vision Foundatio…
Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Model
Xueyu Liu, Xiaoyi Zhang, Guangze Shi +4
Prompt quality plays a critical role in the performance of the Segment Anything Model (SAM), yet existing approaches often rely on heuristic or manually crafted prompts, limiting s…
UI-Evol: Automatic Knowledge Evolving for Computer Use Agents
Ziyun Zhang, Xinyi Liu, Xiaoyi Zhang +3
External knowledge has played a crucial role in the recent development of computer use agents. We identify a critical knowledge-execution gap: retrieved knowledge often fails to tr…
Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo +4
Long-form video understanding presents significant challenges due to extensive temporal-spatial complexity and the difficulty of question answering under such extended contexts. Wh…
UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis
Xinyi Liu, Xiaoyi Zhang, Ziyun Zhang +1
Recent advancements in Large Vision-Language Models are accelerating the development of Graphical User Interface (GUI) agents that utilize human-like vision perception capabilities…
Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis
Tianci Bi, Xiaoyi Zhang, Zhizheng Zhang +4
Significant progress has been made in scene text detection models since the rise of deep learning, but scene text layout analysis, which aims to group detected text instances as pa…
Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API
Zhizheng Zhang, Wenxuan Xie, Xiaoyi Zhang +1
Recent popularity of Large Language Models (LLMs) has opened countless possibilities in automating numerous AI tasks by connecting LLMs to various domain-specific models or APIs, w…