Hugging Face's logo
Feynman Innovations's picture
89 112 140

Feynman Innovations

ajibawa-2023
clem's profile picture rinosashaheed's profile picture SarosVale's profile picture
Β·

AI & ML interests

LLM, RL, DL, ML, AGI. Developing LLMs (preferably fully fine tuned ) for various use cases.

Recent Activity

reacted to DmitryRyumin's post with πŸ”₯ 5 days ago
πŸš€πŸ€–πŸŒŸ New Research Alert - ICCV 2025 (Oral)! πŸŒŸπŸ€–πŸš€ πŸ“„ Title: Variance-based Pruning for Accelerating and Compressing Trained Networks πŸ” πŸ“ Description: The one-shot pruning method efficiently compresses networks, reducing computation and memory usage while retaining almost full performance and requiring minimal fine-tuning. πŸ‘₯ Authors: Uranik Berisha, Jens Mehnert, and Alexandru Paul Condurache πŸ“… Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA πŸ‡ΊπŸ‡Έ πŸ“„ Paper: https://huggingface.co/papers/2507.12988 πŸš€ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers πŸš€ Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md πŸ“š More Papers: more cutting-edge research presented at other conferences in the https://huggingface.co/spaces/DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin πŸ” Keywords: #VarianceBasedPruning #NetworkCompression #ModelAcceleration #EfficientDeepLearning #VisionTransformers #AI #ICCV2025 #ResearchHighlight
reacted to onekq's post with πŸ‘ 5 days ago
Context rot is such a catchy phrase, but the problem has been identified 2+ years ago, called attention decay. https://huggingface.co/papers/2307.03172 I spotted the same problem in coding tasks, and documented in my book (https://www.amazon.com/dp/9999331130). Why did this problem become hot again? This is because many of us thought the problem has been solved by long context models, which is not true. Here we were misled by benchmarks. Most long-context benchmarks build around the QA scenario, i.e. "finding needle in haystack". But in agentic scenarios, the model needs to find EVERYTHING in the haystack, and just can't afford enough attention for this challenge.
reacted to di-zhang-fdu's post with πŸ”₯ 5 days ago
The training dataset of ChemVLM is open-sourced now, have a check! https://huggingface.co/datasets/di-zhang-fdu/chemvlm-sft-datasets papers: https://huggingface.co/papers/2408.07246
View all activity

Organizations

Stanford AI's profile picture AI FILMS's profile picture AI vulnerability Database (AVID)'s profile picture FreedomAI's profile picture Aurora-M/MDEL's profile picture The Waifu Research Department's profile picture Media Party 2023's profile picture Keynote Technology's profile picture ZeroGPU Explorers's profile picture Aurora-M's profile picture Ontocord.AI's profile picture One-Man-Army's profile picture MLX Community's profile picture Social Post Explorers's profile picture M4-ai's profile picture Data Is Better Together Contributor's profile picture