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.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
HazeMatching adapts conditional flow matching with hazy-image guidance to dehaze microscopy images while balancing fidelity and realism on synthetic and real data.
No correlation exists between CNNs' Brain-Score alignment with the visual system and the perceptual content of their Gram-matrix texture representations.
Memisis orchestrates synthetic tabular health data generation and evaluation using LLMs and multiple synthesizers, demonstrated on a schizophrenia dataset with fairness and utility checks.
citing papers explorer
-
Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings
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.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
-
HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching
HazeMatching adapts conditional flow matching with hazy-image guidance to dehaze microscopy images while balancing fidelity and realism on synthetic and real data.
-
Perceptual misalignment of texture representations in convolutional neural networks
No correlation exists between CNNs' Brain-Score alignment with the visual system and the perceptual content of their Gram-matrix texture representations.
-
Memisis: Orchestrating and Evaluating Synthetic Data for Tabular Health Datasets
Memisis orchestrates synthetic tabular health data generation and evaluation using LLMs and multiple synthesizers, demonstrated on a schizophrenia dataset with fairness and utility checks.