crisiumnih
190 posts
I put my CFD lecture notes online, because apparently “just vibe with Navier-Stokes” is not a stable numerical method smh
Finite differences, flows, schemes, and assorted computational fluid chaos here: github.com/jaiselsingh1/N…
in memory of the good ol blackboard sessions heh
English
Actually I’ve been wanting to make a list (in no order of rankings)
- Arnold Palmer cold brew @ Subko
- Cranberry cold brew @ Beanlore
- Whiskey barrel cold brew @ Nerlu
- Pourover @ ground up
- Taaza Tindi filter coffee
- Cranberry foam cold brew @ Kahale
- Yuzu espresso martini @ Katte Kulture
- Ube tender coconut @ ddmmyy
- Moosambi espresso @ Nenapu
- Maverick Mazagran @ Mavericks and Farmers
- Orange Cold brew @ humble bean
- Drip and Drip, JP Nagar
- Practically Sobar Near Richmond Road
- Kappu in HSR
Burger 🍔@chingiiiiix
@agNavya @adii_kris Knows the best coffee spots in blr
English
You know the researchers are absolutely passionate when you see such quotes in the paper
Lucy Shi@lucy_x_shi
1/ We just released π0.7 — a steerable generalist robot model with emergent capabilities. I want to share a bit of the backstory, because π0.7 taught me something surprising about where robot learning is heading. A thread on bittersweet lessons 🧵
English
We are excited to share our #ICRA2026 paper "Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight"!
Paper: rpg.ifi.uzh.ch/docs/ICRA26_Ro…
Video: youtu.be/nctQ2rxZnIc
Can we use Model-Based #ReinforcementLearning (MBRL) to fly a drone from pixels to commands? In this work, we train quadrotor navigation policies from scratch using #WorldModels, mapping raw onboard camera pixels directly to control commands, much like a human pilot!
While model-free methods like PPO are sample-inefficient and struggle in this setting, we leverage #MBRL to train visuomotor policies capable of agile flight through a racetrack using only raw pixel observations, no explicit state estimation needed.
A key finding: because our policies are trained end-to-end directly from pixels, we no longer need the perception-aware reward term used in previous methods. Instead, this behavior emerges naturally! The policies learn to guide the camera toward feature-rich areas of the observation space on their own.
Kudos to @roaguiangel @ashwinshx @isgeles @EliJalbout
Reference:
"Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight"
Angel Romero*, Ashwin Shenai*, Ismail Geles, Elie Aljalbout, Davide Scaramuzza IEEE International Conference on Robotics and Automation (ICRA), Vienna, 2026.
@ERC_Research @AUTOASSESS_EU @uzh_ifi @UZH_en @UZH_Science @Prophesee_ai @SynSenseNeuro @UZHspacehub @swissrobotics @nccrrobotics
YouTube
English
@ETtech Pick & place use case I believe. I hope they intend to spend money on data collection & not fall into the trenches of building a foundational model.
English
crisiumnih retuiteado
I've been to Shenzhen annually since 2023, so I created a map of the shops worth visiting in the electronics district: docs.google.com/presentation/d…
English
Really excited to release mjviser, a web-based MuJoCo viewer, powered by Viser. It has almost all the features of the native MuJoCo viewer, but runs in your browser. Load and simulate any MuJoCo model with a single uv command 👇
uvx mjviser
English
engineering is when robot form follows function
ObotX - Open Source Robotics@open_robotx
Our blueprint for the "Optimal Universal Robot": ❌ Legs: Too complex, too expensive. ✅ Wheels: Fast, stable, 10x cheaper. ❌ Rotary Joints: Massive torque stress, custom gears. ✅ Of the shelf parts & linear actuators: High payload, extrem simplicity, off-the-shelf parts.
English
excited to announce SNAKE-WORLD, a world model trained entirely on EGO-SNAKE
a world model fully trained on egocentric snake POV footage capable of simulating the natural habitat of vipers
comment for a demo rollout
Tejes Srivalsan@tejessrivalsan
excited to announce that we’re open sourcing EGO-SNAKE the largest dataset of egocentric snake pov footage to train the next generation of autonomous vipers comment for a data sample
English
