Re-passing activations through the same layers sounds like recurrent computation stitched back in, curious if it still benefits from longer contexts the way dense transformers do.
MACHINE LEARNING
-
Sub-10% error rates signal continued AI reasoning breakthroughs
By
–
Sub-10% on the frontier is kind of reassuring, the plateau talk this month was starting to sound like we're done with reasoning gains.
-
Chinese AI Models Progress While Remaining Behind Frontier Models
By
–
Excellent article by @RobinRivaton on the OpenClaw fever. While we wonder if Beijing is "catching up" to Silicon Valley, Chinese models are progressing while remaining structurally behind frontier models, but with an industrial diffusion speed that we can't imagine here. Over
-
Leverage AI-Driven Insights To Power Better Business Operations
By
–
How To Leverage #AI-Driven Insights To Power Better Business Operations
by @Forbes Learn more: https://
bit.ly/427aenG #ArtificialIntelligence #MachineLearning #ML -
Simple ML Methods Don’t Scale Well Contrary Belief
By
–
There's a broadly held misconception in AI that methods that scale well are simple methods — even, that simple methods usually scale. This is completely wrong. Pretty much none of the truly simple methods in ML scale well. SVM, kNN, random forests are some of the simplest
-
Best Platforms for AI Agents
By
–
Best Platforms for #AIAgents
by @Python_Dv #AI #LLM #ArtificialIntelligence #MachineLearning #ML -
Why AI Still Cannot Master New Video Games
By
–
Why #AI still can't beat a new video game
by NYU Tandon School of Engineering @TechXplore_com Learn more: https://
buff.ly/UlRyxY1 #MachineLearning #ArtificialIntelligence #ML #MI -
TIPSv2: Enhanced Spatial Awareness in Vision-Language Models
By
–
“TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment” This paper propose a foundational image-text encoder with spatial awareness, as VLMs are usually good at describing an image but much worse at grounding where the concepts live. What they found
-
Empowering AI Agents for Physical World Navigation
By
–
How can we empower AI agents to navigate the physical world with true intelligence and adaptability? Researchers from Beijing University of Posts and Telecommunications, Nanjing University, Tsinghua University, and Peking University are reviewing a groundbreaking shift in
-
Humanoid Robots Successfully Test Riding Electric Motorcycles
By
–
Humanoid #Robots Ride Electric Motorcycles in Real-World Test
— Ronald van Loon (@Ronald_vanLoon) 16 avril 2026
via @sz_mediagroup#Robotics #ArtificialIntelligence #MachineLearning #DeepLearning pic.twitter.com/Zh841HuQfcHumanoid #Robots Ride Electric Motorcycles in Real-World Test
via @sz_mediagroup #Robotics #ArtificialIntelligence #MachineLearning #DeepLearning