Related papers: Skywork-R1V4: Toward Agentic Multimodal Intelligen…
A multimodal AI agent is characterized by its ability to process and learn from various types of data, including natural language, visual, and audio inputs, to inform its actions. Despite advancements in large language models that…
With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve-then-generate paradigm toward more sophisticated agentic…
Multi-agent systems (MAS) built on large language models (LLMs) offer a promising path toward solving complex, real-world tasks that single-agent systems often struggle to manage. While recent advancements in test-time scaling (TTS) have…
Reward models (RMs) are essential for training large language models (LLMs), but remain underexplored for omni models that handle interleaved image and text sequences. We introduce Multimodal RewardBench 2 (MMRB2), the first comprehensive…
Generalization in embodied AI is hindered by the "seeing-to-doing gap," which stems from data scarcity and embodiment heterogeneity. To address this, we pioneer "pointing" as a unified, embodiment-agnostic intermediate representation,…
Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to ``think with images'' by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on…
Large multimodal models (LMMs) show strong visual-linguistic reasoning but their capacity for spatial decision-making and action remains unclear. In this work, we investigate whether LMMs can achieve embodied spatial action like human…
Multimodal large language models (MLLMs) show promise in tasks like visual question answering (VQA) but still face challenges in multimodal reasoning. Recent works adapt agentic frameworks or chain-of-thought (CoT) reasoning to improve…
Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…
The latest advancements in multi-modal large language models (MLLMs) have spurred a strong renewed interest in end-to-end motion planning approaches for autonomous driving. Many end-to-end approaches rely on human annotations to learn…
Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use capabilities, are evolving into autonomous agents capable of performing multimodal web browsing and deep search in open-world environments.…
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…
Recent advances in multimodal models have demonstrated impressive capabilities in unified image generation and editing. However, many prominent open-source models prioritize scaling model parameters over optimizing training strategies,…
Visual analytics (VA) requires analysts to iteratively propose analysis tasks based on observations and execute tasks by creating visualizations and interactive exploration to gain insights. This process demands skills in programming, data…
Recent advances in medical large language models (LLMs), multimodal models, and agents demand evaluation frameworks that reflect real clinical workflows and safety constraints. We present MedBench v4, a nationwide, cloud-based benchmarking…
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and…
Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization…
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framework, which incorporates large-scale, progressive,…
Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on…
Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major shift in how users interact with web-scale information. While…