ProCreate, Dont Reproduce! Propulsive Energy Diffusion for Creative Generation https://
huggingface.co/papers/2408.02
226
… In this paper, we propose ProCreate, a simple and easy-to-implement method to improve sample diversity and creativity of diffusion-based image generative models and to
RESEARCH
-
ProCreate: Propulsive Energy Diffusion for Creative Image Generation
By
–
-
GPUDrive: Multi-Agent Driving Simulation at 1 Million FPS
By
–
GPUDrive
— AK (@_akhaliq) 6 août 2024
Data-driven, multi-agent driving simulation at 1 million FPShttps://t.co/IiIz8hppDk
Multi-agent learning algorithms have been successful at generating superhuman planning in a wide variety of games but have had little impact on the design of deployed multi-agent… pic.twitter.com/X1gZKiFpZDGPUDrive Data-driven, multi-agent driving simulation at 1 million FPS https://
huggingface.co/papers/2408.01
584
… Multi-agent learning algorithms have been successful at generating superhuman planning in a wide variety of games but have had little impact on the design of deployed multi-agent -
MeshAnything V2: Artist-Created Mesh Generation with Adjacent Tokenization
By
–
MeshAnything V2
— AK (@_akhaliq) 6 août 2024
Artist-Created Mesh Generation with Adjacent Mesh Tokenization
demo: https://t.co/QXRUqBcyrI
Equipped with the newly proposed Adjacent Mesh Tokenization (AMT), MeshAnything V2 significantly surpasses MeshAnything in both performance and efficiency. MeshAnything… pic.twitter.com/hEnAlVhF8rMeshAnything V2 Artist-Created Mesh Generation with Adjacent Mesh Tokenization demo: https://
huggingface.co/spaces/Yiwen-n
tu/MeshAnythingV2
… Equipped with the newly proposed Adjacent Mesh Tokenization (AMT), MeshAnything V2 significantly surpasses MeshAnything in both performance and efficiency. MeshAnything -
Self-Taught Evaluators: Model-Based Evaluation Without Large Human Datasets
By
–
Self-Taught Evaluators https://
huggingface.co/papers/2408.02
666
… Model-based evaluation is at the heart of successful model development — as a reward model for training, and as a replacement for human evaluation. To train such evaluators, the standard approach is to collect a large amount of -
OpenAI Co-founder Takes Sabbatical While Pursuing Safe AGI
By
–
I’m taking a sabbatical through end of year. First time to relax since co-founding OpenAI 9 years ago. The mission is far from complete; we still have a safe AGI to build.
-
The Challenge of LLM Consistency and Truthfulness
By
–
The Problem with Lying is Keeping Track of All the Lies https://
bit.ly/3LhJkBa
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Technology Cycle: Unreliability, Reliability, Computerization, Unreliability
By
–
The fate of every technology is to start out unreliable, gradually become more reliable, and then be computerized and become unreliable again.
-
Tribute to Brilliant AI Researcher Leaving OpenAI
By
–
Thank you for everything you've done for OpenAI! You are a brilliant researcher, a deep thinker about product and society, and mostly, you are a great friend to all of us. We will miss you tremendously and make you proud of this place. (I first met John in a cafe in Berkeley in
-
Great minds think alike natural or artificial intelligence
By
–
Great minds think alike, whether they're natural or artificial.
-
Cerebras Wafer Scale Engines: Superior AI Hardware Architecture
By
–
What makes Cerebras Wafer Scale Engines better for AI than GPUs?
— Cerebras (@cerebras) 5 août 2024
Cerebras CTO and cofounder, Sean Lie, sat down with @FoundationCap's @vassallo to explain.
Sean talks end-to-end system design, the power of sparsity, and why wafer-scale clusters are the best tools for AI… https://t.co/qZbWamoh9jWhat makes Cerebras Wafer Scale Engines better for AI than GPUs? Cerebras CTO and cofounder, Sean Lie, sat down with @FoundationCap
's @vassallo to explain. Sean talks end-to-end system design, the power of sparsity, and why wafer-scale clusters are the best tools for AI