코코 @R_U_Sure_o

Joined July 2023

Tweets

10
Followers

1
Following

48
Likes

17

elvis @omarsar0

2 months ago

Agentic RAG for Personalized Recommendation This is a really good example of integrating agentic reasoning into RAG. Leads to better personalization and improved recommendations. Here are my notes:

10 170 1K 91K 1K

Download Image

The best data scientists are experts at getting LLMs to do their bidding For example, the Abacus AI co-pilot will do data wrangling, EDA, algorithm exploration and build a production ready model in hours based on your prompts! Data science is now largely a thinking…

16 136 683 70K 584

Download Image

virat @virattt

a year ago

Fine-tuning a Warren Buffett LLM 🧠 I started this workstream today. Overall goal: fine-tune an LLM to analyze companies like Mr. Buffett does. My initial setup: • use mistral 7b instruct • use single gpu in colab • use QLoRA for fast fine-tune • use small dataset to prove…

25 91 729 166K 1K

Download Image

골빈해커 @golbin

a year ago

📝 교육의 미래에 대한 논문 What Should Data Science Education Do with Large Language Models? 워싱턴, 스탠포드, 펜실배니아, 럿거스 대학에서 공동 연구한 논문. LLM이 이제 데이터 정리, 모델 개발, 해석, 보고서 작성 등 데이터 분석 파이프라인의 거의 모든 일을 다 할 수 있게 되었기…

6 194 351 37K 280

Download Image

AK @_akhaliq

a year ago

Can large language models explore in-context? We investigate the extent to which contemporary Large Language Models (LLMs) can engage in exploration, a core capability in reinforcement learning and decision making. We focus on native performance of existing LLMs, without

2 35 166 25K 77

Download Image

AK @_akhaliq

a year ago

Compress3D a Compressed Latent Space for 3D Generation from a Single Image 3D generation has witnessed significant advancements, yet efficiently producing high-quality 3D assets from a single image remains challenging. In this paper, we present a triplane autoencoder, which

3 22 113 12K 56

Download Video

Jeff Dean @JeffDean

a year ago

We're starting to roll out API support for Gemini 1.5 Pro for developers. We're excited to see what you build with the 1M token context window! We'll be onboarding people to the API slowly at first, and then we'll ramp it up. In the meantime, developers can try out Gemini 1.5…

Jeff Dean @JeffDean

2 years ago

187 1K 6K 1.7M 2K

Download Image

92 382 2K 624K 656

elvis @omarsar0

a year ago

Tool Use in LLMs Great paper to catch up on the latest developments in tool usage with LLMs. It provides an overview of tool use in LLMs, including a formal definition of the tool-use paradigm, scenarios where LLMs leverage tool usage, and for which tasks this approach works…

5 144 638 46K 543

Download Image

DAIR.AI @dair_ai

2 years ago

The Top ML Papers of the Week (Jan 1 - Jan 7): - DocLLM - Mobile ALOHA - Self-Play Fine-tuning - Fast Inference of MoE - LLM Augmented LLMs - Mitigating Hallucination in LLMs ...

8 85 467 81K 350

DAIR.AI @dair_ai

2 years ago

Top ML Papers of the Week (Oct 2 - Oct 8): - StreamingLLM - Analogical Prompting - The Dawn of LMMs - Neural Developmental Programs - LLMs Represent Space and Time - Retrieval meets Long Context LLMs ... ---- 1/ LLMs Represent Space and Time - discovers that LLMs learn linear…