English
Related papers

Related papers: AsgardBench -- Evaluating Visually Grounded Intera…

200 papers

Interactive articulated manipulation requires long-horizon, multi-step interactions with appliances while maintaining physical consistency. Existing vision-language and diffusion-based policies struggle to generalize across parts,…

Robotics · Computer Science 2025-12-01 Yuhan Wu , Tiantian Wei , Shuo Wang , ZhiChao Wang , Yanyong Zhang , Daniel Cremers , Yan Xia

Understanding causal relationships across modalities is a core challenge for multimodal models operating in real-world environments. We introduce ISO-Bench, a benchmark for evaluating whether models can infer causal dependencies between…

Computation and Language · Computer Science 2025-08-01 Ananya Sadana , Yash Kumar Lal , Jiawei Zhou

We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--such as sycophantic deference, opposition to AI regulation,…

Computation and Language · Computer Science 2026-03-11 Abhay Sheshadri , Aidan Ewart , Kai Fronsdal , Isha Gupta , Samuel R. Bowman , Sara Price , Samuel Marks , Rowan Wang

Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate these capabilities holistically. To bridge this gap, we…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Haochen Wang , Xiangtai Li , Zilong Huang , Anran Wang , Jiacong Wang , Tao Zhang , Jiani Zheng , Sule Bai , Zijian Kang , Jiashi Feng , Zhuochen Wang , Zhaoxiang Zhang

In the rapidly evolving field of artificial intelligence (AI), traditional benchmarks can fall short in attempting to capture the nuanced capabilities of AI models. We focus on the case of physical world modeling and propose a novel…

Artificial Intelligence · Computer Science 2025-09-08 Sasha Mitts

Instruction granularity is an important yet poorly controlled variable in language-guided embodied AI. Existing benchmarks typically pair each task with a single static instruction, making it difficult to study how agent behavior changes…

Artificial Intelligence · Computer Science 2026-04-21 Sukai Huang , Chenyuan Zhang , Fucai Ke , Zhixi Cai , Gholamreza Haffari , Lizhen Qu , Hamid Rezatofighi

Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in…

Computer Vision and Pattern Recognition · Computer Science 2025-01-30 Wei Chow , Jiageng Mao , Boyi Li , Daniel Seita , Vitor Guizilini , Yue Wang

Visual reasoning, the capability to interpret visual input in response to implicit text query through multi-step reasoning, remains a challenge for deep learning models due to the lack of relevant benchmarks. Previous work in visual…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Yiqing Shen , Chenjia Li , Chenxiao Fan , Mathias Unberath

Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…

Artificial Intelligence · Computer Science 2026-03-25 Raj Ghugare , Roger Creus Castanyer , Catherine Ji , Kathryn Wantlin , Jin Schofield , Karthik Narasimhan , Benjamin Eysenbach

Agentic AI workflows (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low. A promising solution is inference-time alignment, which uses extra compute at test time to…

Existing visual grounding benchmarks primarily evaluate alignment between image regions and literal referring expressions, where models can often succeed by matching a prominent named category. We explore a complementary and more…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Ruozhen He , Nisarg A. Shah , Qihua Dong , Zilin Xiao , Jaywon Koo , Vicente Ordonez

Rapid advances in audio-video (AV) generation have enabled high-fidelity synthesis with synchronized sound, particularly for human-related scenarios involving speech and interactions. Yet evaluation for AV generation remains at an early…

Artificial Intelligence · Computer Science 2026-05-26 Jialiang Yang , Bin Xia , Ruihang Chu , Dingdong Wang , Wanke Xia , Zhun Mou , Tianyang Zhong , Yiting Zhao , Wenming Yang

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically…

Artificial Intelligence · Computer Science 2026-04-16 Chonghan Qin , Xiachong Feng , Weitao Ma , Xiaocheng Feng , Lingpeng Kong

Egocentric interaction perception is one of the essential branches in investigating human-environment interaction, which lays the basis for developing next-generation intelligent systems. However, existing egocentric interaction…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Yuejiao Su , Yi Wang , Qiongyang Hu , Chuang Yang , Lap-Pui Chau

Ambiguity is ubiquitous in human communication. Previous approaches in Human-Robot Interaction (HRI) have often relied on predefined interaction templates, leading to reduced performance in realistic and open-ended scenarios. To address…

Robotics · Computer Science 2023-10-19 Hanbo Zhang , Jie Xu , Yuchen Mo , Tao Kong

Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluations offer limited coverage, imprecise target-state definitions, and an overreliance on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Fengxian Ji , Jingpu Yang , Zirui Song , Yuanxi Wang , Zhexuan Cui , Yuke Li , Qian Jiang , Xiuying Chen

General-purposed embodied agents are designed to understand the users' natural instructions or intentions and act precisely to complete universal tasks. Recently, methods based on foundation models especially Vision-Language-Action models…

We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web platforms. It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation,…

Existing vision-language understanding benchmarks largely consist of images of objects in their usual contexts. As a consequence, recent multimodal large language models can perform well with only a shallow visual understanding by relying…

How (dis)similar are the learning trajectories of vision-language models and children? Recent modeling work has attempted to understand the gap between models' and humans' data efficiency by constructing models trained on less data,…

Computation and Language · Computer Science 2024-12-10 Alvin Wei Ming Tan , Sunny Yu , Bria Long , Wanjing Anya Ma , Tonya Murray , Rebecca D. Silverman , Jason D. Yeatman , Michael C. Frank