a novel framework that redefines the global pruning process into manageable, coordinated subproblems, allowing for resource-efficient optimization with global optimality
MACHINE LEARNING
-
SparseLLM: Global Pruning Method for Pre-trained Language Models
By
–
SparseLLM: Towards Global Pruning of Pre-trained Language Models https://
arxiv.org/abs/2402.17946 https://
github.com/BaiTheBest/Spa
rseLLM
…
#neurips2024 -

IterComp: Iterative Composition-Aware Feedback Learning for Image Generation
By
–
IterComp Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
-

Real-Time Text Toonify Head Avatar from Single Video
By
–
TextToon
— AK (@_akhaliq) 10 octobre 2024
Real-Time Text Toonify Head Avatar from Single Video pic.twitter.com/0sXccm8IkTTextToon Real-Time Text Toonify Head Avatar from Single
-

Capturing and Physically Synthesizing Piano Hand Motions
By
–
FürElise
— AK (@_akhaliq) 10 octobre 2024
Capturing and Physically Synthesizing Hand Motions of Piano Performance pic.twitter.com/m0rvHUkdfPFürElise Capturing and Physically Synthesizing Hand Motions of Piano Performance
-

Google DeepMind Wins Nobel Prize for AI Protein Structure Prediction
By
–
Leaders of Google DeepMind along with a professor in biochemistry at the University of Washington have been awarded the Nobel Prize in Chemistry for their pioneering work in protein structure prediction using AI. This breakthrough is set to advance scientific research and aid in
-

COLM 2024 Papers Repository with API Access
By
–
COLM 2024 Papers repository with list of all accepted papers with their details Use it via API
-

CuPy: GPU-Accelerated NumPy and SciPy for AI
By
–
GitHub – cupy/cupy: NumPy & SciPy for GPU https://
bit.ly/4dAw0U1
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
The Exponential Costs of Artificial Intelligence Development
By
–
The exponential expenses of AI development
#AI #AIio #BigData #ML #NLU #Futureofwork @ahier @guzmand
@DavidBrin @denisegarth @dez_blanchfield @diioannid @DioFavatas @gerald_bader http://
ow.ly/iuVn30sH01C -

Tx-LLM Predicts Therapeutic Drug Properties with State-of-the-Art Accuracy
By
–
Development of therapeutic drugs is often difficult and time consuming. A new model, Tx-LLM, is able to predict the properties of many entities of potential interest for therapeutic development with accuracy comparable state-of-the-art specialty models.→ https://
goo.gle/3Zb3AfM