SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending
机构 * University of Southern California（南加州大学） ； Stanford University（斯坦福大学） ； Peking University（北京大学） ； University of California, Berkeley（加州大学伯克利分校）
作者
Pieter Abbeel
Robotics
Chip Placement with Diffusion Models
机构 * Department of EECS, UC Berkeley, CA, USA（UC伯克利电子工程与计算机科学系） ； SambaNova Systems Inc., Palo Alto, CA, USA（SambaNova Systems公司） ； Computer Science Department, Stanford University, CA, USA（斯坦福大学计算机科学系）
Comments Code available at https://github.com/vint-1/chipdiffusion
Object-centric 3D Motion Field for Robot Learning from Human Videos
机构 * BAIR, UC Berkeley EECS（伯克利大学电子工程与计算机科学系） ； Google DeepMind（谷歌DeepMind）
Comments Project: https://zhaohengyin.github.io/3DMF
EgoZero: Robot Learning from Smart Glasses
Feel the Force: Contact-Driven Learning from Humans
机构 * New York University（纽约大学） ； UC Berkeley（加州大学伯克利分校） ； New York University Shanghai（纽约大学上海分校）
FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control
机构 * University of California, Berkeley（加州大学伯克利分校） ； University of Warsaw（华沙大学）
Comments Project webpage: https://younggyo.me/fast_td3
Diffusion Guidance Is a Controllable Policy Improvement Operator
机构 * UC Berkeley（加州大学伯克利分校）
Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
机构 * UC, Berkeley（伯克利大学） ； University of Warsaw（华沙大学） ； Nomagic（Nomagic公司） ； CMU（卡内基梅隆大学）
Comments preprint
Intrinsically-Motivated Humans and Agents in Open-World Exploration
机构 * BAIR ； University of California Berkeley（加州大学伯克利分校） ； Psychology（心理学）
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Comments Project website: https://robotics-transformer-x.github.io
Prioritized Generative Replay
机构 * Department of Electrical Engineering and Computer Science（电气工程与计算机科学系） ； University of California, Berkeley（加州大学伯克利分校）
Comments Project page available at: https://pgenreplay.github.io
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
机构 * UC Berkeley（加州大学伯克利分校） ； PKU（北京大学） ； USC（南加州大学） ； UMich（密歇根大学） ； UIUC（伊利诺伊大学厄巴纳-香槟分校） ； Stanford（斯坦福大学） ； CMU（卡内基梅隆大学） ； UCLA（加州大学洛杉矶分校） ； BIGAI（大疆创新）
Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction
Comments Code is available on the project webpage: https://huiwon-jang.github.io/coordtok/
RoboCopilot: Human-in-the-loop Interactive Imitation Learning for Robot Manipulation
Geometric Retargeting: A Principled, Ultrafast Neural Hand Retargeting Algorithm
Comments Project Website: https://zhaohengyin.github.io/geort
Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos
Learning a Diffusion Model Policy from Rewards via Q-Score Matching
Comments ICML 2024. 21 pages, 9 figures
MuJoCo Playground
Interactive Task Planning with Language Models
Comments Transactions on Machine Learning Research (TMLR), 2025
DexterityGen: Foundation Controller for Unprecedented Dexterity
Comments Project: https://zhaohengyin.github.io/dexteritygen
World Model on Million-Length Video And Language With Blockwise RingAttention
ElasticTok: Adaptive Tokenization for Image and Video
Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding
Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
Twisting Lids Off with Two Hands
Comments Project page can be found at https://toruowo.github.io/bimanual-twist
Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own
Comments CoRL 2024 (Oral)
Learning Interactive Real-World Simulators
Hand-Object Interaction Pretraining from Videos
MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting
FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning
Comments IJRR 2024
