CHR improves medical question answering retrieval by explicitly promoting evidence aligned with a correct hypothesis while penalizing content aligned with a plausible incorrect alternative.
hub
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
An efficient enumeration algorithm is developed from sufficient conditions on subgraphs in the bipartite König representation to identify autocatalytic subnetworks and minimal cores in full metabolic networks.
Pluot enables a single Rust visualization rendering function to execute reproducibly across languages and output formats via generated bindings.
A new tree-conditioned edit-flow model for ancestral sequence reconstruction achieves reasonable accuracy on substitution-only evolved sequences and superior localization of changes on natural indel-rich sequences.
EncFormer reduces online MPC communication by 1.4x-30.4x and end-to-end latency by 1.3x-9.8x versus prior hybrid FHE-MPC systems for private GPT- and BERT-style inference while preserving accuracy.
RAG-GNN augments GNNs with retrieved literature knowledge via gated fusion to improve functional clustering of 379 proteins in cancer signaling networks, raising silhouette score by 0.093.
PepMorph generates morphology-targeted peptides via a Transformer conditional VAE and reports 83% success under CG-MD validation.
Presents an optimal transport framework for simulating particle systems with arbitrary cell shapes and volumes that automatically handles exclusion constraints.
scHelix uses explicit gene-level partitioning into Anchors and Variants plus an asymmetric Align-Refine-Fuse dual-stream architecture to improve batch correction in scRNA-seq without over-correcting biological signals.
Hyformer jointly models molecule generation and property prediction via alternating attention and joint pre-training, showing synergistic gains in conditional sampling, OOD prediction, and a drug design case for antimicrobial peptides.
Large-scale neutral benchmark of survival models on low-dimensional right-censored data finds Cox PH performs comparably to more complex methods across discrimination, calibration, and predictive metrics.
MathQA retrieves Wikidata formulas for natural language questions in English or Hindi, enables SymPy-based computation with user inputs and Wikidata constants, and outperformed a commercial engine by 13% in a user study while aiding formula imports with an 80% accurate heuristic.
Fine-tuned LLaMA3 with LoRA reaches 81.24% F1 on 18-category fine-grained medical entity recognition, beating zero-shot by 63.11% and few-shot by 35.63%.
citing papers explorer
-
Ruling Out to Rule In: Contrastive Hypothesis Retrieval for Medical Question Answering
CHR improves medical question answering retrieval by explicitly promoting evidence aligned with a correct hypothesis while penalizing content aligned with a plausible incorrect alternative.
-
Enumeration of Autocatalytic Subsystems in Large Chemical Reaction Networks
An efficient enumeration algorithm is developed from sufficient conditions on subgraphs in the bipartite König representation to identify autocatalytic subnetworks and minimal cores in full metabolic networks.
-
Pluot: Towards 'write once, run everywhere' visualization software
Pluot enables a single Rust visualization rendering function to execute reproducibly across languages and output formats via generated bindings.
-
Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction
A new tree-conditioned edit-flow model for ancestral sequence reconstruction achieves reasonable accuracy on substitution-only evolved sequences and superior localization of changes on natural indel-rich sequences.
-
EncFormer: Secure and Efficient Transformer Inference over Encrypted Data
EncFormer reduces online MPC communication by 1.4x-30.4x and end-to-end latency by 1.3x-9.8x versus prior hybrid FHE-MPC systems for private GPT- and BERT-style inference while preserving accuracy.
-
RAG-GNN: Integrating Retrieved Knowledge with Graph Neural Networks for Precision Medicine
RAG-GNN augments GNNs with retrieved literature knowledge via gated fusion to improve functional clustering of 379 proteins in cancer signaling networks, raising silhouette score by 0.093.
-
Morphology-Aware Peptide Discovery via Masked Conditional Generative Modeling
PepMorph generates morphology-targeted peptides via a Transformer conditional VAE and reports 83% success under CG-MD validation.
-
Multicellular simulations with shape and volume constraints using optimal transport
Presents an optimal transport framework for simulating particle systems with arbitrary cell shapes and volumes that automatically handles exclusion constraints.
-
scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement
scHelix uses explicit gene-level partitioning into Anchors and Variants plus an asymmetric Align-Refine-Fuse dual-stream architecture to improve batch correction in scRNA-seq without over-correcting biological signals.
-
Synergistic Benefits of Joint Molecule Generation and Property Prediction
Hyformer jointly models molecule generation and property prediction via alternating attention and joint pre-training, showing synergistic gains in conditional sampling, OOD prediction, and a drug design case for antimicrobial peptides.
-
A Large-Scale Neutral Comparison Study of Survival Models on Low-Dimensional Data
Large-scale neutral benchmark of survival models on low-dimensional right-censored data finds Cox PH performs comparably to more complex methods across discrimination, calibration, and predictive metrics.
-
Introducing MathQA -- A Math-Aware Question Answering System
MathQA retrieves Wikidata formulas for natural language questions in English or Hindi, enables SymPy-based computation with user inputs and Wikidata constants, and outperformed a commercial engine by 13% in a user study while aiding formula imports with an 80% accurate heuristic.
-
Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition
Fine-tuned LLaMA3 with LoRA reaches 81.24% F1 on 18-category fine-grained medical entity recognition, beating zero-shot by 63.11% and few-shot by 35.63%.