LLM-based chatbots’ capabilities have been advancing every month. These improvements are mostly measured by benchmarks like MMLU, HumanEval, and MATH (e.g. sonnet 3.5, gpt-4o). However, as these measures get more and more saturated, is user experience increasing in proportion to these scores? If we envision a future of human-AI collaboration rather than AI replacing humans, […]
AI-generated images are not just hyper-realistic; they can also be crafted to embody an infinite variety of features, expressions, and aesthetics. A recent example is a post by Moritz Stellmacher on X that showcases a very intriguing human portrait, leaving viewers puzzled about whether it’s a photograph of a real person or an AI creation. This
Science Published 5 September 2024 Authors Protein Design and Wet Lab teams New AI system designs proteins that successfully bind to target molecules, with potential for advancing drug design, disease understanding and more. Every biological process in the body, from cell growth to immune responses, depends on interactions between molecules called proteins. Like a key
When we began studying jailbreak evaluations, we found a fascinating paper claiming that you could jailbreak frontier LLMs simply by translating forbidden prompts into obscure languages. Excited by this result, we attempted to reproduce it and found something unexpected.
Science Published 22 August 2024 Authors David Pfau and James Spencer Note: This blog was first published on 19 October 2020. Following the publication of our breakthrough work on excited states in Science on 22 August 2024, we’ve made minor updates and added a section below about this new phase of work. Using deep learning
Large language models (LLMs) are incredible tools that enable new ways for humans to interact with computers and devices. These models are frequently run on specialized server farms, with requests and responses ferried over an internet connection. Running models fully on-device is an appealing alternative, as this can eliminate server costs, ensure a higher degree
Vocal characteristics contribute significantly to the construction and perception of individual identity. The loss of one’s voice, caused by physical or neurological conditions, can result in a profound sense of loss, striking at the very heart of one’s identity. Speakers with degenerative neural diseases, such as amyotrophic lateral sclerosis (ALS), Parkinson’s, and multiple sclerosis, may
Speculative RAG consists of two components: (1) a specialist RAG drafter, and (2) a generalist RAG verifier. First, the base model’s knowledge retriever retrieves related documents from the knowledge base. Then, Speculative RAG offloads computational burden to the specialist RAG drafter, a small LM specialized in answering questions using retrieved documents and not expected to
Users have more choices for listening to music than ever before. Popular services boast of massive and varied catalogs. The YouTube Music catalog, for example, has over 100M songs globally. It follows that item recommendations are a core part of these products. Recommender systems make sense of the item catalog and are critical for tuning
We use LLaVA-v1.5, a widely used open-sourced MLLM, as our base model and train it using our contrastive tuning framework (HALVA). We then evaluate its performance on object hallucination mitigation and general visual question answering tasks (VQA) against fine-tuning–based approaches, HA-DPO and EOS. We consider LLaVA-v1.5 as the lower bound and GPT-4V as a strong
