Hugging Face's logo
Feynman Innovations's picture
84 54 126

Feynman Innovations

ajibawa-2023
samusenps's profile picture shyamsubbu's profile picture floydprice's profile picture
·

AI & ML interests

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

Recent Activity

reacted to singhsidhukuldeep's post with 🔥 12 days ago
Exciting Research Alert: Revolutionizing Complex Information Retrieval! A groundbreaking paper from researchers at MIT, AWS AI, and UPenn introduces ARM (Alignment-Oriented LLM-based Retrieval Method), a novel approach to tackle complex information retrieval challenges. >> Key Innovations Information Alignment The method first decomposes queries into keywords and aligns them with available data using both BM25 and embedding similarity, ensuring comprehensive coverage of information needs. Structure Alignment ARM employs a sophisticated mixed-integer programming solver to identify connections between data objects, exploring relationships beyond simple semantic matching. Self-Verification The system includes a unique self-verification mechanism where the LLM evaluates and aggregates results from multiple retrieval paths, ensuring accuracy and completeness. >> Performance Highlights The results are impressive: - Outperforms standard RAG by up to 5.2 points in execution accuracy on Bird dataset - Achieves 19.3 points higher F1 scores compared to existing approaches on OTT-QA - Reduces the number of required LLM calls while maintaining superior retrieval quality >> Technical Implementation The system uses a three-step process: 1. N-gram indexing and embedding computation for all data objects 2. Constrained beam decoding for information alignment 3. Mixed-integer programming optimization for structure exploration This research represents a significant step forward in making complex information retrieval more efficient and accurate. The team's work demonstrates how combining traditional optimization techniques with modern LLM capabilities can solve challenging retrieval problems.
reacted to Tonic's post with 🔥 12 days ago
🙋🏻‍♂️hey there folks , Goedel's Theorem Prover is now being demo'ed on huggingface : https://huggingface.co/spaces/Tonic/Math give it a try !
reacted to hba123's post with 🔥 12 days ago
We developed a method that ensures almost-sure safety (i.e., safety with probability approaching 1). We proved this result. We then, present a practical implementation which we call InferenceGuard. InferenceGuard has impressive practical results: 91.04% on Alpaca-7B and 100% safety results on Beaver 7B-v3. Now, it is easy to get high safety results like those if we want a dumb model, e.g., just don't answer or answer with EOS and so on. However, our goal is not to only have safe results, but also to make sure that the rewards are high - we want a good trade-off between safety and rewards! That's exactly, what we show. InferenceGuard achieves that! Check it out: https://huggingface.co/papers/2502.01208
View all activity

Organizations

Stanford AI's profile picture AI FILMS's profile picture Giskard's profile picture AI vulnerability Database (AVID)'s profile picture FreedomAI's profile picture Ontocord's M*DEL'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 Cognitive Computations's profile picture M4-ai's profile picture Data Is Better Together Contributor's profile picture

ajibawa-2023's activity

upvoted a collection 19 days ago
upvoted 12 papers about 2 months ago
upvoted an article 4 months ago
view article
Article

🇮🇹🇯🇵🇧🇷 Generating multilingual instruction datasets with Magpie 🐦‍⬛

By anakin87 •
• 19
upvoted a paper 4 months ago
upvoted a paper 5 months ago
upvoted 2 collections 5 months ago
upvoted 2 papers 5 months ago