7 papers
EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
Ruofei Ju, Xinrui Wang, Xin Ding +12
Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments. Since embodied environments vary across layouts,…
ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies
Bingjia Huang, Xiangyu Li, Xiang Wang +7
Generative robot policies fail unpredictably at deployment: they hesitate at critical moments, drift off-task, or commit to unrecoverable actions. Existing online failure detectors…
GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models
Mingzhe Huang, Weijun Wang, Xin Ding +7
In Vision-Language Models (VLMs), processing a massive number of visual tokens incurs prohibitive computational overhead. While recent training-aware pruning methods attempt to sel…
Efficient Remote KV Cache Reuse with GPU-native Video Codec
Liang Mi, Weijun Wang, Jinghan Chen +3
Remote KV cache reuse fetches KV cache for identical contexts from remote storage, avoiding recomputation, accelerating LLM inference. While it excels in high-speed networks, its p…
SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution
Guoying Zhu, Meng Li, Haipeng Dai +6
The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consum…
AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation
Xin Ding, Jianyu Wei, Yifan Yang +10
Vision Language Navigation (VLN) requires agents to follow natural language instructions by grounding them in sequential visual observations over long horizons. Explicit reasoning…