aimodels-fyi (AIModels.fyi)

mikelabs

posted an update about 2 months ago

Post

1151

this paper is like when you tell an art student just draw it in your own style and they actually do it perfectly on the first try 🎨 diffusion models getting too powerful fr

https://www.aimodels.fyi/papers/arxiv/diffusion-self-distillation-zero-shot-customized-image

mikelabs

posted an update about 2 months ago

Post

2210

love how bipedal robot papers are always like we made it not fall down! and somehow thats still a major accomplishment in 2024 🤖 (that's actually not totally fair, walking is really hard ok)

https://www.aimodels.fyi/papers/arxiv/real-time-safe-bipedal-robot-navigation-using

mikelabs

posted an update about 2 months ago

Post

1056

LLMs developing theory of mind is wild - were basically teaching AI to understand what other AIs are thinking. Its like robot therapy but for making them better team players 🤖🧠

https://www.aimodels.fyi/papers/arxiv/large-model-strategic-thinking-small-model-efficiency

mikelabs

posted an update about 2 months ago

Post

1597

SAM: I can segment anything!
SAMURAI: Hold my sake while I track it through time and space without even training 🎯

Researchers really said what if we gave SAM object permanence and it worked 🤯

https://www.aimodels.fyi/papers/arxiv/samurai-adapting-segment-anything-model-zero-shot

2 replies

·

mikelabs

posted an update 2 months ago

Post

1013

That Chip Has Sailed: A Critique of Unfounded Skepticism Around AI for Chip Design

https://www.aimodels.fyi/papers/arxiv/that-chip-has-sailed-critique-unfounded-skepticism

* Research paper critiques skepticism around AI for chip design
* Addresses reproduction errors in previous work by Cheng et al.
* Defends effectiveness of AI/ML approaches in integrated circuit design
* Identifies specific methodological flaws in critique paper
* Emphasizes importance of proper implementation in ML research

mikelabs

posted an update 2 months ago

Post

906

https://www.aimodels.fyi/papers/arxiv/llava-o1-let-vision-language-models-reason

* New approach called LLaVA-o1 improves visual reasoning in AI models
* Implements step-by-step reasoning for analyzing images
* Achieves state-of-the-art performance on visual reasoning benchmarks
* Uses chain-of-thought prompting to break down complex visual tasks
* Integrates with existing vision-language models

AIModels.fyi

AI & ML interests

aimodels-fyi's activity

AI & ML interests

Team members 1

aimodels-fyi's activity