37 citations · 64 across the 13 of their papers we have counts for
14 papers
Multimodal Co-Generation With Continuous Bitstream Diffusion
Georgios Batzolis, Georgios Kontos, Bruno Trentini +4
We show that continuous bitstream diffusion (CoBit), originally developed for language modeling, provides a unified framework for joint and conditional multimodal generation using…
Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction
Yifan Xue, Srimukh Prasad Veccham, Saee Paliwal +2
Accurate prediction of absorption, distribution, metabolism, and excretion (ADME) properties is critical to drug discovery, but remains challenging because ADME endpoints are noisy…
Contrastive Mutual Information Learning: Toward Robust Representations without Positive-Pair Augmentations
Micha Livne
Learning representations that transfer well to diverse downstream tasks remains a central challenge in representation learning. Existing paradigms -- contrastive learning, self-sup…
A Study on Regularization-Based Continual Learning Methods for Indic ASR
Gokul Adethya T, S. Jaya Nirmala
Indias linguistic diversity poses significant challenges for developing inclusive Automatic Speech Recognition (ASR) systems. Traditional multilingual models, which require simulta…
Contrastive MIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning
Micha Livne
Learning representations that generalize well to unknown downstream tasks is a central challenge in representation learning. Existing approaches such as contrastive learning, self-…
BioNeMo Framework: a modular, high-performance library for AI model development in drug discovery
Peter St. John, Dejun Lin, Polina Binder +89
Artificial Intelligence models encoding biology and chemistry are opening new routes to high-throughput and high-quality in-silico drug development. However, their training increas…
nach0: Multimodal Natural and Chemical Languages Foundation Model
Micha Livne, Zulfat Miftahutdinov, Elena Tutubalina +8
Large Language Models (LLMs) have substantially driven scientific progress in various domains, and many papers have demonstrated their ability to tackle complex problems with creat…
Improving Small Molecule Generation using Mutual Information Machine
Danny Reidenbach, Micha Livne, Rajesh K. Ilango +2
We address the task of controlled generation of small molecules, which entails finding novel molecules with desired properties under certain constraints (e.g., similarity to a refe…
SentenceMIM: A Latent Variable Language Model
Micha Livne, Kevin Swersky, David J. Fleet
SentenceMIM is a probabilistic auto-encoder for language data, trained with Mutual Information Machine (MIM) learning to provide a fixed length representation of variable length la…
High Mutual Information in Representation Learning with Symmetric Variational Inference
Micha Livne, Kevin Swersky, David J. Fleet
We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/d…
MIM: Mutual Information Machine
Micha Livne, Kevin Swersky, David J. Fleet
We introduce the Mutual Information Machine (MIM), a probabilistic auto-encoder for learning joint distributions over observations and latent variables. MIM reflects three design p…
TzK: Flow-Based Conditional Generative Model
Micha Livne, David Fleet
We formulate a new class of conditional generative models based on probability flows. Trained with maximum likelihood, it provides efficient inference and sampling from class-condi…
Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture
Micha Livne, Leonid Sigal, Marcus A. Brubaker +1
We propose a generative approach to physics-based motion capture. Unlike prior attempts to incorporate physics into tracking that assume the subject and scene geometry are calibrat…
TzK Flow - Conditional Generative Model
Micha Livne, David J. Fleet
We introduce TzK (pronounced "task"), a conditional probability flow-based model that exploits attributes (e.g., style, class membership, or other side information) in order to lea…