paper-with-me

Papers

CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity

2025-06-19 · Guang Yin, Yitong Li, YiXuan Wang, Dale McConachie, Paarth Shah, Kunimatsu Hashimoto, huan zhang, Katherine Liu, Yunzhu Li

Natural language instructions for robotic manipulation tasks often exhibit ambiguity and vagueness. For instance, the instruction "Hang a mug on the mug tree" may involve multiple valid actions if there are several mugs and branches to choose from. Existing language-conditioned policies typically rely on end-to-end models that jointly handle high-level semantic understanding and low-level action generation, which can result in suboptimal performance due to their lack of modularity and interpretability. To address these challenges, we introduce a novel robotic manipulation framework that can accomplish tasks specified by potentially ambiguous natural language. This framework employs a Vision-Language Model (VLM) to interpret abstract concepts in natural language instructions and generates task-specific code - an interpretable and executable intermediate representation. The generated code interfaces with the perception module to produce 3D attention maps that highlight task-relevant regions by integrating spatial and semantic information, effectively resolving ambiguities in instructions. Through extensive experiments, we identify key limitations of current imitation learning methods, such as poor adaptation to language and environmental variations. We show that our approach excels across challenging manipulation tasks involving language ambiguity, contact-rich manipulation, and multi-object interactions.

📄 PDF Abstract BibTeX arXiv:2506.16652

Code (0)

등록된 구현이 없습니다.

Tasks

Action GenerationContact-rich ManipulationImitation Learning

Similar Papers 제목 키워드 기반

Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization

2024-05-25 · Shutong Ding, Ke Hu, Zhenhao Zhang, Kan Ren 외

Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the…

continuous-controlContinuous ControlMuJoCoOffline RL+3

Implicit Search via Discrete Diffusion: A Study on Chess

2025-02-27 · Jiacheng Ye, Zhenyu Wu, Jiahui Gao, Zhiyong Wu 외

In the post-AlphaGo era, there has been a renewed interest in search techniques such as Monte Carlo Tree Search (MCTS), particularly in their application to Large Language Models (LLMs). This renewed attention is driven …

Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models

2024-09-11 · Jiahang Cao, Qiang Zhang, Jingkai Sun, Jiaxu Wang 외

Diffusion models have been widely employed in the field of 3D manipulation due to their efficient capability to learn distributions, allowing for precise prediction of action trajectories. However, diffusion models typic…

Mamba

FlightDiffusion: Revolutionising Autonomous Drone Training with Diffusion Models Generating FPV Video

2025-09-17 · Valerii Serpiva, Artem Lykov, Faryal Batool, Vladislav Kozlovskiy 외 arxiv

We present FlightDiffusion, a diffusion-model-based framework for training autonomous drones from first-person view (FPV) video. Our model generates realistic video sequences from a single frame, enriched with correspond…

Trajectory Planning

GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion

2026-02-26 · Enda Xiang, Haoxiang Ma, Xinzhu Ma, Zicheng Liu 외 arxiv

This paper focuses on enhancing the grasping precision and generalization of manipulation policies learned via imitation learning. Diffusion-based policy learning methods have recently become the mainstream approach for …