返回首页

端到端

共 46 篇论文

cs.CL端到端Transformer

The Autonomy Tax: Defense Training Breaks LLM Agents

Large language model agents increasingly rely on external tools such as file operations, API calls, and database transactions to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against prompt injection attacks that manipulate agent behavior through malicious observations. This paper reveals a fundamental capability-alignment paradox where defense training designed to improve safety systematically destroys agent competence while failing to prevent sophisticated attacks. Evaluating defended models against undefended baselines across 97 agent tasks and 1,000 adversarial prompts, we uncover three systematic biases unique to multi-step agents including agent incompetence bias manifesting as immediate tool execution breakdown and cascade amplification bias causing early failures to propagate through retry loops. These findings demonstrate that current defense training approaches create significant trade-offs between safety and functional capability in autonomous LLM agents.

Anonymous Authors
about 1 month ago
arXiv 2603.19423v1
cs.RO端到端CV

Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation

This paper presents Speculative Policy Orchestration (SPO), a novel latency-resilient framework designed for cloud-robotics manipulation tasks. The proposed approach enables robots to offload computationally intensive motion planning to remote cloud servers while maintaining stable high-frequency control at the edge. By utilizing a cloud-hosted world model to pre-compute and stream kinematic waypoints, the system effectively decouples execution frequency from network round-trip latency. To ensure safe operation, an epsilon-tube verifier bounds kinematic execution errors, preventing unsafe predictive drift. Additionally, an Adaptive Horizon Scaling mechanism dynamically adjusts the speculative pre-fetch depth based on real-time tracking performance. The framework is validated through continuous manipulation experiments on RLBench under emulated network delay conditions.

Anonymous Authors
about 1 month ago
arXiv 2603.19418v1
cs.CV端到端CV

VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models

This paper presents VAMPO, a post-training framework that improves visual dynamics in video action models for robot control. The key contribution is formulating multi-step denoising as a sequential decision process and optimizing the denoising policy with rewards defined over expert visual dynamics in latent space. The approach addresses the objective mismatch in current diffusion-based video predictors by explicitly optimizing precision-critical visual dynamics needed for manipulation tasks.

VAMPO Authors
about 1 month ago
arXiv 2603.19370v1
cs.CV端到端CV

MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

This paper presents MonoArt, a unified framework for reconstructing articulated 3D objects from single images through progressive structural reasoning. The method addresses the challenge of inferring object geometry, part structure, and motion parameters from limited visual evidence without direct articulation regression. By progressively transforming visual observations into canonical geometry, structured part representations, and motion-aware embeddings within a single architecture, the framework enables stable and interpretable articulation inference without external templates or multi-stage pipelines. The approach is validated on articulated object datasets demonstrating effective 3D reconstruction of objects with movable parts.

MonoArt Team
about 1 month ago
arXiv 2603.19231v1
cs.CV端到端CV

ATG-MoE: Autoregressive trajectory generation with mixture-of-experts for assembly skill learning

This paper presents ATG-MoE, an end-to-end autoregressive trajectory generation method with mixture-of-experts architecture for robot assembly skill learning from demonstration. The method processes multi-modal inputs including RGB-D observations, natural language instructions, and robot proprioception to generate manipulation trajectories in a closed-loop manner. It incorporates multi-modal feature fusion for comprehensive scene and task understanding, autoregressive sequence modeling for temporally coherent trajectory generation, and a mixture-of-experts architecture enabling unified multi-skill learning. The approach addresses challenges in flexible manufacturing where robot systems must adapt to changing tasks, objects, and environments without labor-intensive traditional programming.

ATG-MoE Authors
about 1 month ago
arXiv 2603.19029v1
cs.RO端到端Transformer

RoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids

This paper presents RoboForge, a unified latent-driven framework for text-guided whole-body humanoid locomotion. The approach bridges natural language and physical robot execution through a retarget-free pipeline that couples motion generation and control bidirectionally. A Physical Plausibility Optimization module serves as the coupling interface, refining teacher-student distillation policies with plausibility-centric rewards to eliminate physical artifacts like floating, skating, and penetration. This work enables humanoid robots to execute natural language-directed motions with improved physical feasibility.

RoboForge Authors
about 1 month ago
arXiv 2603.17927v2
上一页第 3 / 3 页