Top Papers of the week（Dec 18 - Dec 24）
1.Gemini: A Family of Highly Capable Multimodal Models ( paper )
2.An In-depth Look at Gemini's Language Abilities ( paper )
3.AppAgent: a novel LLM-based multimodal agent framework designed to operate smartphone applications ( repo )
4.Retrieval-Augmented Generation for Large Language Models: A Survey( paper )
5.LLM in a flash: Efficient Large Language Model Inference with Limited Memory( paper )
6.StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation ( paper | code )
7.Mini-GPTs: Efficient Large Language Models through Contextual Pruning (paper)
8.Social Learning: Towards Collaborative Learning with Large Language Models ( paper )
9.ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent ( paper )
10.DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models ( paper | webpage | code )
AIGC News of the week（Dec 18 - Dec 24）
Google VideoPoet: A large language model for zero-shot video generation ( google research | sites )
AnyDoor: Zero-shot Object-level Image Customization ( repo )
Accessibility update: arXiv now offers papers in HTML format ( arxiv blog )
NLP Research in the Era of LLMs ( link )
PowerInfer:High-speed Large Language Model Serving on PCs with Consumer-grade GPUs ( repo )
Google Gemini is not even as good as GPT-3.5 Turbo, researchers find ( link )
Advanced RAG Techniques: an Illustrated Overview ( link )
NeurIPS 2023 Recap — Best Papers ( link )
Daily Papers of the week（Dec 18 - Dec 24）
12.18
12.19
12.20
12.21
12.22
Starting from January 1, 2024, the AIGC Deep Articles will begin to be updated, covering topics such as World Model, Agents and RAG, etc. Those interested in subscribing can opt for a monthly or annual membership. We look forward to your subscription.