ニュース&特集
AsgardBench: A benchmark for visually grounded interactive planning
| Andrea Tupini, Lars Liden, Reuben Tan, Yu Wang, と Jianfeng Gao
Imagine a robot tasked with cleaning a k…
GroundedPlanBench: Spatially grounded long-horizon task planning for robot manipulation
| Sehun Jung, HyunJee Song, Dong-Hee Kim, Reuben Tan, Jianfeng Gao, Yong Jae Lee, と Donghyun Kim
Vision-language models (VLMs) use images…
PlugMem: Transforming raw agent interactions into reusable knowledge
| Ke Yang, Michel Galley, Chenglong Wang, Jianfeng Gao, Jiawei Han, と ChengXiang Zhai
It seems counterintuitive: giving AI age…
Argos: Multimodal reinforcement learning with agentic verifier for AI agents
| Reuben Tan, Baolin Peng, Zhengyuan Yang, Oier Mees, と Jianfeng Gao
Argos improves multimodal RL by evaluati…
MindJourney enables AI to explore simulated 3D worlds to improve spatial interpretation
| Yuncong Yang, Reuben Tan, Swadheen Shukla, と Jianfeng Gao
MindJourney can enable AI to navigate an…
CollabLLM: Teaching LLMs to collaborate with users
| Shirley Wu, Michel Galley, Baolin Peng, Swadheen Shukla, と Jianfeng Gao
Recipient of an ICML 2025 Outstanding Pa…
Research Focus: Week of April 21, 2025
In this issue: our CHI 2025 & ICLR 2025 …
Research Focus: Week of March 24, 2025
In this issue, we examine a new conversa…
Magma: A foundation model for multimodal AI agents across digital and physical worlds
| Swadheen Shukla, Jianwei Yang, Reuben Tan, Qianhui Wu, と Jianfeng Gao
Explore Magma, a foundation model that c…