中文
相关论文

相关论文: ECHO: Continuous Hierarchical Memory for Vision-La…

200 篇论文

Language model (LM) agents deployed in novel environments often exhibit poor sample efficiency when learning from sequential interactions. This significantly hinders the usefulness of such agents in environments where interaction is costly…

机器学习 · 计算机科学 2026-01-06 Michael Y. Hu , Benjamin Van Durme , Jacob Andreas , Harsh Jhamtani

Vision-Language-Action (VLA) models fail systematically on long-horizon manipulation tasks despite strong short-horizon performance. We show that this failure is not resolved by extending context length alone in the current reactive…

机器学习 · 计算机科学 2026-04-22 Zijian Zeng , Fei Ding , Huiming Yang , Xianwei Li

Recent progress in Vision-Language-Action (VLA) models has enabled embodied agents to interpret multimodal instructions and perform complex tasks. However, existing VLAs are mostly confined to short-horizon, table-top manipulation, lacking…

Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environmental variations in out-of-distribution (OOD) tasks remains fundamentally limited by the…

机器人学 · 计算机科学 2026-03-30 Zhuoran Li , Zhiyang Li , Kaijun Zhou , Jinyu Gu

Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance…

计算与语言 · 计算机科学 2025-08-01 Haoran Sun , Shaoning Zeng

While long-term memory is essential for intelligent agents to maintain consistent historical awareness, the accumulation of extensive interaction data often leads to performance bottlenecks. Naive storage expansion increases retrieval noise…

人工智能 · 计算机科学 2026-04-03 Junming Liu , Yifei Sun , Weihua Cheng , Haodong Lei , Yuqi Li , Yirong Chen , Ding Wang

Vision-Language-Action (VLA) models offer promising capabilities for autonomous driving through multimodal understanding. However, their utilization in safety-critical scenarios is constrained by inherent limitations, including imprecise…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Yiru Wang , Zichong Gu , Yu Gao , Anqing Jiang , Zhigang Sun , Shuo Wang , Yuwen Heng , Hao Sun

Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Mingqiang Wu , Weilun Feng , Zhefeng Zhang , Haotong Qin , Yuqi Li , Guoxin Fan , Xiaokun Liu , Zhulin An , Libo Huang , Yongjun Xu , Chuanguang Yang

Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it and struggle with long-horizon, temporally dependent tasks. Cognitive science suggests…

机器人学 · 计算机科学 2026-02-02 Hao Shi , Bin Xie , Yingfei Liu , Lin Sun , Fengrong Liu , Tiancai Wang , Erjin Zhou , Haoqiang Fan , Xiangyu Zhang , Gao Huang

LIBERO has emerged as a widely adopted benchmark for evaluating Vision-Language-Action (VLA) models; however, its current training and evaluation settings are problematic, often leading to inflated performance estimates and preventing fair…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Xueyang Zhou , Yangming Xu , Guiyao Tie , Yongchao Chen , Guowen Zhang , Duanfeng Chu , Pan Zhou , Lichao Sun

General-purpose robots must master long-horizon manipulation, defined as tasks involving multiple kinematic structure changes (e.g., attaching or detaching objects) in unstructured environments. While Vision-Language-Action (VLA) models…

机器人学 · 计算机科学 2026-02-26 Yue Yang , Shuo Cheng , Yu Fang , Homanga Bharadhwaj , Mingyu Ding , Gedas Bertasius , Daniel Szafir

Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often struggle in scenarios requiring precise spatial…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Tao Lin , Yuxin Du , Jiting Liu , Nuobei Zhu , Yunhe Li , Yuqian Fu , Yinxinyu Chen , Hongyi Cai , Zewei Ye , Bing Cheng , Kai Ye , Yiran Mao , Yilei Zhong , MingKang Dong , Junchi Yan , Gen Li , Bo Zhao

Error attribution in Large Language Model (LLM) multi-agent systems presents a significant challenge in debugging and improving collaborative AI systems. Current approaches to pinpointing agent and step level failures in interaction traces…

人工智能 · 计算机科学 2025-10-20 Adi Banerjee , Anirudh Nair , Tarik Borogovac

Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle…

机器人学 · 计算机科学 2026-04-16 Zhen Liu , Xinyu Ning , Zhe Hu , Xinxin Xie , Weize Li , Zhipeng Tang , Chongyu Wang , Zejun Yang , Hanlin Wang , Yitong Liu , Zhongzhu Pu

Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into…

机器人学 · 计算机科学 2025-06-03 Yi Yang , Jiaxuan Sun , Siqi Kou , Yihan Wang , Zhijie Deng

Large language models have been widely deployed in various applications, encompassing both interactive online tasks and batched offline tasks. Given the burstiness and latency sensitivity of online tasks, over-provisioning resources is…

分布式、并行与集群计算 · 计算机科学 2025-04-08 Zhibin Wang , Shipeng Li , Xue Li , Yuhang Zhou , Zhonghui Zhang , Zibo Wang , Rong Gu , Chen Tian , Kun Yang , Sheng Zhong

While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts or focus exclusively on human speech. This leaves a significant gap in real-time, sound-centric…

机器人学 · 计算机科学 2026-03-18 Chang Nie , Tianchen Deng , Guangming Wang , Zhe Liu , Hesheng Wang

Multimodal LLM agents operating in complex game environments must continually reuse past experience to solve new tasks efficiently. In this work, we propose Echo, a transfer-oriented memory framework that enables agents to derive actionable…

人工智能 · 计算机科学 2026-04-08 Chenghao Li , Jun Liu , Songbo Zhang , Huadong Jian , Hao Ni , Lik-Hang Lee , Sung-Ho Bae , Guoqing Wang , Yang Yang , Chaoning Zhang

Vision-Language-Action (VLA) models have demonstrated significant potential for embodied decision-making; however, their application in complex chemical laboratory automation remains restricted by limited long-horizon reasoning and the…

机器人学 · 计算机科学 2026-04-20 Xu Huang , Weixin Mao , Yinhao Li , Hua Chen , Jiabao Zhao

Prior Vision-Language-Action (VLA) models are typically trained on teleoperated successful demonstrations, while discarding numerous failed attempts that occur naturally during data collection. However, these failures encode where and how…

‹ 上一页 1 2 3 10 下一页 ›