-
University of Maryland
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining
Official PyTorch implementation for "Large Language Diffusion Models"
CodonTransformer: The ultimate tool for codon optimization, optimizing DNA sequences for heterologous protein expression across 164 species.
[ICLR 2025] Stem: Gene Expression Inference from Histology Images
Codes for paper: Evaluating the Utilities of Large Language Models in Single-cell Data Analysis.
Aligning protein generative models with experimental fitness
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.
Concrete: TFHE Compiler that converts python programs into FHE equivalent
The repository for ACL 2024 paper "TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models"
TRAM: Benchmarking Temporal Reasoning for Large Language Models (Findings of ACL 2024)
Unbiased watermark with speculative sampling
add statistical significance annotations on seaborn plots. Further development of statannot, with bugfixes, new features, and a different API.
A generative latent variable model for biological sequence families.
Deep mutational scanning of the receptor-binding domain of SARS-CoV-2 Spike
Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"
CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation
Euclidean Wasserstein-2 optimal transportation