SafeDiffuser: Safe Planning with Diffusion Probabilistic Models paper page: https://
huggingface.co/papers/2306.00
148
… propose a new method, called SafeDiffuser, to ensure diffusion probabilistic models satisfy specifications by using a class of control barrier functions. The key idea of our
RESEARCH
-
SafeDiffuser: Safe Planning with Diffusion Probabilistic Models
By
–
-
ByteFormer: Transformers Processing Raw File Bytes for Image Classification
By
–
Bytes Are All You Need: Transformers Operating Directly On File Bytes paper page: https://
huggingface.co/papers/2306.00
238
… ByteFormer, achieves an ImageNet Top-1 classification accuracy of 77.33% when training and testing directly on TIFF file bytes using a transformer backbone with -
Brainformers: Trading Simplicity for Efficiency in Transformers
By
–
Brainformers: Trading Simplicity for Efficiency paper page: https://
huggingface.co/papers/2306.00
008
… develop a complex block, named Brainformer, that consists of a diverse sets of layers such as sparsely gated feed-forward layers, dense feed-forward layers, attention layers, and various forms -
Understanding Transformer Internal Mechanisms Through Memory Analysis
By
–
Birth of a Transformer: A Memory Viewpoint paper page: https://
huggingface.co/papers/2306.00
802
… Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms -
Analyzing Attention Glitches in Transformer Language Models
By
–
Exposing Attention Glitches with Flip-Flop Language Modeling abs: https://
arxiv.org/abs/2306.00946 identifies and analyzes the phenomenon of attention glitches, in which the Transformer architecture's inductive biases intermittently fail to capture robust reasoning. To isolate the -
Hiera: Hierarchical Vision Transformer Simplified Architecture
By
–
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles abs: https://
arxiv.org/abs/2306.00989 Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance. While these components lead to -
Understanding Concept Representations in Text-to-Image Diffusion Models
By
–
The Hidden Language of Diffusion Models
— AK (@_akhaliq) 2 juin 2023
paper page: https://t.co/biwX1KX7hG
tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a… pic.twitter.com/mF0QzNxAjoThe Hidden Language of Diffusion Models paper page: https://
huggingface.co/papers/2306.00
966
… tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a -
AI Expectations Paradox: Short-term Hype, Long-term Underestimation
By
–
the paradox of ai expectations: expectations of what AI will do in the next 1-2 years are always too high but expectations of AI will do in 5+ years are usually too low 5 years ago we were in self-driving summer. we didn’t get L5 autonomy, but we got the FAR more powerful LLMs
-
AI-Controlled Drone Kills Operator in USAF Simulated Test
By
–
“We trained the system–‘Hey don’t kill the operator–that’s bad. You’re gonna lose points..’ So what does it start doing? It starts destroying the communication tower that the operator uses to communicate with the drone to stop it from killing the target.” https://
vice.com/en/article/4a3
3gj/ai-controlled-drone-goes-rogue-kills-human-operator-in-usaf-simulated-test
… -
ReviewerGPT: Using Large Language Models for Scientific Paper Review
By
–
ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing Given the rapid ascent of large language models (LLMs), we study the question: (How) can large language models help in reviewing of scientific papers or proposals? We first conduct some pilot