A q-log odds variant of BM25 raises NDCG@10 by 89% relative on CodeSearchNet Go under fixed generic tokenization while recovering standard BM25 at q=1.
Torchdeq: A library for deep equilibrium models
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
Independent quantum signal injection into graph DEQs yields higher test accuracy and fewer solver iterations than state-dependent or backbone-dependent injection and classical equilibrium models on NCI1, PROTEINS, and MUTAG benchmarks.
A spatio-temporal GNN model reduces storm surge water-level forecast RMSE by more than 70% for 48-hour horizons and over 50% for 72-hour horizons on U.S. Gulf Coast hurricane data.
ReFinE is a Figma plugin that synthesizes contextualized design implications from HCI literature to provide actionable visual guidance for iterating on UI mockups.
Prepending a compact learnable prefix to LLMs produces safety gains comparable to next-generation aligned models while preserving fluency and adding negligible parameters.
Activation patching provides evidence about neural network circuits when the choice of metric is aligned with the hypothesis and common interpretation errors are avoided.
GEMS is an interactive system that lets domain experts steer evolutionary molecule design for sustainable chemicals by modifying scoring and populations in a visual interface.
citing papers explorer
-
Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix
A q-log odds variant of BM25 raises NDCG@10 by 89% relative on CodeSearchNet Go under fixed generic tokenization while recovering standard BM25 at q=1.
-
Quantum Injection Pathways for Implicit Graph Neural Networks
Independent quantum signal injection into graph DEQs yields higher test accuracy and fewer solver iterations than state-dependent or backbone-dependent injection and classical equilibrium models on NCI1, PROTEINS, and MUTAG benchmarks.
-
StormNet: Improving storm surge predictions with a GNN-based spatio-temporal offset forecasting model
A spatio-temporal GNN model reduces storm surge water-level forecast RMSE by more than 70% for 48-hour horizons and over 50% for 72-hour horizons on U.S. Gulf Coast hurricane data.
-
ReFinE: Streamlining UI Mockup Iteration with Research Findings
ReFinE is a Figma plugin that synthesizes contextualized design implications from HCI literature to provide actionable visual guidance for iterating on UI mockups.
-
Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models
Prepending a compact learnable prefix to LLMs produces safety gains comparable to next-generation aligned models while preserving fluency and adding negligible parameters.
-
How to use and interpret activation patching
Activation patching provides evidence about neural network circuits when the choice of metric is aligned with the hypothesis and common interpretation errors are avoided.
-
GEMS -- Guided Evolutionary Molecule Design for Sustainable Chemicals
GEMS is an interactive system that lets domain experts steer evolutionary molecule design for sustainable chemicals by modifying scoring and populations in a visual interface.
- Escaping Mode Collapse in LLM Generation via Geometric Regulation