16 papers
ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning
Yike Wu, Keyan Chen, Qixiong Wang +6
Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, but indiscriminate computation…
What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training Strategies
Duo Li, Haojun Pan, Zuhao Yang +4
Contrastive learning has become the standard paradigm for multimodal representation learning, aligning semantically matched pairs while separating mismatched ones in a shared embed…
ReMem: Streaming Video Understanding With Long Context Retention
Li Yiheng, He Xu, Wang Shaobo +2
Despite their impressive performance on a wide range of video understanding tasks, current Vision Language Models (VLMs) are predominantly designed for offline scenarios and strugg…
CodeActionBench: Evaluating Agentic Code-as-Policy for Embodied Manipulation
Yiheng Lyu, Xueying Jiang, Wenhao Li +2
How well can general-purpose multimodal models turn visual understanding and reasoning into embodied manipulation via executable code? We introduce CodeActionBench, a benchmark of…
DocClaw: A Unified Agentic System for Intelligent Document Processing
Siqi Xiang, Zhipeng Xu, Yufei Liu +6
Intelligent document processing (IDP) encompasses a broad range of tasks, including optical character recognition (OCR), document question answering (DocQA), and key information ex…
3D-Aware VLMs with Implicit and Explicit Geometries
Wenhao Li, Xueying Jiang, Quanhao Qian +4
Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial unde…
From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
Wenhao Li, Xueying Jiang, Quanhao Qian +4
Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios. Existing vie…
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
Zuhao Yang, Kaichen Zhang, Sudong Wang +7
Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video unders…
Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs
Xueying Jiang, Wenhao Li, Quanhao Qian +4
3D localization in Multimodal Large Language Models (MLLMs), including 3D object detection and 3D visual grounding, is fundamentally limited by camera intrinsic ambiguity: the same…
Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
Haoyuan Sun, Jing Wang, Yuxin Song +9
Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for furth…
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Keming Wu, Zuhao Yang, Kaichen Zhang +24
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning…
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Zuhao Yang, Sudong Wang, Kaichen Zhang +8
Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when proc…
A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models
Duo Li, Zuhao Yang, Xiaoqin Zhang +2
Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding a…
TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding
Zuhao Yang, Yingchen Yu, Yunqing Zhao +2
Video Temporal Grounding (VTG) aims to precisely identify video event segments in response to textual queries. The outputs of VTG tasks manifest as sequences of events, each define…
Versatile Transition Generation with Image-to-Video Diffusion
Zuhao Yang, Jiahui Zhang, Yingchen Yu +2
Leveraging text, images, structure maps, or motion trajectories as conditional guidance, diffusion models have achieved great success in automated and high-quality video generation…
ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
Duo Li, Zuhao Yang, Xiaoqin Zhang +2
Visual token pruning, which aims to compress and prune redundant visual tokens, plays a critical role in efficient inference with large vision-language models (LVLMs). However, exi…