3 papers
cs.CV2026
PanoAffordanceNet: Towards Holistic Affordance Grounding in 360° Indoor Environments
Guoliang Zhu, Wanjun Jia, Caoyang Shao +3
Global perception is essential for embodied agents in 360° spaces, yet current affordance grounding remains largely object-centric and restricted to perspective views. To bridge th…
cs.LG2025
AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity
Yu Zhang, Dong Guo, Fang Wu +3
Large Language Models (LLMs) with extended context lengths face significant computational challenges during the pre-filling phase, primarily due to the quadratic complexity of self…
cs.CV2025
Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts
Yizhou Huang, Fan Yang, Guoliang Zhu +6
Affordance refers to the functional properties that an agent perceives and utilizes from its environment, and is key perceptual information required for robots to perform actions.…