6 papers
BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent
Yibin Huang, Bin Xu, Hailong Cao +1
Multi-step search is a fundamental capability for search agents, enabling them to iteratively acquire, refine, and integrate external evidence for complex reasoning QA. However, va…
World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
Wanyue Zhang, Wenxiang Wu, Wang Xu +6
Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scene…
Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning
Yibin Huang, Wang Xu, Wanyue Zhang +6
Spatial intelligence is a critical frontier for Multimodal Large Language Models (MLLMs), empowering them to comprehend the physical world. Drawing inspiration from human perceptio…
MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues
Yaning Pan, Qianqian Xie, Guohui Zhang +13
The recent development of Multimodal Large Language Models (MLLMs) has significantly advanced AI's ability to understand visual modalities. However, existing evaluation benchmarks…
MM-UAVBench: How Well Do Multimodal Large Language Models See, Think, and Plan in Low-Altitude UAV Scenarios?
Shiqi Dai, Zizhi Ma, Zhicong Luo +8
While Multimodal Large Language Models (MLLMs) have exhibited remarkable general intelligence across diverse domains, their potential in low-altitude applications dominated by Unma…
Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture
Wanyue Zhang, Yibin Huang, Yangbin Xu +5
Spatial understanding is essential for Multimodal Large Language Models (MLLMs) to support perception, reasoning, and planning in embodied environments. Despite recent progress, ex…