Robotics paper reading clubs
Robotics research outgrew the ability of any one person to follow it, so labs started reading in rooms. One person takes a paper apart, everyone else gets the signal in ten minutes, and the room argues about what it means. This site indexes those rooms, where they meet, what they put on the reading list and who is presenting, and it gives you a six-slide kit for any paper you want to bring to one.
Refreshed twice a week from the clubs' own pages and the arXiv API. Latest full month: 1,166 submissions to cs.RO in July 2026, up 45% on a year earlier.
Papers a club has already put on the table, each with a slide kit pulled from its own sections: the problem, what came before, the method, the numbers, where it breaks, and the one line worth remembering.
Ranked for presentability: recent, venue-accepted or already collecting citations, code available. If you need a paper for this week, start here and be the first.
01 / Who is in the room
A PhD student three years into tactile sensing, an engineer shipping arms to factories, a founder who read the paper on the train, someone switching in from computer vision. Different stages of a career, different backgrounds, reading the same paper and disagreeing about it. You can come and just listen. Presenting is open to anyone, and at some clubs it earns you priority when spots run short.
02 / What is moving
Vision-language-action +7.1pp, World models +2.85pp, Tactile & force sensing +2.2pp. Share of monthly cs.RO submissions, last six months against the twelve before. One arXiv query per topic per month, query strings published.
03 / Your city
Tel Aviv, Singapore, London, Tokyo, Bangalore and more have world-class robotics labs and no public reading club we could find. Starting one costs a room, a date and a first presenter, which is usually you.
Learned simulators that predict future observations, so a policy can plan or train inside imagination instead of on hardware.
242 papers here · 7.55% of cs.RO last month
Policies that consume pixels and language and emit robot actions directly, usually fine-tuned from a VLM backbone.
269 papers here · 11.92% of cs.RO last month
Multi-fingered hands, in-hand reorientation, and contact-rich control of everyday objects.
378 papers here · 2.23% of cs.RO last month
Whole-body control, legged locomotion, and loco-manipulation on human-form robots.
320 papers here · 5.92% of cs.RO last month
Turning first-person human video and wearable capture into robot training signal, bypassing teleoperation.
295 papers here · 4.55% of cs.RO last month
Touch as a first-class modality: skins, current sensing, and contact-rich feedback loops.
262 papers here · 6.69% of cs.RO last month
Simulators, domain randomisation, and the evaluation harnesses that decide whether a policy really works.
317 papers here · 6% of cs.RO last month
Behaviour cloning at scale, and the generative-model action heads that made it work.
257 papers here · 6.26% of cs.RO last month
Online and offline RL, model-predictive control, and the safety filters wrapped around them.
507 papers here · 15.35% of cs.RO last month