Vision-Language Models (VLMs) have achieved strong performance in visual perception and spatial reasoning, leading to growing interest in using them as high-level planners for embodied AI. However, physical tasks require models to integrate spatial information, reason over temporal states, and generate multi-step plans...
Jun Feng, Qin-Gan Liu, Jing-Ru Dong et al.· 0 citations
Latent world models offer a promising way to improve Vision-Language-Action policies by capturing the consequences of actions. However, models trained primarily on expert demonstrations have limited exposure to failure outcomes and may struggle to distinguish visually similar successful and failed interactions. We prop...
Lin Liu, Lu Zhang, Zi-Ying Song et al.· 0 citations
GUI agents accumulate high-resolution screenshots as the trajectory unfolds, increasing inference latency and memory usage. Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint. Once tokens are discarded, the corresponding visual evidence cannot be recovered witho...
Yu-Hao Wang, Mu Qiao, Xin-Dong Zhang et al.· 0 citations
Streaming video understanding requires Video Large Language Models (Video-LLMs) to reason over continuous visual streams under causal constraints. As the visual history grows, a bounded visual?processing budget requires evidence selection that balances temporal recency with query relevance. Recent-only selection exclud...
Xiang Hu, Jia-Zuo Yu, Lu Zhang et al.· 0 citations
Visual object tracking aims to continuously locate specific targets within sequential frames, evolving from single-modal methods to multi-modal ones. However, existing multi-modal trackers are typically designed for fixed modality combinations, requiring separate models for different inputs. This leads to a poor adapta...
Hao Li, Yun-Zhi Zhuge, Wenning Hao et al.· 0 citations
GROVE is introduced, a training-free framework that supports both behaviors with one memory grown causally from a continuous video stream, and achieves the best results among the compared methods.
Sitong Gong, Caixin Kang, Tianyu Yan et al.· 0 citations
This work demonstrates that the aligned LLM with a general-purpose vision encoder can effectively enhance downstream VQA performance with task-specific encoders, and investigates several alignment strategies between the aligned LLM and new task-specific encoders.
Jiazuo Yu, Yunzhi Zhuge, Lu Zhang et al.· International Journal of Com...· 0 citations
ERA establishes logit-preserving visual token pruning as a principled framework for efficient MLLMs, unifying theoretical foundation, algorithmic design, and practical deployment.
Yuhao Wang, Mu Qiao, Haiwen Diao et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
