Mr. Agent @AgenticAI

Creator of new things. Joined May 2024

Tweets

84
Followers

66
Following

270
Likes

106

Harrison Chase @hwchase17

a year ago

❓What is an agent? I get asked this question a lot, so I wrote a little blog on this topic and other things: - What is an agent? - What does it mean to be agentic? - Why is “agentic” a helpful concept? - Agentic is new Check it out here: blog.langchain.dev/what-is-an-age…

15 43 334 57K 377

Download Image

Namgyu Ho @itsnamgyu

a year ago

Do you know your LLM uses less than 1% of your GPU at inference? Too much time is wasted on KV cache memory access ➡️ We tackle this with the 🎁 Block Transformer: a global-to-local architecture that speeds up decoding up to 20x 🚀 @kaist_ai @LG_AI_Research w/ @GoogleDeepMind 🧵

12 118 626 74K 547

Download Image

Eugene Vinitsky (@RLC) 🍒🦋 @EugeneVinitsky

a year ago

This page of common pytorch mistakes is pretty invaluable uvadlc-notebooks.readthedocs.io/en/latest/tuto…

4 106 825 80K 1K

Download Image

Aran Komatsuzaki @arankomatsuzaki

a year ago

Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities Enables MLLMs to express intermediate reasoning as images using code. You probably didn't use typography knowledge to solve this query proj: whiteboard.cs.columbia.edu abs: arxiv.org/abs/2406.14562

3 51 209 23K 112

Download Image

elvis @omarsar0

a year ago

From RAG to Rich Parameters Investigates more closely how LLMs utilize external knowledge over parametric information for factual queries. Finds that in a RAG pipeline, LLMs take a “shortcut” and display a strong bias towards utilizing only the context information to answer the…

6 92 351 28K 242

Download Image

Rohan Paul @rohanpaul_ai

a year ago

Transformer models can learn robust reasoning skills (beyond those of GPT-4-Turbo and Gemini-1.5-Pro) through a stage of training dynamics that continues far beyond the point of overfitting (i.e. with 'Grokking') 🤯 For a challenging reasoning task with a large search space,…

8 34 281 31K 242

Download Image

Aran Komatsuzaki @arankomatsuzaki

a year ago

Google presents What Are the Odds? Language Models Are Capable of Probabilistic Reasoning arxiv.org/abs/2406.12830

4 58 369 37K 272

Download Image

Sumit @_reachsumit

a year ago

A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges Explores applications of LLMs in various financial tasks, discussing the challenges, opportunities, and resources for further development in this domain. 📝arxiv.org/abs/2406.11903

0 7 20 976 11

Download Image

Harrison Chase @hwchase17

a year ago

I have lots of thoughts on "agents"! ❓What is an agent? Why do the basic agents not work reliably? How are teams bringing "agentic" applications to production 🙏I had a lot of fun talking about these topics (and more!) for nearly a hour with Sonya/Pat open.spotify.com/episode/786INO…

7 59 253 44K 253

Download Image

Tanishq Mathew Abraham, Ph.D. @iScienceLuvr

a year ago

Learning Iterative Reasoning through Energy Diffusion abs: arxiv.org/abs/2406.11179 project page: energy-based-model.github.io/ired/ "IRED learns energy functions to represent the constraints between input conditions and desired outputs. After training, IRED adapts the number of…

2 44 210 15K 116

Download Image

Tanishq Mathew Abraham, Ph.D. @iScienceLuvr

a year ago

Transcendence: Generative Models Can Outperform The Experts That Train Them abs: arxiv.org/abs/2406.11741 Uses chess games as a simple testbed for studying transcedence: generative models trained on human labels that outperform humans. Transformer models are trained on public…

6 79 308 29K 196

Download Image

DeepSeek @deepseek_ai

a year ago

DeepSeek-Coder-V2: First Open Source Model Beats GPT4-Turbo in Coding and Math > Excels in coding and math, beating GPT4-Turbo, Claude3-Opus, Gemini-1.5Pro, Codestral. > Supports 338 programming languages and 128K context length. > Fully open-sourced with two sizes: 230B (also…

61 333 2K 484K 741

Download Image

Aran Komatsuzaki @arankomatsuzaki

a year ago

How Do Large Language Models Acquire Factual Knowledge During Pretraining? Reveals several important insights into the dynamics of factual knowledge acquisition during pretraining arxiv.org/abs/2406.11813

6 77 408 54K 388

Download Image

Aran Komatsuzaki @arankomatsuzaki

a year ago

Google presents Improve Mathematical Reasoning in Language Models by Automated Process Supervision - MCTS for the efficient collection of high-quality process supervision data - 51% -> 69.4% on MATH - No human intervention arxiv.org/abs/2406.06592

5 62 348 36K 277

Download Image

Bindu Reddy @bindureddy

a year ago

Announcing LiveBench AI - The WORLD'S FIRST LLM Benchmark That Can't Be Gamed!! We (Abacus AI) partnered with Yann LeCunn and his team to create LiveBench AI! LiveBench is a living/breathing benchmark with new challenges that you CAN'T simply memorize. Unlike blind human eval,…

91 185 920 300K 482

Download Image

AK @_akhaliq

a year ago

Husky A Unified, Open-Source Language Agent for Multi-Step Reasoning Language agents perform complex tasks by using tools to execute each step precisely. However, most existing agents are based on proprietary models or designed to target specific tasks, such as

3 78 325 35K 258

Download Image

elvis @omarsar0

a year ago

Towards Lifelong Learning of LLMs Nice survey on techniques to enable LLMs to learn continuously, integrate new knowledge, retain previously learned information, and prevent catastrophic forgetting. arxiv.org/abs/2406.06391

6 86 349 30K 279

Download Image

Aran Komatsuzaki @arankomatsuzaki

a year ago

Simple and Effective Masked Diffusion Language Models Achieves a new SotA among diffusion models on a range of LM tasks and approaches AR perplexity repo: github.com/kuleshov-group… abs: arxiv.org/abs/2406.07524

5 60 255 41K 146

Download Image

Chief AI Officer @chiefaioffice

a year ago

BREAKING: Mistral raises a $640M Series B led by General Catalyst at a $6B valuation. Here's their Seed pitch deck to remind you of their vision:

22 174 1K 284K 2K

Download Image

Sumit @_reachsumit

a year ago

Synthetic Query Generation using Large Language Models for Virtual Assistants Apple investigates the use of LLMs to generate synthetic queries for virtual assistants that are similar to real user queries and specific to retrieving relevant entities. 📝arxiv.org/abs/2406.06729