This is just absurd, how can this happen in Neurips?

Best attention visualization ever

Vision-Flan Scaling Human-Labeled Tasks in Visual Instruction Tuning Despite vision-language models' (VLMs) remarkable capabilities as versatile visual assistants, two substantial challenges persist within the existing VLM frameworks: (1) lacking task diversity in pretraining

Have you ever done a dense grid search over neural network hyperparameters? Like a *really dense* grid search? It looks like this (!!). Blueish colors correspond to hyperparameters for which training converges, redish colors to hyperparameters for which training diverges.

Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. https://t.co/7j2JN27M3W Prompt: “Beautiful, snowy

Announcing Sora — our model which creates minute-long videos from a text prompt: https://t.co/SZ3OxPnxwz

Wishing everyone a happy Chinese New Year!

🌎 𝕤𝕒𝕪 𝕙𝕖𝕝𝕝𝕠 𝕥𝕠 𝕧𝕚𝕣𝕝 🌏 https://t.co/eBq55NxcbJ

❗❗❗Workshop Call for Paper❗❗❗ Interested in trustworthy learning on graphs? We are inviting contributions to the 2nd Workshop on Trustworthy Learning on Graphs (TrustLOG), colocated with WWW2024. Workshop website: https://t.co/uYElfQIBtH Deadline: February 13, 2024

Thrilled to share that we @osunlp have 5 papers accepted to #ICLR2024 (2 spotlights/3 posters), covering LLM knowledge conflicts, math LLMs, language agents, interpretable transformer, and instruction tuning. Interestingly it's my first ICLR papers. Glad to get 5 firsts! 🧵

New 𝐬𝐮𝐫𝐯𝐞𝐲 paper about "𝐋𝐋𝐌𝐬 𝐨𝐧 𝐆𝐫𝐚𝐩𝐡𝐬"! We provide a comprehensive overview of LLMs on graphs. We systematically summarize scenarios where LLMs are utilized on graphs and discuss specific techniques. paper:

🚀 Introducing MMMU, a Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI. https://t.co/vPw4beOeha 🧐 Highlights of the MMMU benchmark: > 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks >

We published the list of papers accepted to #NeurIPS2023 here: https://t.co/TWLudQGKJE

https://t.co/WGvwrT09yy

Our new work ✨The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models✨ is accepted to #EMNLP2023. Inspired by the human cognitive process, we propose SOCRATIC QUESTIONING, a divide-and-conquer style algorithm that mimics the 🤔recursive thinking process.

Nice work by Zhiyang, please give it a try if you want to benchmark multimodal instruction tuning!

Today we officially release ✨Vision-Flan✨, the largest human-annotated visual-instruction tuning dataset with 💥200+💥 diverse tasks. 🚩Our dataset is available on Huggingface https://t.co/XqFrpudysl 🚀 For more details, please refer to our blog

Dive into ICML 2023 papers effortlessly! 🧐 Introducing a handy toy tool for paper collection and filtering. Whether you want the full list or targeted topics, this GitHub repo has got you covered:

🤔 How to let Large Language Models (LLMs) agent utilize diverse tools via Tree Search 🔍? In AVIS, we enable LLM Agent to dynamically traverse a transition graph with self-critic (when one path is not informative, backtrack to previous state). This achieves SOTA VQA result.