11 papers
MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning
Ziyang Luo, Yan Yang, Xiangru Jian +5
Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks stop at the policy update.…
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
Yan Yang, Xiangru Jian, Ziyang Luo +7
Computer-use agents are usually improved by strengthening perception: better models for reading a screenshot and choosing where to click. Yet a screenshot is only a lossy rendering…
GPA: Learning GUI Process Automation from Demonstrations
Zirui Zhao, Jun Hao Liew, Yan Yang +5
GUI Process Automation (GPA) is a lightweight but general vision-based Robotic Process Automation (RPA), which enables fast and stable process replay with only a single demo. Addre…
EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
Tianwei Xiong, Jun Hao Liew, Zilong Huang +3
Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancin…
Depth Anything 3: Recovering the Visual Space from Any Views
Haotong Lin, Sili Chen, Junhao Liew +5
We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of…
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
Tianwei Xiong, Jun Hao Liew, Zilong Huang +2
In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for…