JUNE
JUNE updates. Focusing on quality over quantity now.
1. Meta Quest 3 officially announced by Mark Zuckerberg
3. AVFormer: Injecting vision into frozen speech models for zero-shot AV-ASR
4. SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
5. Bytes Are All You Need: Transformers Operating Directly On File Bytes
6. Diffusion Self-Guidance for Controllable Image Generation
8. Humans in 4D: Reconstructing and Tracking Humans with Transformers
10. Segment Anything in High Quality
13. VideoComposer: Compositional Video Synthesiswith Motion Controllability
14. Meet LTM-1: LLM with 5,000,000 prompt tokens (coming in future)
15. Text-to-3D Character From DAZ 3D
16. AlphaDev, an AI system using reinforcement learning to discover enhanced computer science algorithms
17. Stability AI launches Uncrop, a new outpainting tool powered by Stable Diffusion XL
18. Recognize Anything: A Strong Image Tagging Model
19. Tracking Everything Everywhere All at Once
20. Meta just released MusicGen, a simple and controllable model for music generation
21. OpenLLaMA 7B trained on 1T tokens
22. Google's Generative AI support on Vertex AI is now generally available (PaLM 2 and more)
25. Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
26. Augmenting Language Models with Long-Term Memory
27. Google: How AI makes virtual clothing try-on more realistic
28. Seeing the World through Your Eyes
29. Progressively Optimized Local Radiance Fields for Robust View Synthesis (Better NeRFs)
30. MetaAI: Introducing Voicebox, a new breakthrough generative speech system
32. DeepMind: Introducing RoboCat, a new AI model designed to operate multiple robots
33. MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing
34. Textbooks Are All You Need
35. Inflection-1, powering Pi - outperforming GPT-3.5, Llama and PALM-540B
36. Stability AI - Stable Diffusion XL 0.9 (SDXL 0.9)
38. zeroscope_v2 - Open Source Text to Video Model
40. Salesforce Introduces XGen-7B, a new 7B LLM trained on 8K seq. length for 1.5T tokens
41. Introducing Playground with Mixed Image Editing - AI Image Editor
42. New GPT-4 powered Microsoft Shopping tools arrive on the new Bing and Edge
44. Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
45. CSM AI releases Any Image to 3D
46. One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
47. DreamDiffusion: Generating High-Quality Images from Brain EEG Signals
48. OpenFlamingo V2
49. Pi chatbot now available in over 70+ countries
Comments
Post a Comment