From the 2 of 7 linked papers with an AI index.
7 papers
RetroHolmes: When Semantic Plausibility Fails Retrospective Physical Process Reasoning
Ruoxuan Zhang, Qiyun Zheng, Siyu Wu +12
The paper presents RetroHolmes, a benchmark for testing vision‑language models on retrospective physical process reasoning—inferring hidden causes from image outcomes—and shows tha…
MindClaw: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
Ruoxuan Zhang, Qiaoqiao Wan, Zhengguang Wang +4
The paper introduces MindClaw, a closed-loop framework that lets embodied agents reason about human mental states in real time and intervene only when assistance is needed.
Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning
Wenke Xia, Pei Ren, Wenbo Yu +10
Offline-to-online reinforcement learning is promising for generalizable robotic manipulation, yet its full-stack complexity obscures reproduction and diagnosis. Within such systems…
Latent Policy Steering through One-Step Flow Policies
Hokyun Im, Andrey Kolobov, Jianlong Fu +1
Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration. Yet, offline RL's performance often hinges on a brittle trade-off betwee…
Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity
Che-Sang Park, Junsu Ha, Jianlong Fu +1
Sampling action chunks via generative models has become a widely adopted methodology for robotic learning from demonstration. However, existing methods often struggle to balance re…
MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents
Ruoxuan Zhang, Qiyun Zheng, Zhiyu Zhou +7
Theory of Mind (ToM) refers to the ability to infer others' mental states, such as beliefs, desires, and intentions. Current vision-language embodied agents lack ToM-based decision…