中文
相关论文

相关论文: MiraBench: Evaluating Action-Conditioned Reliabili…

200 篇论文

Human safety awareness gaps often prevent the timely recognition of everyday risks. In solving this problem, a proactive safety artificial intelligence (AI) system would work better than a reactive one. Instead of just reacting to users'…

计算与语言 · 计算机科学 2025-10-21 Youliang Yuan , Wenxiang Jiao , Yuejin Xie , Chihao Shen , Menghan Tian , Wenxuan Wang , Jen-tse Huang , Pinjia He

Visual-Language-Action (VLA) models report impressive success rates on robotic manipulation benchmarks, yet these results may mask fundamental weaknesses in robustness. We perform a systematic vulnerability analysis by introducing…

Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has…

Fetching, which includes approaching, grasping, and retrieving, is a critical challenge for robot manipulation tasks. Existing methods primarily focus on table-top scenarios, which do not adequately capture the complexities of environments…

机器人学 · 计算机科学 2024-10-21 Beining Han , Meenal Parakh , Derek Geng , Jack A Defay , Gan Luyang , Jia Deng

The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, hallucination, and strategic deception that resist mitigation…

人工智能 · 计算机科学 2026-02-23 Xingcheng Xu , Jingjing Qu , Qiaosheng Zhang , Chaochao Lu , Yanqing Yang , Na Zou , Xia Hu

We investigate the real-time estimation of human situation awareness using observations from a robot teammate with limited visibility. In human factors and human-autonomy teaming, it is recognized that individuals navigate their…

机器人学 · 计算机科学 2025-02-13 Jack Kolb , Karen M. Feigh

This paper introduces Amazon Robotic Manipulation Benchmark (ARMBench), a large-scale, object-centric benchmark dataset for robotic manipulation in the context of a warehouse. Automation of operations in modern warehouses requires a robotic…

机器人学 · 计算机科学 2023-03-30 Chaitanya Mitash , Fan Wang , Shiyang Lu , Vikedo Terhuja , Tyler Garaas , Felipe Polido , Manikantan Nambi

It is unclear whether strong forecasting performance reflects genuine temporal understanding or the ability to reason under contextual and event-driven conditions. We introduce TemporalBench, a multi-domain benchmark designed to evaluate…

人工智能 · 计算机科学 2026-02-17 Muyan Weng , Defu Cao , Wei Yang , Yashaswi Sharma , Yan Liu

Image editing has achieved remarkable progress recently. Modern editing models could already follow complex instructions to manipulate the original content. However, beyond completing the editing instructions, the accompanying physical…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Yuandong Pu , Le Zhuo , Songhao Han , Jinbo Xing , Kaiwen Zhu , Shuo Cao , Bin Fu , Si Liu , Hongsheng Li , Yu Qiao , Wenlong Zhang , Xi Chen , Yihao Liu

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…

计算与语言 · 计算机科学 2026-03-04 Aradhye Agarwal , Gurdit Siyan , Yash Pandya , Joykirat Singh , Akshay Nambi , Ahmed Awadallah

Understanding human perceptions of robot performance is crucial for designing socially intelligent robots that can adapt to human expectations. Current approaches often rely on surveys, which can disrupt ongoing human-robot interactions. As…

机器人学 · 计算机科学 2025-12-03 Qiping Zhang , Nathan Tsoi , Mofeed Nagib , Booyeon Choi , Jie Tan , Hao-Tien Lewis Chiang , Marynel Vázquez

Foundation model reliability assessment typically requires thousands of evaluation examples, making it computationally expensive and time-consuming for real-world deployment. We introduce microprobe, a novel approach that achieves…

人工智能 · 计算机科学 2025-12-25 Aayam Bansal , Ishaan Gangwani

Formal verification of robotic tasks requires a simple yet conformant model of the used robot. We present the first work on generating reachset conformant models for robotic contact tasks considering hybrid (mixed continuous and discrete)…

机器人学 · 计算机科学 2024-10-15 Chencheng Tang , Matthias Althoff

Physical AI aims to develop models that can perceive and predict real-world dynamics; yet, the extent to which current multi-modal large language models and video generative models support these abilities is insufficiently understood. We…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Fengzhe Zhou , Jiannan Huang , Jialuo Li , Deva Ramanan , Humphrey Shi

Despite the promising performance of existing visual models on public benchmarks, the critical assessment of their robustness for real-world applications remains an ongoing challenge. To bridge this gap, we propose an explainable visual…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Qiang Li , Dan Zhang , Shengzhao Lei , Xun Zhao , Porawit Kamnoedboon , WeiWei Li , Junhao Dong , Shuyan Li

Reward models play an essential role in training vision-language models (VLMs) by assessing output quality to enable aligning with human preferences. Despite their importance, the research community lacks comprehensive open benchmarks for…

计算机视觉与模式识别 · 计算机科学 2025-02-21 Michihiro Yasunaga , Luke Zettlemoyer , Marjan Ghazvininejad

With the rapid advancement of Multi-modal Large Language Models (MLLMs), several diagnostic benchmarks have recently been developed to assess these models' multi-modal reasoning proficiency. However, these benchmarks are restricted to…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Sanjoy Chowdhury , Sayan Nag , Subhrajyoti Dasgupta , Yaoting Wang , Mohamed Elhoseiny , Ruohan Gao , Dinesh Manocha

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…

Commonly, AI or machine learning (ML) models are evaluated on benchmark datasets. This practice supports innovative methodological research, but benchmark performance can be poorly correlated with performance in real-world applications -- a…

机器学习 · 计算机科学 2024-06-18 Olivier Binette , Jerome P. Reiter

Robots such as autonomous vehicles and assistive manipulators are increasingly operating in dynamic environments and close physical proximity to people. In such scenarios, the robot can leverage a human motion predictor to predict their…

机器人学 · 计算机科学 2023-06-07 Kensuke Nakamura , Somil Bansal