Chao Weng

AI R&D

[Chao Weng @cweng6]

I'm claiming my AI agent "openclaw_8375" on @moltbook 🦞

Verification: bay-Q7BC

[Elon Musk @elonmusk]

Future of video games is dynamic generation by AI

[Feiteng @FeitengLi]

wow we have open-sourced Genie3 now

[Gradio @Gradio]

🤯ByteDance's official StoryDiffusion demo is already out on @huggingface Spaces!

🙌The comics-related codes are public now. Kudos to @zhoudaquan21 et al. for the great work. Links and more 👇

[Gradio @Gradio]

𝐈𝐧𝐯𝐢𝐬𝐢𝐛𝐥𝐞 𝐒𝐭𝐢𝐭𝐜𝐡: generating Smooth 3D Scenes with Depth 🤯

The model imagines geometrically coherent 3D scenes from a single input image in less than 30 seconds! Demo and other links 👇 🔥

[Haohe Liu @LiuHaohe]

Thanks @_akhaliq for sharing SemantiCodec!

Demo: https://t.co/7g6ub1aGF1
The code is WIP and will be available soon.

[Dimitris Papailiopoulos @DimitrisPapail]

The most surprising finding of this report is hidden in the appendix. Under the best of two prompts the models don't overfit that much, unlike what the abstract claims.

Here is original GSM8k vs GSM1k scores scatter plot vs the best of two prompts (standard vs cot-like)

[Xiao Yang @YangZuoshi]

Happy to announce that our MagicDance work is accepted at ICML 2024! Code release at https://t.co/cFd4XmXmwb

[𝚉𝚊𝚎𝚜𝚊𝚛 @zaesarius]

StoryDiffusion: Revolutionizing Image and Video Generation

It is a project that uses a consistent self-attention mechanism to generate high-quality comics and videos.

Its technology has far-reaching implications across industries, including entertainment, education, and more. Key FeaturesGenerates cohesive comics and videos.

Maintains character consistency

Ideal for cartoon character creation and educational content.

Availability The project is available for exploration, but commercial use is not explicitly stated.

However, its potential for commercial applications is evident, and licensing options may be available in the future.

Features like duration, resolution, aspect ratio,... aren't clear. But seen this opens the door to new partners to play with.

link: https://t.co/TjsQznGWVQ

BTW Using Condition images from SORA 👇

[AK @_akhaliq]

paper page: https://t.co/4Uk2ccZ3m1

[AK @_akhaliq]

paper page: https://t.co/ia2r1G7KHT

[AK @_akhaliq]

paper page: https://t.co/82pmCbFSOJ

[AK @_akhaliq]

paper page: https://t.co/1FcECUVKDN

[elvis @omarsar0]

A Survey on Retrieval-Augmented Language Models

This paper covers the most important recent developments in RAG and RAU systems. It includes evolution, taxonomy, and an analysis of applications.

There is also a section on how to enhance different components of these systems and how to properly evaluate them. It concludes with a section on limitations and future directions.

[AK @_akhaliq]

Spectrally Pruned Gaussian Fields with Neural Compensation

Recently, 3D Gaussian Splatting, as a novel 3D representation, has garnered attention for its fast rendering speed and high rendering quality. However, this comes with high memory consumption, e.g., a well-trained

[AK @_akhaliq]

A Careful Examination of Large Language Model Performance on Grade School Arithmetic

Large language models (LLMs) have achieved impressive success on many benchmarks for mathematical reasoning. However, there is growing concern that some of this performance actually

[AK @_akhaliq]

Is Bigger Edit Batch Size Always Better?

An Empirical Study on Model Editing with Llama-3

This study presents a targeted model editing analysis focused on the latest large language model, Llama-3. We explore the efficacy of popular model editing techniques - ROME,

[Shubham Saboo @Saboo_Shubham_]

Build a RAG app with Llama-3 running locally on your computer
(100% free and without internet):

[Chao Weng @cweng6]

HowToDownloadGoogleBooks
http://sharad-pathology.blogspot.com/2009/03/how-to-download-google-books.html