a novel framework that redefines the global pruning process into manageable, coordinated subproblems, allowing for resource-efficient optimization with global optimality
@jiqizhixin
-
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 -
AI Research Challenges: Open Science and Responsible Development
By
–
the paper aim to address critical challenges in contemporary AI research, foster open science, redefine scientific communication, lay the groundwork for AI-driven scientific discovery, and promote responsible AI development.
-
SJTU GAIR-NLP Group Shares OpenAI o1 Replication Journey
By
–
Nice! SJTU GAIR-NLP Group introduces their OpenAI o1 Replication Journey. https://
github.com/GAIR-NLP/O1-Jo
urney/blob/main/resource/report.pdf
… https://
github.com/GAIR-NLP/O1-Jo
urney
… By providing a comprehensive, real-time account of our journey to replicate the groundbreaking o1 model, -
VIDEO OCEAN: Advanced AI-Powered Video Generation Tool
By
–
BIG NEWS!!! VIDEO OCEAN from luchentech empowers you with advanced tools and detailed resources, all designed to simplify the complexities of video generation.#sora #LLMs https://t.co/dPO8t3UP7W pic.twitter.com/68xOCPjOb8
— 机器之心 JIQIZHIXIN (@jiqizhixin) 8 octobre 2024BIG NEWS!!! VIDEO OCEAN from luchentech empowers you with advanced tools and detailed resources, all designed to simplify the complexities of video generation.#sora #LLMs https://
video.luchentech.com -
Safe Reinforcement Learning: Methods, Theories and Applications Review
By
–
A Review of Safe Reinforcement Learning: Methods, Theories and Applications https://
ieeexplore.ieee.org/abstract/docum
ent/10675394
… https://
github.com/chauncygu/Safe
-Reinforcement-Learning-Baselines
… This paper provide a review of safe RL from the perspectives of methods, theories, and applications. -
Carnegie Mellon AI4BIO Center Revolutionizes Biomedicine Research
By
–
Exciting news from @CarnegieMellon
! The new AI4BIO center is set to revolutionize biomedicine with cutting-edge AI and machine learning. Unlocking the secrets of gene regulation and disease progression could transform healthcare. #AI #Biomedicine #Innovation #CMU -
Oryx MLLM: Spatial-Temporal Understanding at Arbitrary Resolution
By
–
Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution https://
oryx-mllm.github.io https://
arxiv.org/abs/2409.12961
The work proposes Oryx, a unified multimodal architecture for the spatial-temporal understanding of images, videos, and multi-view 3D scenes. -
Critic Plasticity Loss Bottleneck in Deep Reinforcement Learning
By
–
(1) data augmentation is essential in maintaining plasticity; (2) the critic's plasticity loss serves as the principal bottleneck impeding efficient training; and (3) without timely intervention to recover critic's plasticity in the early stages, its loss becomes catastrophic.
-
Plasticity in Visual Reinforcement Learning: Data and Training
By
–
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages #ICLR2024 https://
arxiv.org/abs/2310.07418 https://
github.com/Guozheng-Ma/Ad
aptive-Replay-Ratio
…
we conduct a systematic empirical exploration focusing on three primary underexplored facets and derive the following conclusions: