ArBG replaces flow-based methods with autoregressive models for Boltzmann sampling, showing gains on peptide benchmarks and a 132M-parameter model Robin cutting zero-shot energy error by over 60% on 8-residue systems.
hub
J., Bambrick, J., Bodenstein, S
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 11 cs.AI 2 q-bio.BM 2 q-bio.QM 2 astro-ph.IM 1 physics.app-ph 1 physics.chem-ph 1 physics.comp-ph 1 q-bio.PE 1roles
background 2polarities
background 2representative citing papers
LOGICA adds context to pretrained biological LMs via logit-space contrastive alignment with gated adapters, improving AUC on held-out drug-resistance mutation ranking from ~0.55 to ~0.65 while preserving token likelihoods.
AMPGAN v3 generates non-canonical AMPs with D-amino acids and modifications using two discriminators for stability, validated with two active candidates in vitro, alongside the PepCraft multi-agent discovery framework.
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
RosettaSearch applies LLM-driven multi-objective search at inference time to improve backbone-conditioned protein sequences, recovering designs with 18-68% better structural fidelity and 2.5x higher success rates than single-pass models like LigandMPNN.
Dual Triangle Attention achieves effective bidirectional attention with built-in positional inductive bias via dual triangular masks, outperforming standard bidirectional attention on position-sensitive tasks and showing strong masked language modeling results with or without positional embeddings.
A novel neural architecture based on Pairformer is introduced for learning committor functions to better capture dynamical features in biomolecular rare events without specialized priors.
Sesame introduces spatial density-map conditioning and a pairformer module in a diffusion framework to enable de novo and scaffold-conditioned molecular generation for drug design.
LLMs can forecast GPU kernel performance accurately enough to serve as selective surrogates, allowing kernel searches to consider more candidates and recover faster kernels under fixed GPU evaluation budgets.
Presents Hack-Verifiable TextArena, a benchmark that embeds verifiable reward hacking opportunities into environments to enable deterministic measurement of exploitation by language models.
CrystalBoltz performs experiment-guided posterior sampling with diffusion models on structure-factor amplitudes for protein structure determination, reporting lower RMSD and R-factors than baselines with 33x faster runtime.
A two-layer certification framework decouples knowledge validity from human authorship to accommodate AI-enabled research in existing publication systems.
ADIOS applies opponent shaping in a meta-learning setup to create antibodies that target current and future viral variants while biasing evolution toward weaker strains, demonstrated in Absolut! simulations.
Emyx, a compact flow matching model with EDM reparametrization, outperforms larger protein generators on enzyme design benchmarks with substantially lower training compute.
DeltaDiff is a physics-guided inference method that predicts mutant protein structures from a baseline diffusion model without retraining, tested on three systems with nonlocal changes.
Explicit E(3)-equivariance in neural CFD surrogates improves generalization on diverse-geometry hemodynamics benchmarks but degrades in-distribution performance on strongly aligned aerodynamics data, consistently beating data augmentation.
Boltz-2 and fine-tuned DrugFormDTA lead ML-based binding prediction while GNINA leads docking tools on a cleaned antiviral dataset, with performance varying by viral protein.
An integrated framework with ConGA-PepPI for PepPI prediction and binding-site localization plus TC-PepGen for target-conditioned peptide generation reports 0.839 accuracy and 0.921 AUROC in cross-validation along with 40.39% of generated peptides exceeding native templates on AlphaFold 3 ipTM.
AIMBio-Mat is a conceptual blueprint for an AI-native, FAIR, governance-aware decision layer that formulates biomedical-materials discovery as constrained multi-objective optimization under uncertainty.
A putative homotrimeric structure of BP180 is predicted with Boltz-2 and shown to remain mostly folded over 500 ns MD trajectories, with a stiff NC16A domain and flexible Col-15.
Agentic AI platforms autonomously train 87%-accurate PPI prediction models on protein-disjoint data and induce aligning human-readable rules for human-human and virus-human interactions.
Machine learning enables better data integration across scales, increased sensitivity to complex features, and adaptive sampling strategies for astrobiological searches, viewed through Viking missions and AI developments.
citing papers explorer
-
ADIOS: Antibody Development via Opponent Shaping
ADIOS applies opponent shaping in a meta-learning setup to create antibodies that target current and future viral variants while biasing evolution toward weaker strains, demonstrated in Absolut! simulations.