9 citations · 23 across the 18 of their papers we have counts for
19 papers
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents
Dongki Kim, Namkyeong Lee, Surag Nair +7
As agents rapidly evolve, existing benchmarks can become saturated, limiting their ability to distinguish capabilities and reveal remaining failure modes. Particularly in scientifi…
Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens
Carl Edwards, Edward De Brouwer, Xiner Li +5
Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation te…
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
Edward De Brouwer, Carl Edwards, Alexander Wu +9
Recent advances in machine learning and large-scale biological data collections have revived the prospect of building a virtual cell, a computational model of cellular behavior tha…
DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning
Chi-Min Chan, Ehsan Hajiramezanali, Xiner Li +6
In scientific reasoning tasks, the veracity of the reasoning process is as critical as the final outcome. While Process Reward Models (PRMs) offer a solution to the coarse-grained…
Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
Saleh Afroogh, Syed Ishtiaque Ahmed, Petra Ahrweiler +46
This study provides a cross-disciplinary examination of Explainable Artificial Intelligence (XAI) approaches-focusing on deep neural networks (DNNs) and large language models (LLMs…
Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design
Xingyu Su, Xiner Li, Masatoshi Uehara +7
We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex,…
RAG-Enhanced Collaborative LLM Agents for Drug Discovery
Namkyeong Lee, Edward De Brouwer, Ehsan Hajiramezanali +3
Recent advances in large language models (LLMs) have shown great potential to accelerate drug discovery. However, the specialized nature of biochemical data often necessitates cost…
MolCap-Arena: A Comprehensive Captioning Benchmark on Language-Enhanced Molecular Property Prediction
Carl Edwards, Ziqing Lu, Ehsan Hajiramezanali +3
Bridging biomolecular modeling with natural language information, particularly through large language models (LLMs), has recently emerged as a promising interdisciplinary research…
Cell Morphology-Guided Small Molecule Generation with GFlowNets
Stephen Zhewen Lu, Ziqing Lu, Ehsan Hajiramezanali +4
High-content phenotypic screening, including high-content imaging (HCI), has gained popularity in the last few years for its ability to characterize novel therapeutics without prio…
Adding Conditional Control to Diffusion Models with Reinforcement Learning
Yulai Zhao, Masatoshi Uehara, Gabriele Scalia +4
Diffusion models are powerful generative models that allow for precise control over the characteristics of the generated samples. While these diffusion models trained on large data…
Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
Masatoshi Uehara, Yulai Zhao, Ehsan Hajiramezanali +5
AI-driven design problems, such as DNA/protein sequence design, are commonly tackled from two angles: generative modeling, which efficiently captures the feasible design space (e.g…
Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control
Masatoshi Uehara, Yulai Zhao, Kevin Black +6
Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in th…
Feedback Efficient Online Fine-Tuning of Diffusion Models
Masatoshi Uehara, Yulai Zhao, Kevin Black +6
Diffusion models excel at modeling complex data distributions, including those of images, proteins, and small molecules. However, in many cases, our goal is to model parts of the d…
Toward the Identifiability of Comparative Deep Generative Models
Romain Lopez, Jan-Christian Huetter, Ehsan Hajiramezanali +2
Deep Generative Models (DGMs) are versatile tools for learning data representations while adequately incorporating domain knowledge such as the specification of conditional probabi…
Conformalized Deep Splines for Optimal and Efficient Prediction Sets
Nathaniel Diamant, Ehsan Hajiramezanali, Tommaso Biancalani +1
Uncertainty estimation is critical in high-stakes machine learning applications. One effective way to estimate uncertainty is conformal prediction, which can provide predictive inf…
Towards Understanding and Improving GFlowNet Training
Max W. Shen, Emmanuel Bengio, Ehsan Hajiramezanali +3
Generative flow networks (GFlowNets) are a family of algorithms that learn a generative policy to sample discrete objects with non-negative reward . Learning objectives g…
Conditional Diffusion with Less Explicit Guidance via Model Predictive Control
Max W. Shen, Ehsan Hajiramezanali, Gabriele Scalia +4
How much explicit guidance is necessary for conditional diffusion? We consider the problem of conditional sampling using an unconditional diffusion model and limited explicit guida…
Parameter Averaging for Feature Ranking
Talip Ucar, Ehsan Hajiramezanali
Neural Networks are known to be sensitive to initialisation. The methods that rely on neural networks for feature ranking are not robust since they can have variations in their ran…
SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning
Talip Ucar, Ehsan Hajiramezanali, Lindsay Edwards
Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and te…