Related papers: GeoBrowse: A Geolocation Benchmark for Agentic Too…
In this paper, we introduce OSUniverse: a benchmark of complex, multimodal desktop-oriented tasks for advanced GUI-navigation AI agents that focuses on ease of use, extensibility, comprehensive coverage of test cases, and automated…
The pursuit of general-purpose embodied agents is hindered by fragmented evaluation protocols that isolate navigation skills and fixate on specific robot morphologies, failing to reflect real-world scenarios where agents must orchestrate…
Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large…
Geolocating Twitter users---the task of identifying their home locations---serves a wide range of community and business applications such as managing natural crises, journalism, and public health. Many approaches have been proposed for…
Recent years, multimodal models have made remarkable strides and pave the way for intelligent browser use agents. However, when solving tasks on real world webpages in multi-turn, long-horizon trajectories, current agents still suffer from…
We present AutoPose, a novel neural architecture search(NAS) framework that is capable of automatically discovering multiple parallel branches of cross-scale connections towards accurate and high-resolution 2D human pose estimation.…
Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity. Recent generative approaches based on Retrieval-Augmented Generation (RAG) and Large…
Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only…
Applications in the field of augmented reality or robotics often require joint localisation and 6D pose estimation of multiple objects. However, most algorithms need one network per object class to be trained in order to provide the best…
Mathematical reasoning is a hallmark of human intelligence, requiring logical deduction, symbolic manipulation, and abstract thinking. Recent multimodal large language models (MLLMs) have demonstrated strong performance on geometry problems…
Large language models are increasingly being used to assess and forecast research ideas, yet we lack scalable ways to evaluate the quality of models' judgments about these scientific ideas. Towards this goal, we introduce PoT, a…
Remote management devices facilitate critical infrastructure monitoring for administrators but simultaneously increase asset exposure. Sensitive geographical information overlooked in exposed device management pages poses substantial…
Agentic retrieval improves multi-hop question answering by giving language models autonomy to iteratively gather evidence. Recent work augments these systems with knowledge graphs for structured traversal, but this combination introduces…
Language agents have demonstrated remarkable potential in web search and information retrieval. However, these search agents assume user queries are complete and unambiguous, an assumption that diverges from reality where users begin with…
Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…
Recent studies have extended the application of large language models (LLMs) to geographic problems, revealing surprising geospatial competence even without explicit spatial supervision. However, LLMs still face challenges in spatial…
Extracting the "correct" location information from text data, i.e., determining the place of event, has long been a goal for automated text processing. To approximate human-like coding schema, we introduce a supervised machine learning…
The evolution of autonomous agents is redefining information seeking, transitioning from passive retrieval to proactive, open-ended web research. However, a significant modality gap remains in processing the web's most dynamic and…
Geometric spatial reasoning forms the foundation of many applications in artificial intelligence, yet the ability of large language models (LLMs) to operate over geometric spatial information expressed in procedural code remains…
Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or…