13 papers
SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video
Weili Guan, Haoyu Zhang, Meng Liu +3
Visual-spatial understanding, defined as the ability to infer object relationships and scene layouts from visual inputs, is fundamental to downstream tasks such as robotic navigati…
SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion
Haoyu Zhang, Meng Liu, Qianlong Xiang +3
Spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation. However, existing UAV benchmarks often emphasize image-l…
MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents
Yv Zhang, Hao Sun, Hao Fang +5
External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences. However, this paradigm introduces a cri…
Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
Haoxiang Shi, Xiang Deng, Haoyu Zhang +3
Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions while navigating in real-world-like environments. Most VLN-CE…
DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
Haoxiang Shi, Xiang Deng, Zaijing Li +3
Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typic…
Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025
Qiaohui Chu, Haoyu Zhang, Yisen Feng +4
In this report, we present a novel three-stage framework developed for the Ego4D Long-Term Action Anticipation (LTA) task. Inspired by recent advances in foundation models, our met…
OSGNet @ Ego4D Episodic Memory Challenge 2025
Yisen Feng, Haoyu Zhang, Qiaohui Chu +4
In this report, we present our champion solutions for the three egocentric video localization tracks of the Ego4D Episodic Memory Challenge at CVPR 2025. All tracks require precise…
Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization
Zaijing Li, Yuquan Xie, Rui Shao +5
Developing generalist agents capable of solving open-ended tasks in visually rich, dynamic environments remains a core pursuit of embodied AI. While Minecraft has emerged as a comp…
Spatial Understanding from Videos: Structured Prompts Meet Simulation Data
Haoyu Zhang, Meng Liu, Zaijing Li +4
Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied in…
HCQA-1.5 @ Ego4D EgoSchema Challenge 2025
Haoyu Zhang, Yisen Feng, Qiaohui Chu +4
In this report, we present the method that achieves third place for Ego4D EgoSchema Challenge in CVPR 2025. To improve the reliability of answer prediction in egocentric video ques…
Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling
Qiyuan Deng, Xuefeng Bai, Kehai Chen +3
Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution s…
Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding
Haoyu Zhang, Qiaohui Chu, Meng Liu +3
AI personal assistants, deployed through robots or wearables, require embodied understanding to collaborate effectively with humans. However, current Multimodal Large Language Mode…
Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog
Haoyu Zhang, Meng Liu, Yisen Feng +3
In contrast to conventional visual question answering, video-grounded dialog necessitates a profound understanding of both dialog history and video content for accurate response ge…