

Discover more from NLP Newsletter
1). Universal Adversarial LLM Attacks - finds universal and transferable adversarial attacks that cause aligned models like ChatGPT and Bard to generate objectionable behaviors; the approach automatically produces adversarial suffixes using greedy and gradient search. (paper | tweet)
2). RT-2 - a new end-to-end vision-language-action model that learns from both web and robotics data; enables the model to translate the learned knowledge to generalized instructions for robotic control. (paper | tweet)
3). Med-PaLM Multimodal - introduces a new multimodal biomedical benchmark with 14 different tasks; it presents a proof of concept for a generalist biomedical AI system called Med-PaLM Multimodal; it supports different types of biomedical data like clinical text, imaging, and genomics. (paper | tweet)
4). Tracking Anything in High Quality - propose a framework for high-quality tracking anything in videos; consists of a video multi-object segmented and a pretrained mask refiner model to refine the tracking results; the model ranks 2nd place in the VOTS2023 challenge. (paper | tweet)
5). Foundation Models in Vision - presents a survey and outlook discussing open challenges and research directions for foundational models in computer vision. (paper | tweet)
6). L-Eval - a standardized evaluation for long context language models containing 411 long documents over 2K query-response pairs encompassing areas such as law, finance, school lectures, long conversations, novels, and meetings. (paper | tweet)
7). LoraHub - introduces LoraHub to enable efficient cross-task generalization via dynamic LoRA composition; it enables the combination of LoRA modules without human expertise or additional parameters/gradients; mimics the performance of in-context learning in few-shot scenarios. (paper | tweet)
8). Survey of Aligned LLMs - presents a comprehensive overview of alignment approaches, including aspects like data collection, training methodologies, and model evaluation. (paper | tweet)
9). WavJourney - leverages LLMs to connect various audio models to compose audio content for engaging storytelling; this involves an explainable and interactive design that enhances creative control in audio production. (paper | tweet)
10). FacTool - a task and domain agnostic framework for factuality detection of text generated by LLM; the effectiveness of the approach is tested on tasks such as code generation and mathematical reasoning; a benchmark dataset is released, including a ChatGPT plugin. (paper | tweet)
Reach out to elvis if you would like to sponsor the next issue of the newsletter. We can help promote your tool, research, company, etc.
🥇Top ML Papers of the Week
I'm particularly excited about the Med-PaLM Multimodal and L-Eval papers, as they seem to have great potential in the biomedical and long-context language model domains. Looking forward to more insightful updates.