7 papers
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…
Training-Free Self-Correction for Multimodal Masked Diffusion Models
Yidong Ouyang, Panwen Hu, Zhengyan Wan +7
Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats…
Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage
Peiyu Yu, Suraj Kothawade, Sirui Xie +2
Most post-training methods for text-to-image samplers focus on model weights: either fine-tuning the backbone for alignment or distilling it for few-step efficiency. We take a diff…
InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning
Muzhi Han, Yifeng Zhu, Song-Chun Zhu +2
Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predic…
LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning
Shu Wang, Muzhi Han, Ziyuan Jiao +4
Conventional Task and Motion Planning (TAMP) approaches rely on manually crafted interfaces connecting symbolic task planning with continuous motion generation. These domain-specif…
Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning
Yilue Qian, Peiyu Yu, Ying Nian Wu +3
Visual planning simulates how humans make decisions to achieve desired goals in the form of searching for visual causal transitions between an initial visual state and a final visu…