paper-with-me

Papers

RETSim: Resilient and Efficient Text Similarity

2023-11-28 · Marina Zhang, Owen Vallis, Aysegul Bumin, Tanay Vakharia, Elie Bursztein

This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication tasks. We demonstrate that RETSim is significantly more robust and accurate than MinHash and neural text embeddings, achieving new state-of-the-art performance on dataset deduplication, adversarial text retrieval benchmarks, and spam clustering tasks. We also introduce the W4NT3D benchmark (Wiki-40B 4dversarial Near-T3xt Dataset) for evaluating multilingual, near-duplicate text retrieval capabilities under adversarial settings. RETSim and the W4NT3D benchmark are open-sourced under the MIT License at https://github.com/google/unisim.

📄 PDF Abstract BibTeX arXiv:2311.17264

Code (3)

google/unisim 공식 구현 jax
unum-cloud/usearch 공식 구현
chenghaomou/text-dedup

Tasks

Adversarial TextClusteringRetrievalText Retrievaltext similarity

Similar Papers 제목 키워드 기반

Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective

2025-11-09 · Bing Wang, Ximing Li, Yanjun Wang, Changchun Li 외 arxiv

Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold…

Text-to-Image GenerationGraph Neural Network

ReLATE: Resilient Learner Selection for Multivariate Time-Series Classification Against Adversarial Attacks

2025-03-10 · Cagla Ipek Kocal, Onat Gungor, Aaron Tartz, Tajana Rosing 외

Minimizing computational overhead in time-series classification, particularly in deep learning models, presents a significant challenge. This challenge is further compounded by adversarial attacks, emphasizing the need f…

Adversarial AttackDeep LearningModel SelectionTime Series+1

Byzantine Resilient Distributed Multi-Task Learning

2020-10-25 · NeurIPS 2020 12 · Jiani Li, Waseem Abbas, Xenofon Koutsoukos

Distributed multi-task learning provides significant advantages in multi-agent networks with heterogeneous data sources where agents aim to learn distinct but correlated models simultaneously.However, distributed algorit…

Multi-Task Learning

Reasoning to Attend: Try to Understand How <SEG> Token Works

2024-12-23 · CVPR 2025 1 · Rui Qian, Xin Yin, Dejing Dou

Current Large Multimodal Models (LMMs) empowered visual grounding typically rely on $\texttt{<SEG>}$ token as a text prompt to jointly optimize the vision-language model (e.g., LLaVA) and the downstream task-specified mo…

Semantic SimilaritySemantic Textual SimilarityVisual Grounding

Resilience for Distributed Consensus with Constraints

2022-06-12 · Xuan Wang, Shaoshuai Mou, Shreyas Sundaram

This paper proposes a new approach that enables multi-agent systems to achieve resilient \textit{constrained} consensus in the presence of Byzantine attacks, in contrast to existing literature that is only applicable to …