works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.RO2026

Embodied Agents Take Control: Minimal-Interface Zero-Shot Agents Rival Industrial-Scale Policies in Vision-and-Language Navigation

Jian Zhou, Xunyi Zhao, Gengze Zhou +4

The paper investigates using general-purpose language models as autonomous embodied agents for zero-shot vision-and-language navigation, showing that with only a monocular RGB came…

cs.CV2026

Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation

Xunyi Zhao, Sihao Lin, Gengze Zhou +5

Instance Goal Navigation (IGN) requires an embodied agent to find a specific object instance among distractors from an under-specified natural-language description. Such ambiguity…

cs.RO2026

TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models

Wenbo Zhang, Jianxiong Li, Shuai Yang +4

Vision-Language-Action (VLA) models trained on large-scale data have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time. Recent VLA mode…

cs.RO2026

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

Wenbo Zhang, Tianrun Hu, Hanbo Zhang +7

We present Chain-of-Action (CoA), a novel visuo-motor policy paradigm built upon Trajectory Autoregressive Modeling. Unlike conventional approaches that predict next step action(s)…

cs.CV2025

VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation

Sihao Lin, Zerui Li, Xunyi Zhao +10

Despite remarkable progress in Vision-Language Navigation (VLN), existing benchmarks remain confined to fixed, small-scale datasets with naive physical simulation. These shortcomin…

cs.AI2025

The Singapore Consensus on Global AI Safety Research Priorities

Yoshua Bengio, Tegan Maharaj, Luke Ong +84

Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy,…