Related papers: WebSight: A Vision-First Architecture for Robust W…
The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection attempts remain limited to offline trajectories for supervised fine-tuning or a handful of…
The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging automation and Large Language Models (LLMs). Many existing benchmarks suffer from fragmentation and…
Facing scaling laws, video data from the internet becomes increasingly important. However, collecting extensive videos that meet specific needs is extremely labor-intensive and time-consuming. In this work, we study the way to expedite this…
Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity…
Visual grounding, the task of linking textual queries to specific regions within images, plays a pivotal role in vision-language integration. Existing methods typically rely on extensive task-specific annotations and fine-tuning, limiting…
Visual compliance verification is a critical yet underexplored problem in computer vision, especially in domains such as media, entertainment, and advertising where content must adhere to complex and evolving policy rules. Existing methods…
Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts…
Current vision-language-action (VLA) models, pre-trained on large-scale robotic data, exhibit strong multi-task capabilities and generalize well to variations in visual and language instructions for manipulation. However, their success rate…
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as…
The rapid advancement of AI-powered smart glasses-one of the hottest wearable devices-has unlocked new frontiers for multimodal interaction, with Visual Question Answering (VQA) over external knowledge sources emerging as a core…
Vision-Language-Action (VLA) models have advanced autonomous driving, but existing benchmarks still lack scenario diversity, reliable action-level annotation, and evaluation protocols aligned with human preferences. To address these…
Artificial intelligence has shown promise in medical imaging, yet most existing systems lack flexibility, interpretability, and adaptability - challenges especially pronounced in ophthalmology, where diverse imaging modalities are…
Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passive interaction with static image collections, resulting in…
Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely sampled video frames, resulting in high computational cost. We present VideoSeek, a…
WebAssembly is the new low-level language for the web and has now been implemented in all major browsers since over a year. To ensure the security, performance, and correctness of future web applications, there is a strong need for dynamic…
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…
We present a visualization infrastructure that maps data elements to agents, which have behaviors parameterized by those elements. Dynamic visualizations emerge as the agents change position, alter appearance and respond to one other.…
Spatiotemporal intelligence in autonomous driving (AD) requires an agent to integrate multi-view observations into a coherent scene representation, maintain object continuity across viewpoints and time, and reason about spatial relations,…
Multimodal large language models (MLLMs) that integrate visual and textual reasoning leverage chain-of-thought (CoT) prompting to tackle complex visual tasks, yet continue to exhibit visual hallucinations and an over-reliance on textual…
We present VISTAR, a user-centric, multi-dimensional benchmark for text-to-image (T2I) evaluation that addresses the limitations of existing metrics. VISTAR introduces a two-tier hybrid paradigm: it employs deterministic, scriptable metrics…