Search Results for author:
Found 11 papers, 4 papers with code
CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering
To address this, we explore the Cross-Lingual Self-Aligning ability of Language Models (CALM) to align knowledge across languages.
2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings
Our contributions include experimenting with three different dropout techniques, namely standard dropout, curriculum dropout, and adaptive dropout, to tackle overfitting, proposing a novel 2-Tier SimCSE Fine-tuning Model that combines both unsupervised and supervised SimCSE on STS task, and exploring transfer learning potential for Paraphrase and SST tasks.
DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models
With the rapid advancement of neural language models, the deployment of over-parameterized models has surged, increasing the need for interpretable explanations comprehensible to human inspectors.
Croc: Pretraining Large Multimodal Models with Cross-Modal Comprehension
Then, we conceptualize visual tokens as analogous to a "foreign language" for the LLMs and propose a mixed attention mechanism with bidirectional visual attention and unidirectional textual attention to comprehensively enhance the understanding of visual tokens.
QUIDS: Query Intent Generation via Dual Space Modeling
In this paper, we address the task of query intent generation: to automatically generate detailed and precise intent descriptions for search queries using relevant and irrelevant documents given a query.
LoMA: Lossless Compressed Memory Attention
We introduce Lossless Compressed Memory Attention (LoMA), a novel approach that enables lossless compression of the KV cache, thereby reducing the memory and computational demands during autoregressive generation.
DoNet: Deep De-overlapping Network for Cytology Instance Segmentation
Cell instance segmentation in cytology images has significant importance for biology analysis and cancer screening, while remains challenging due to 1) the extensive overlapping translucent cell clusters that cause the ambiguous boundaries, and 2) the confusion of mimics and debris as nuclei.
Explainable Information Retrieval: A Survey
Explainable information retrieval is an emerging research area aiming to make transparent and trustworthy information retrieval systems.
BERT Rankers are Brittle: a Study using Adversarial Document Perturbations
The aim of our algorithms is to add/replace a small number of tokens to a highly relevant or non-relevant document to cause a large rank demotion or promotion.
WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma
According to the technical reports of the top-tier teams, CAM is still the most popular approach in WSSS.
Data Augmentation
Weakly supervised Semantic Segmentation
+1
A Black-Scholes user's guide to the Bachelier model
To cope with the negative oil futures price caused by the COVID-19 recession, global commodity futures exchanges temporarily switched the option model from Black--Scholes to Bachelier in 2020.
