i compared embedding similarity between colors and emotions and normalized it to create this chart and then when i changed the language, the results changed (eg. 赤、愛) see: english, spanish, japanese, hindi
RESEARCH
-
AnyFlow: New Video Diffusion Model with On-Policy Flow Map Distillation
By
–
AnyFlow
— AK (@_akhaliq) 14 mai 2026
Any-Step Video Diffusion Model with On-Policy Flow Map Distillation pic.twitter.com/rXWlrNhv0KAnyFlow Any-Step Diffusion Model with On-Policy Flow Map Distillation
-
MulTaBench: A New Benchmark for Multimodal Tabular Learning
By
–
MulTaBench Benchmarking Multimodal Tabular Learning with Text and Image
-
Microsoft Explores Acquisition of AI Lab Behind Reasoning Diffusion LLM
By
–
Microsoft is exploring a deal to acquire Inception, an AI lab that recently released Mercury 2, the world's first reasoning diffusion LLM, according to Reuters. Imagine diffusion Copilot
-
Addressing Step Size Instability in Reinforcement Learning
By
–
Why do standard step sizes cause instability when learning from every single experience? Arsalan Sharifnassab, @RichardSSutton , and their team from Openmind Research Institute and University of Alberta present intentional updates: instead of picking a step size and hoping for
-
Google’s new Gemini model to rival GPT-5.5 at I/O
By
–
Lets go: Google’s next Gemini model is expected to compete with GPT-5.5 Google is reportedly preparing to unveil a new Gemini model at I/O, positioning it near OpenAI’s recent GPT-5.5 rather than the more elusive Anthropic Mythos. Google i/o got even more exciting
-
Hölder Policy Optimisation paper and code
By
–
Hölder Policy Optimisation Paper: https://
arxiv.org/abs/2605.12058
Code: https://
github.com/YihangChen9/Ho
lderPO
… -
HölderPO: single-parameter fix to prevent AI training collapse
By
–
Wow, fixing one simple parameter could stop your AI training from collapsing! UCL, Shanghai Jiao Tong University, and HKUST (Guangzhou) present HölderPO. Instead of summing token probabilities in a fixed way, HölderPO uses a flexible averaging trick controlled by a single “p”
-
Peking University Researchers Unveil SEAlign for AI Code Agents
By
–
Why can't top code models handle real-world software engineering? Researchers from Peking University unveil SEAlign — a new alignment framework that trains code agents on actual software workflows. Instead of just solving coding puzzles, it uses Monte Carlo Tree Search to
-
AI capability growth past exponential takeoff per METR and UK AISA
By
–
Everyone has seen the @waitbutwhy cartoon of AI capability growth with a "you are here" indicator just before the exponential really starts, but the independent assessments of both METR and the UK's AISA do seem to show that we are past that point now (until we hit a slowdown?)