Today we’re releasing TRL v1. 75+ methods. SFT, DPO, GRPO, async RL to take advantage of the latest and greatest open-source. 6 years from first commit to the library that post-trains most open models in the world. Built to be future proof. pip install trl
MACHINE LEARNING
-
Spider-Inspired Robot 3D Prints Buildings Using On-Site Materials
By
–
Spider-Inspired #Robot #3D Prints Buildings Using On-Site Materials
— Ronald van Loon (@Ronald_vanLoon) 31 mars 2026
via @ZappyZappy7
#3Dprinted #Robotics #Engineering #ArtificialIntelligence #Innovation #Technology pic.twitter.com/6F1NxzmQpxSpider-Inspired #Robot #3D Prints Buildings Using On-Site Materials
via @ZappyZappy7 #3Dprinted #Robotics #Engineering #ArtificialIntelligence #Innovation #Technology -
Pareto Chart Analysis for Local LLMs Performance
By
–
this is the right Pareto chart for local LLMs, everything else is just pretending (they should use AAIIv4 instead of doing their own average but eh, nitpicks)
-
Industry Standards: Why 99% Accuracy Isn’t Enough in AI
By
–
i haven’t read that specific report but read many from over the years and its always been apples vs oranges and i have written about that here frequently. 99% isn’t good enough, as everyone in the industry realizes.
-
Face Patches Implement Domain-Specific and Domain-General Processing
By
–
We show face patches implement the following code through recurrent dynamics: Detect face If (face found) Discriminate face else Continue to detect face IMHO, our paper conclusively resolves a debate that has raged since I was a graduate student, about whether face patches are specialized for processing faces or not. It turns out domain-general folks were right early on, domain-specific folks were right later in the response. So proud of @Yuelin_Shi and the entire team! Yuelin Shi (@Yuelin_Shi) Our paper is now out! nature.com/articles/s41586-0… A big question: 1) Is IT cortex well described as a general-purpose feedforward DNN? OR 2) Are face patches genuinely specialized for processing faces? Read on to find out the answer. (1/N) — https://nitter.net/Yuelin_Shi/status/2039100718100185426#m
→ View original post on X — @berkeley_ai, 2026-03-31 22:17 UTC
-
Robot quadrupède tout terrain révolutionne la mobilité intelligente
By
–
Agile All-Terrain Wheeled Quadruped Redefines Smart #Robotic Mobility
— Ronald van Loon (@Ronald_vanLoon) 31 mars 2026
by @PuduRobotics
#Robot #Engineering #ArtificialIntelligence #Innovation #Technology pic.twitter.com/CDP5hK4weBAgile All-Terrain Wheeled Quadruped Redefines Smart #Robotic Mobility
by @PuduRobotics #Robot #Engineering #ArtificialIntelligence #Innovation #Technology -
RF-DETR Real-Time Instance Segmentation Now Available on MLX
By
–
RF-DETR by @roboflow now on MLX
— Prince Canuma (@Prince_Canuma) 31 mars 2026
It can do realtime instance segmentation on-device and enable some cool use cases for visual analysis, monitoring and robotics like Reachy Mini.
Also augmented VLM and VLA by preprocessing image and video with areas of interest.
New release… pic.twitter.com/Q4waKyAoofRF-DETR by @roboflow now on MLX It can do realtime instance segmentation on-device and enable some cool use cases for visual analysis, monitoring and robotics like Reachy Mini. Also augmented VLM and VLA by preprocessing image and video with areas of interest. New release coming soon on mlx-vlm 🚀 For those who can’t wait you can install mlx-vlm from source.
→ View original post on X — @learnopencv, 2026-03-31 21:19 UTC
-
3D Gaussian Splats Improvement with MRNF and PPISP
By
–
3d gaussian splats suddenly looking way less splatty! high frequency details look so much better with MRNF + PPISP https://t.co/hMBrdgWsyB
— Bilawal Sidhu (@bilawalsidhu) 31 mars 20263d gaussian splats suddenly looking way less splatty! high frequency details look so much better with MRNF + PPISP Tavius Koktavy 🌐💿🔆 (@TaviusKoktavy) In @lichtfeldstudio the new MRNF strategy plus PPISP is great. Compare MCMC (left) to MRNF (right) on a quick 20 second scan. Full-screen recommended Fine details pop, backgrounds are much more clear, and the color space is true-to-life. — https://nitter.net/TaviusKoktavy/status/2039061893722091533#m
→ View original post on X — @bilawalsidhu, 2026-03-31 21:00 UTC
-
AI Optimization Drives Mediocrity: Strategies for Originality
By
–
#AI Is Optimizing Us Into Mediocrity. Here’s How To Stay Original
by Vince Carrabba @Forbes Learn more: https://
bit.ly/4sxwSRK #ArtificialIntelligence #MachineLearning #ML #DL -
Autoregressive Models Error Propagation in Discrete Sequences
By
–
That's a ridiculous argument. – all auto-regressive models diverge, whether they are generative (in input space) or not. – for discrete symbol sequences, the probability of correctness decreases exponentially with the sequence length, assuming independence of errors. – THAT