Top Papers of the week(Nov 27 - Dec 03)
1.VCHITECT: A GENERALIST VIDEO GENERATION SYSTEM FOR CINEMATIC STORYTELLING(paper | webpage | code | demo)
2.Qwen-72B approaches GPT-4 on many task except coding (Technical Report | code | model )
3.DeepSeek-67B approaches GPT-4 on reasoning tasks (code | model )
4.CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation(paper | webpage )
5.GAIA: Zero-shot Talking Avatar Generation(paper | webpage)
6.One-step Diffusion with Distribution Matching Distillation(paper | webpage)
7.Diffusion Models Without Attention(paper)
8.Initializing Models with Larger Ones(paper | code )
9.Language Models: A Guide for the Perplexed(paper)
10.TLcontrol: Trajectory and Language Control for Human Motion Synthesis(paper | webpage)
11.Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models(paper | webpage)
12.Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation(paper | webpage)
AIGC News of the week(Nov 27 - Dec 03)
1.Seamless Communication:A significant step towards removing language barriers through expressive, fast and high-quality AI translation(metaAI)
2.Generative AI to Become a $1.3 Trillion Market by 2032, Research Finds(link)
3.Using GPTs as Team Members(link)
4.langchain blog: 1.OpenAI's Bet on a Cognitive Architecture 2.Adding Long Term Memory to OpenGPTs
5.The AI Battlefield Engineering - What You Need To Know(link)
6.Information Retrieval: Who wins, GPT-4-Turbo or a RAG based on GPT4?(repo)
7.Interview: Sam Altman on being fired and rehired by OpenAI(news)
8.RAGs To Riches: Bringing Wandbot into Production(link)