Articles for category: AI Research

March 5, 2025

ikayaniaamirshahzad@gmail.com

Deep mutational learning for the selection of therapeutic antibodies resistant to the evolution of Omicron variants of SARS-CoV-2

Design and construction of a high-distance Omicron BA.1 RBD library A mutagenesis library was constructed based on BA.1, covering the entire 201 amino acid RBD region (positions 331–531 of SARS-CoV-2 S protein). To maximize the interrogated RBD sequence space, the library design was entirely synthetic and unbiased, as it did not consider evolutionary data or previous experimental findings. For the construction of the library, the RBD sequence was split into 11–12 fragments, each with an approximate length of 48 nucleotides (Supplementary Table 1). For a fragment of average length, 137 different single-stranded oligonucleotides (ssODN) were designed, where each ssODN had

March 5, 2025

ikayaniaamirshahzad@gmail.com

Third-party evaluation to identify risks in LLMs’ training data

TLDR – EleutherAI and OpenMined conducted a demonstration project to show how third-party evaluators can query a non-public AI training dataset. This approach provides third-party evaluators with a new method for conducting AI safety evaluations without accessing the model or sensitive data. The Problem# With the rapid advancement of frontier artificial intelligence (AI) models, establishing effective third-party oversight and evaluation is crucial to ensure their responsible development and maintain public trust. However, many third-party oversight methods primarily rely on black-box access, in which evaluators can only query the system and observe its outputs. This degree of access severely restricts the

March 5, 2025

ikayaniaamirshahzad@gmail.com

Stanford CRFM

In collaboration with SCBX and SCB 10X, we introduce the ThaiExam leaderboard. ThaiExam is a Thai language benchmark derived from standardized examinations in Thailand. It consists of assessments that evaluate general knowledge at the high school level, such as the ONET, TGAT, TPAT-1, and A-Level exams, as well as the IC exam, which assesses financial knowledge among investment professionals. The ThaiExam leaderboard is the first public leaderboard for language models on Thai language scenarios, and features evaluations of leading language models. Like all other HELM leaderboards, the ThaiExam leaderboard provides full prompt-level transparency, and the results can be fully reproduced

March 5, 2025

ikayaniaamirshahzad@gmail.com

Updating the Frontier Safety Framework

Our next iteration of the FSF sets out stronger security protocols on the path to AGI AI is a powerful tool that is helping to unlock new breakthroughs and make significant progress on some of the biggest challenges of our time, from climate change to drug discovery. But as its development progresses, advanced capabilities may present new risks. That’s why we introduced the first iteration of our Frontier Safety Framework last year – a set of protocols to help us stay ahead of possible severe risks from powerful frontier AI models. Since then, we’ve collaborated with experts in industry, academia,

March 5, 2025

ikayaniaamirshahzad@gmail.com

[2212.03683] Neighborhood Adaptive Estimators for Causal Inference under Network Interference

[Submitted on 7 Dec 2022 (v1), last revised 4 Mar 2025 (this version, v2)] View a PDF of the paper titled Neighborhood Adaptive Estimators for Causal Inference under Network Interference, by Alexandre Belloni and 1 other authors View PDF HTML (experimental) Abstract:Estimating causal effects has become an integral part of most applied fields. In this work we consider the violation of the classical no-interference assumption with units connected by a network. For tractability, we consider a known network that describes how interference may spread. Unlike previous work the radius (and intensity) of the interference experienced by a unit is unknown

March 5, 2025

ikayaniaamirshahzad@gmail.com

A Light-weight and Dimension-independent Vision Mamba for 3D Medical Image Analysis

This paper has been withdrawn by Wei Dai [Submitted on 19 Feb 2025 (v1), last revised 1 Mar 2025 (this version, v2)] View a PDF of the paper titled MobileViM: A Light-weight and Dimension-independent Vision Mamba for 3D Medical Image Analysis, by Wei Dai and 2 other authors No PDF available, click to view other formats Abstract:Efficient evaluation of three-dimensional (3D) medical images is crucial for diagnostic and therapeutic practices in healthcare. Recent years have seen a substantial uptake in applying deep learning and computer vision to analyse and interpret medical images. Traditional approaches, such as convolutional neural networks (CNNs)

March 5, 2025

ikayaniaamirshahzad@gmail.com

[2410.09230] Improving Semantic Understanding in Speech Language Models via Brain-tuning

[Submitted on 11 Oct 2024 (v1), last revised 4 Mar 2025 (this version, v3)] View a PDF of the paper titled Improving Semantic Understanding in Speech Language Models via Brain-tuning, by Omer Moussa and 2 other authors View PDF HTML (experimental) Abstract:Speech language models align with human brain responses to natural language to an impressive degree. However, current models rely heavily on low-level speech features, indicating they lack brain-relevant semantics which limits their utility as model organisms of semantic processing in the brain. In this work, we address this limitation by inducing brain-relevant bias directly into the models via fine-tuning

March 5, 2025

ikayaniaamirshahzad@gmail.com

[2412.01786] Gradient-Free Generation for Hard-Constrained Systems

[Submitted on 2 Dec 2024 (v1), last revised 3 Mar 2025 (this version, v2)] View a PDF of the paper titled Gradient-Free Generation for Hard-Constrained Systems, by Chaoran Cheng and 6 other authors View PDF HTML (experimental) Abstract:Generative models that satisfy hard constraints are critical in many scientific and engineering applications, where physical laws or system requirements must be strictly respected. Many existing constrained generative models, especially those developed for computer vision, rely heavily on gradient information, which is often sparse or computationally expensive in some fields, e.g., partial differential equations (PDEs). In this work, we introduce a novel framework

March 5, 2025

ikayaniaamirshahzad@gmail.com

Pixel Studio features to try, including human image generation

General summary Pixel Studio is a text-to-image AI generator that lets you visualize your ideas. You can use it to redecorate your home, create stickers, design invitations, and even document your dreams. The app is easy to use and integrates with Google Photos, making it easy to share your creations. Summaries were generated by Google AI. Generative AI is experimental. Bullet points Pixel Studio is a text-to-image AI generator that lets you visualize your ideas. Use Pixel Studio to redecorate your home, create mockups, and rearrange furniture. Turn any image into a sticker to use in your messages, emails, and