“Representation Fréchet Loss for Visual Generation” FID has always been generative modeling's scoreboard, where everyone optimizes toward it indirectly, but almost nobody trains on it directly. However, this paper shows that you actually can. They achieved this by estimating
RESEARCH
-
Artificial Analysis Index Limitations for AI Model Benchmarking
By
–
The artificial analysis index is a normalized score of several benchmarks (and has changed over time) it is fine for roughly comparing models, it is not useful for trend analysis and it is unclear what individual point differences in the scores mean.
-
Sakana Fugu: Multi-Agent Orchestration System as Foundation Model
By
–
Sakana Fugu: A Multi-Agent Orchestration System as a Foundation Model
-
3D Printed Robotic Hand Mirrors Human Gestures in Real Time
By
–
#3DPrinted #Robotic Hand Mirrors Human Gestures in Real Time
— Ronald van Loon (@Ronald_vanLoon) 3 mai 2026
by @YKwolfpec
#EmergingTech #Innovation #TechForGood #Tech pic.twitter.com/BYV0ks5vzO#3DPrinted #Robotic Hand Mirrors Human Gestures in Real Time
by @YKwolfpec #EmergingTech #Innovation #TechForGood #Tech -
Shared Experts Reduce Redundancy in Mixture-of-Experts Models
By
–
It can learn shared patterns so that the individual experts don’t have to relearn the same info; ie it’s to reduce redundancy among the non-shared experts
-
Scaling RL Training Boosts Larger LLMs in Math Reasoning
By
–
Why do larger LLMs get even better with reinforcement learning post-training? Researchers from USTC, Oxford, and Shanghai AI Lab reveal how scaling RL training works for math reasoning. They tested the Qwen2.5 series (0.5B to 72B) and found: – Larger models are more compute-
-
Sakana Fugu: A Multi-Agent Orchestration System as a Foundation Model
By
–
Sakana Fugu: A Multi-Agent Orchestration System as a Foundation Model
-
April 2025 AI Architecture Drops: Six New Models Released
By
–
Here is a 2nd batch of April architecture drops. What a month!
– Ant Ling 2.6 1T
– Minimax M2.7
– Xiaomi MiMo V2.5
– Poolside Laguna XS.2
– Tencent Hy3-preview
– IBM Granite 4.1 -
AI Detects Thymus Health in Elderly People Unexpectedly
By
–
My Ground Truths post was about the unanticipated, remarkable AI- enabled detection of thymus health in people of advanced age. Today @Carolynyjohnson wrote about it here @PostHealthSci gift link
-
Top AI Papers of the Week: Agents, MAS, and Agentic Models
By
–
The Top AI Papers of the Week (April 26 – May 3) – Latent Agents
– RecursiveMAS
– OneManCompany
– AgenticQwen-30B-A3B
– Agentic World Modeling
– Agentic Harness Engineering
– From Skill Text to Skill Structure Read on for more: