Boris Belousov
@_bbelousov
Followers
940
Following
15K
Media
128
Statuses
1K
Curious, intrinsically motivated agent; previously senior researcher @DFKI Systems AI for Robot Learning https://t.co/1DHZstGPr9, w/@ias_tudarmstadt & @Hessian_AI
Darmstadt, Germany
Joined April 2019
RT @markgadala: At this point TikTok is probably 70% AI content. I spent my whole morning on TikTok researching AI trends. Here are 10 ne….
0
226
0
RT @v_debakker: Can we teach dexterous robot hands manipulation without human demos or hand-crafted rewards?.Our key insight: Use Vision-La….
0
11
0
RT @haldar_siddhant: Current robot policies often face a tradeoff: they're either precise (but brittle) or generalizable (but imprecise).….
0
74
0
RT @pdculbert: 🥋 We're excited to share judo: a hackable toolbox for sampling-based MPC (SMPC), data collection, and more, designed to make….
0
43
0
RT @aditya_bhatt: Achieved expressive whole body policies on our Unitree H1. … with a control architecture lends itself better to novel mot….
0
8
0
RT @SungjinAhn_: ⚡️ New breakthrough in Monte Carlo Tree Diffusion (MCTD) for System 2 Planning — powered by the KAIST–Mila collaboration!….
0
61
0
RT @HaoruXue: 🚀 Introducing LeVERB, the first 𝗹𝗮𝘁𝗲𝗻𝘁 𝘄𝗵𝗼𝗹𝗲-𝗯𝗼𝗱𝘆 𝗵𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗩𝗟𝗔 (upper- & lower-body), trained on sim data and zero-shot deplo….
0
102
0
RT @JunyaoShi: Check out our new work Points2Reward: Robotic Manipulation Rewards from Just One Video at #RSS2025 Workshop on Semantic Reas….
0
13
0
RT @YufeiWang25: Introducing ArticuBot🤖at #RSS2025, in which we learn a single policy for manipulating diverse articulated objects across 3….
0
32
0
RT @Haoyu_Xiong_: Your bimanual manipulators might need a Robot Neck 🤖🦒. Introducing Vision in Action: Learning Active Perception from Huma….
0
84
0
RT @pathak2206: Tired of tuning PPO or blaming it on reward, task design, etc.? Introducing EPO -- our second (and hopefully final :) attem….
0
8
0
RT @C___eric417: 🚀Introducing GMT — a general motion tracking framework that enables high-fidelity motion tracking on humanoid robots by tr….
0
59
0
RT @realyunlong: Swarm navigation at 20 m/s with no communication, no state estimation, & on a $21 computer? .This paper combines deep lear….
0
52
0
RT @GeorgiaChal: 🚨 We're hiring a Postdoc in Robot Learning @ PEARL Lab, TU Darmstadt 🚨. Join our ERC-funded project SIREN (Structured Inte….
0
12
0
RT @PhysInHistory: As a physicist who has devoted his whole life to rational science, to the study of matter, I think I can safely claim to….
0
213
0
Tactile MNIST 🔥.
5️⃣ Key Experiments:.We tested TAP on a variety of ap_gym ( tasks from the TactileMNIST benchmark (. In all cases, TAP learns to actively explore & infer object properties efficiently.
0
0
5
RT @Theo_Vincent_: Sparse network -> sparse poster. I will be presenting Eau De Q-Network today @RLDMDublin2025. Feel free to come and exch….
0
1
0
RT @timschneider94: Excited to present our latest work at RLDM 2025! If you’re curious about tactile sensing, active perception, or RL in r….
0
3
0
RT @zhaohengyin: Just open-sourced Geometric Retargeting (GeoRT) — the kinematic retargeting module behind DexterityGen. Includes tools fo….
0
11
0