6 papers
Harnessing VLM in Embodied RL: From Reward Regressor to Success Detector via Exploration-Augmented Key-Observation Gating
Xin Liu, Yutong Jiang, Jian Su +4
VLMs provide promising solutions to embodied reward design. Most current methods that train VLMs as reward regressors not only require extensive annotations but are also primarily…
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
Incomplete Observations Boost Evolutionary Performance in Ocean Modeling
Yangyang Kong, Yutong Jiang, Yanhai Gan +3
Data-driven methods have revolutionized ocean modeling, yet current approaches rely heavily on complete reanalysis datasets, imposing computational constraints and limiting model p…
WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
Zhennan Jiang, Shangqing Zhou, Yutong Jiang +11
Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interact…
Learn by Selling: Equipping Large Language Models with Product Knowledge for Context-Driven Recommendations
Sarthak Anand, Yutong Jiang, Giorgi Kokaia
The rapid evolution of large language models (LLMs) has opened up new possibilities for applications such as context-driven product recommendations. However, the effectiveness of t…
Writing your own book: A method for going from closed to open book QA to improve robustness and performance of smaller LLMs
Giorgi Kokaia, Pratyush Sinha, Yutong Jiang +1
We introduce two novel methods, Tree-Search and Self-contextualizing QA, designed to enhance the performance of large language models (LLMs) in question-answering tasks. Tree-Searc…