Look Again, YOLO: Baidu’s RT-DETR Detection Transformer Achieves SOTA Results on Real-Time Object Detection
@jiqizhixin
-
Huawei DiffFit Enables Diffusion Models Transfer to New Domains
By
–
Huawei’s DiffFit Unlocks the Transferability of Large Diffusion Models to New Domains
-
DeepMind and MPG Launch Meta-Learned Cognition Research Program
By
–
DeepMind & MPG Establish a Research Program for Meta-Learned Models of Cognition
-
SpectFormer Improves Vision Transformers via Frequency Attention
By
–
Microsoft & Bath U’s SpectFormer Significantly Improves Vision Transformers via Frequency and Attention https://
syncedreview.com/2023/04/18/mic
rosoft-bath-us-spectformer-significantly-improves-vision-transformers-via-frequency-and-attention/
… -
Google and UC Berkeley’s Self-Debugging Framework for LLMs
By
–
Google & UC Berkeley’s ‘Self-Debugging’ Framework Teaches LLMs to Debug Their Own Code https://
syncedreview.com/2023/04/17/goo
gle-uc-berkeleys-self-debugging-framework-teaches-llms-to-debug-their-own-code/
… -
Microsoft LLMA Accelerates LLM Generation via Inference Reference Decoding
By
–
Microsoft’s LLMA Accelerates LLM Generations via an ‘Inference-With-Reference’ Decoding Approach
-
Stanford and Google’s Generative Agents Mimic Human Behavior
By
–
Stanford U & Google’s Generative Agents Produce Believable Proxies of Human Behaviours https://
syncedreview.com/2023/04/12/sta
nford-u-googles-generative-agents-produce-believable-proxies-of-human-behaviours/
… -
Pix2Video: Text-Guided Video Editing via Image Diffusion
By
–
Adobe & UCL’s Pix2Video: Text-Guided Editing via Image Diffusion Without Preprocessing or Finetuning
-
UC Berkeley’s Instruct-NeRF2NeRF Edits 3D Scenes With Text
By
–
UC Berkeley’s Instruct-NeRF2NeRF Edits 3D Scenes With Text Instructions https://
syncedreview.com/2023/04/10/uc-
berkeleys-instruct-nerf2nerf-edits-3d-scenes-with-text-instructions/
… -
Google TPU v4 Supercomputer Outperforms Nvidia A100 in Speed
By
–
Google Reveals Its Latest TPU v4-Based Supercomputer, Which Betters Nvidia’s A100s in Speed and Efficiency