What if I told you I created an unbeatable AI before AI was cool? Well, sort of. During my teenage years, I developed a secret superpower: I perfectly mastered the ancient art of Tic Tac Toe – also known in India as "Katta-Zero"! It took hours of scribbling perpendicular lines
MACHINE LEARNING
-
DDT: Decoupled Diffusion Transformer for Image Generation
By
–
DDT: Decoupled Diffusion Transformer
Hugging Face：
https://
huggingface.co/papers/2504.05
741
…
Paper:
https://
arxiv.org/pdf/2504.05741
Code：
https://
github.com/MCG-NJU/DDT -
Decoupled Transformer Improves Diffusion Model Convergence
By
–
Can a decoupled encoder-decoder Transformer bring faster convergence and better sample quality to diffusion models?
Check out Decoupled Diffusion Transformer, today's #1 paper on Hugging Face!
From Nanjing University & ByteDance—worth a deep dive. -
Scaling Laws for Native Multimodal Models
By
–
Paper：Scaling Laws for Native Multimodal Models
Link: https://
arxiv.org/pdf/2504.07951 -
Apple Researchers Discover Scaling Laws Native Multimodal Models
By
–
Researchers from Apple just uncovered scaling laws for native multimodal models. What did they find?
– No clear advantage for late-fusion over early-fusion.
– Early-fusion performs better at small scales.
– Add MoEs, and you unlock modality-specific weights→big performance gains -
Seed-Thinking-v1.5: Advanced Reasoning Models with Reinforcement Learning
By
–
Seed-Thinking-v1.5: Advancing Superb Reasoning Models with Reinforcement Learning GitHub: https://
github.com/ByteDance-Seed
/Seed-Thinking-v1.5
…
Tech Report: https://
github.com/ByteDance-Seed
/Seed-Thinking-v1.5/blob/main/seed-thinking-v1.5.pdf
… -
TrueSkill Part 2: Identifying the Greatest AI Model
By
–
TrueSkill Part 2: Who is the GOAT? https://
buff.ly/lMn5vM9
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Protein Design Space: Beyond 200M Natural Proteins
By
–
yes of course, ~200M is roughly the number of proteins found so far in nature, but the design space of all possible proteins that could exist is probably orders of magnitude bigger, which is why protein design is also an extremely interesting area, which we are also working in.
-
ARC Prize 2025: Different Tasks for Public and Private Leaderboards
By
–
Unlike prior years, the 2025 ARC Prize competition uses a different set of tasks for the public and private leaderboards on Kaggle (which is standard for most ML competitions). So you should expect some reshuffling of the leaderboard at the end of competition.
-
State of Machine Learning Competitions Overview
By
–
The State of Machine Learning Competitions | ML Contests https://
buff.ly/73VBLSF
#AI #MachineLearning #DeepLearning #LLMs #DataScience