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.
Theis, and Bo Wang
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
DECAT classifies multimodal representations into four diagnostic scenarios using null-referenced metrics and a rule-based procedure to detect shared biology versus confounders without knowing the confounder identity.
citing papers explorer
-
Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment
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.
-
When to Align, When to Predict: A Phase Diagram for Multimodal Learning
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
-
When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework
DECAT classifies multimodal representations into four diagnostic scenarios using null-referenced metrics and a rule-based procedure to detect shared biology versus confounders without knowing the confounder identity.