Related papers: MOOSEnger -- a Domain-Specific AI Agent for the MO…

Effective human-agent interaction (HAI) relies on accurate and adaptive perception of human emotional states. While multimodal deep learning models - leveraging facial expressions, speech, and textual cues - offer high accuracy in emotion…

We present MUG, a novel interactive task for multimodal grounding where a user and an agent work collaboratively on an interface screen. Prior works modeled multimodal UI grounding in one round: the user gives a command and the agent…

We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among…

Multimodal AI Agents are AI models that have the capability of interactively and cooperatively assisting human users to solve day-to-day tasks. Augmented Reality (AR) head worn devices can uniquely improve the user experience of solving…

Traditional augmented reality (AR) systems predominantly rely on fixed class detectors or fiducial markers, limiting their ability to interpret complex, open-vocabulary natural language queries. We present a modular AR agent system that…

Multimodal Large Language Models (MLLMs) have significantly advanced GUI agents, yet long-horizon automation remains constrained by two critical bottlenecks: context overload from raw sequential trajectory dependence and architectural…

This paper presents IronEngine, a general AI assistant platform organized around a unified orchestration core that connects a desktop user interface, REST and WebSocket APIs, Python clients, local and cloud model backends, persistent…

Large language models (LLMs) have enabled powerful advances in natural language understanding and generation. Yet their application to complex, real-world scientific workflows remain limited by challenges in memory, planning, and tool…

Tensor compilers play a key role in enabling high-performance implementations of deep learning workloads. These compilers rely on existing CPU and GPU code generation backends to generate device-specific code. Recently, many tensor…

Large models are increasingly becoming autonomous agents that interact with real-world environments and use external tools to augment their static capabilities. However, most recent progress has focused on text-only large language models,…

Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of…

Rapid advancements over the years have helped machine learning models reach previously hard-to-achieve goals, sometimes even exceeding human capabilities. However, to attain the desired accuracy, the model sizes and in turn their…

Language-guided navigation is a cornerstone of embodied AI, enabling agents to interpret language instructions and navigate complex environments. However, expert-provided instructions are limited in quantity, while synthesized annotations…

Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermediate content can overwhelm the agent, increasing costs and the risk of errors. We…

This paper presents an AI glasses system that integrates real-time voice processing, artificial intelligence(AI) agents, and cross-network streaming capabilities. The system employs dual-agent architecture where Agent 01 handles Automatic…

Pathology report generation remains a relatively under-explored downstream task, primarily due to the gigapixel scale and complex morphological heterogeneity of Whole Slide Images (WSIs). Existing pathology report generation frameworks…

Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent proposes, implements, evaluates, and refines candidate solutions against a quantitative objective. Here, we use composition-based…

Current deep-research agents run in a ''fire-and-forget'' mode: once started, they give users no way to fix errors or add expert knowledge during execution. We present ResearStudio, the first open-source framework that places real-time…

In the rapidly advancing research fields such as AI, managing and staying abreast of the latest scientific literature has become a significant challenge for researchers. Although previous efforts have leveraged AI to assist with literature…

Advanced reverse engineering tools are required to cope with the complexity of software systems and the specific requirements of numerous different tasks (re-architecturing, migration, evolution). Consequently, reverse engineering tools…