21 papers
From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents
Yue Zhang, Han Lin, Zun Wang +3
Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agent needs to learn. Existing env…
Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation
Atin Pothiraj, Jaemin Cho, Yue Zhang +2
Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Compounding this is a la…
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
Yidong Huang, Zun Wang, Han Lin +6
Generating realistic human motion is a central yet unsolved challenge in video generation. While reinforcement learning (RL)-based post-training has driven recent gains in general…
LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment
Junyi Hu, Qiji Zhou, Lei Zhang +1
Zero-shot visual recognition often depends on localized parts, attributes, and textures that are diluted in global image representations. Existing training-free localized methods a…
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
Ziyang Wang, Yue Zhang, Shoubin Yu +6
Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems, must reason over an entire day or more of continuous visual experienc…
3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience
Hongcan Xiao, Xinyue Xiao, Yilin Wang +2
Sketching in 3D space enables expressive reasoning about shape, structure, and spatial relationships, yet generating 3D sketches through natural language remains a major challenge.…
Gym-V: A Unified Vision Environment System for Agentic Vision Research
Fanqing Meng, Lingxiao Du, Jiawei Gu +9
As agentic systems increasingly rely on reinforcement learning from verifiable rewards, standardized ``gym'' infrastructure has become essential for rapid iteration, reproducibilit…
A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding
Yue Zhang, Liqiang Jing, Jia Li +4
Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos remains limited. Existing approa…
V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
Han Lin, Xichen Pan, Zun Wang +4
Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel…
VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
Daeun Lee, Shoubin Yu, Yue Zhang +1
Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still…
Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution
Nithin Sivakumaran, Shoubin Yu, Hyunji Lee +4
Chain-of-thought (CoT) reasoning sometimes fails to faithfully reflect the true computation of a large language model (LLM), hampering its utility in explaining how LLMs arrive at…
AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
Zun Wang, Han Lin, Jaehong Yoon +3
Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory-based approaches often condition gene…
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
Shoubin Yu, Yue Zhang, Zun Wang +4
Despite rapid progress in MLLMs, visual spatial reasoning remains unreliable when correct answers depend on how a scene would appear under unseen or alternative viewpoints. Recent…
Hierarchy-Aware Multimodal Unlearning for Medical AI
Fengli Wu, Vaidehi Patil, Jaehong Yoon +2
Pretrained Multimodal Large Language Models (MLLMs) are increasingly used in sensitive domains such as medical AI, where privacy regulations like HIPAA and GDPR require specific re…
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
Tianyi Niu, Justin Chih-Yao Chen, Genta Indra Winata +6
Large Language Model (LLM) routers dynamically select optimal models for given inputs. Existing approaches typically assume access to ground-truth labeled data, which is often unav…
DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
Nithin Sivakumaran, Justin Chih-Yao Chen, David Wan +4
Specialized visual tools can augment large language models or vision language models with expert knowledge (e.g., grounding, spatial reasoning, medical knowledge, etc.), but knowin…
Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering
Noah Frahm, Prakrut Patel, Yue Zhang +3
Large vision-language models (VLMs) have improved embodied question answering (EQA) agents by providing strong semantic priors for open-vocabulary reasoning. However, when used dir…
Planning with Sketch-Guided Verification for Physics-Aware Video Generation
Yidong Huang, Zun Wang, Han Lin +5
Recent video generation approaches increasingly rely on planning intermediate control signals such as object trajectories to improve temporal coherence and motion fidelity. However…
Error-Driven Scene Editing for 3D Grounding in Large Language Models
Yue Zhang, Zun Wang, Han Lin +5
Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. This limitation stems in part from train…
MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation
Shoubin Yu, Yue Zhang, Ziyang Wang +2
Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diver…
EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
Zun Wang, Jaemin Cho, Jialu Li +4
Recent approaches for video generation with camera control often create anchor videos (i.e., rendered videos that approximate desired camera motions) to guide diffusion models as a…