9 papers
Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance
Zhuobai Dong, Junchao Yi, Hu Jian Guo +3
Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Today's dominant approach distills a bidirectional diffusion model…
Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors
Yilin Wang, Xiangxi Zheng, Dongxing Mao +6
Understanding long videos with multimodal large language models (MLLMs) requires selecting a compact set of frames from thousands of candidates, yet identifying the right frames se…
TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering
Dongxing Mao, Yilin Wang, Linjie Li +2
Despite recent advances in text-to-image generation, models still struggle to accurately render prompt-specified text with correct spatial layout -- especially in multi-span, struc…
RAGEN-2: Reasoning Collapse in Agentic RL
Zihan Wang, Chi Gui, Xing Jin +13
RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. Howeve…
FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching
Junchao Yi, Rui Zhao, Jiahao Tang +7
Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking wh…
Glance: Accelerating Diffusion Models with 1 Sample
Zhuobai Dong, Rui Zhao, Songjie Wu +5
Diffusion models have achieved remarkable success in image generation, yet their deployment remains constrained by the heavy computational cost and the need for numerous inference…
VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
Kevin Qinghong Lin, Yuhao Zheng, Hangyu Ran +5
Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis…
Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents
Yiqi Lin, Alex Jinpeng Wang, Linjie Li +2
Contrastive vision-language models such as CLIP have demonstrated strong performance across a wide range of multimodal tasks by learning from aligned image-text pairs. However, the…
Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT
Zhuobai Dong, Junchao Yi, Ziyuan Zheng +5
Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While…