Krishna Mohan
@KMohan2006
Followers
2K
Following
33K
Media
242
Statuses
3K
Denoising present to hopefully get brighter future | loves diffusion models
GPU
Joined May 2024
RT @natolambert: My top 5 most memorable models from using them at/soonafter launch:.1. Claude 3.5 Sonnet (personality, all round perf).2.….
0
11
0
RT @jxmnop: curious about the training data of OpenAI's new gpt-oss models? i was too. so i generated 10M examples from gpt-oss-20b, ran….
0
522
0
RT @LeonardoAi_: Lucid Origin has cracked top 10 in the leaderboards. Ranked #8 in the world's top text-to-image gen models on @Artificia….
0
8
0
In brief, everything is just an optimization.
0
0
5
Morning with attention sinks.
I've written the full story of Attention Sinks — a technical deep-dive into how the mechanism was developed and how our research ended up being used in OpenAI's new OSS models. For those interested in the details:.
0
0
14
RT @AnthropicAI: Today we're releasing Claude Opus 4.1, an upgrade to Claude Opus 4 on agentic tasks, real-world coding, and reasoning. htt….
0
1K
0
They cooked world model 🔥.
What if you could not only watch a generated video, but explore it too? 🌐. Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵
0
0
9
RT @GoogleDeepMind: What if you could not only watch a generated video, but explore it too? 🌐. Genie 3 is our groundbreaking world model th….
0
3K
0
RT @cwolferesearch: Reinforcement Learning (RL) is quickly becoming the most important skill for AI researchers. Here are the best resource….
0
256
0
RT @TheAITimeline: 🚨This week's top AI/ML research papers:. - GSPO.- Diffusion Beats Autoregressive in Data-Constrained Settings.- Gemini 2….
0
73
0
Discipline is explaining to your brain that you need to sacrifice immediate pleasures for greater rewards in future.
0
0
13