语言大模型 / LLM

Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning

Nathaniel Krasner, Nicholas Lanuzo, Antonios Anastasopoulos

机构 * Department of Computer Science, George Mason University（计算机科学系，乔治·马歇尔大学） 纠错

专题命中 知识编辑与模型理解 ：pretraining(abstract)；分类 cs.CL

Comments Accepted to ACL 2025 Main Conference

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing

Jiakuan Xie, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所认知与决策智能复杂系统实验室） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL

Comments Accepted by ACL 2025 main

Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables

Yu Gui, Cong Ma, Zongming Ma

机构 * Department of Statistics, University of Chicago（芝加哥大学统计系） ； Department of Statistics and Data Science, Yale University（耶鲁大学统计学与数据科学系） 纠错

专题命中 知识编辑与模型理解 ：foundation model(abstract)；分类 cs.LG

CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs

David Méndez, Gianpaolo Bontempo, Elisa Ficarra, Roberto Confalonieri, Natalia Díaz-Rodríguez

机构 * Dept. of Computer Science and Artificial Intelligence, DaSCI Institute, University of Granada（计算机科学与人工智能系，DaSCI研究所，格拉纳达大学） ； Dept. of Engineering ”Enzo Ferrari”, University of Modena and Reggio Emilia（工程系，摩德纳和雷吉奥艾米利亚大学） ； Dept. of Mathematics ’Tullio Levi-Civita’, University of Padova（数学系，帕多瓦大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.AI

Comments 8 pages, 3 figures, 5 tables. Accepted at IJCNN 2025; to appear in IEEE Xplore

Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation

David Minkwan Kim, Soeun Lee, Byeongkeun Kang

专题命中 知识编辑与模型理解 ：foundation model(abstract)；分类 cs.AI

Comments 8 pages

Journal ref Pattern Recognition Letters, 2025

EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot Manipulation

Zibin Dong, Fei Ni, Yifu Yuan, Yinchuan Li, Jianye Hao

机构 * Tianjin University（天津大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

专题命中 知识编辑与模型理解 ：foundation model(abstract)；分类 cs.AI

What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation

Michal Golovanevsky, William Rudman, Vedant Palit, Ritambhara Singh, Carsten Eickhoff

机构 * Department of Computer Science, Brown University（布朗大学计算机科学系） ； Indian Institute of Technology Kharagpur（印度理工学院Khargpur分校） ； Center for Computational Molecular Biology, Brown University（布朗大学计算分子生物学中心） ； School of Medicine, University of Tübingen（图宾根大学医学院） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL

AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL

Yunsheng Bai, Ghaith Bany Hamad, Syed Suhaib, Haoxing Ren

机构 * NVIDIA（英伟达） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；分类 cs.AI

Comments LAD 2025

Jointly spatial-temporal representation learning for individual trajectories

Fei Huang, Jianrong Lv, Yang Yue

专题命中 知识编辑与模型理解 ：foundation model(abstract)；分类 cs.LG

Comments 27 pages, 3 tables, 7 figures

Journal ref Computers, Environment and Urban Systems, 112(2024)

AI-powered virtual eye: perspective, challenges and opportunities

Yue Wu, Yibo Guo, Yulong Yan, Jiancheng Yang, Xin Zhou, Ching-Yu Cheng, Danli Shi, Mingguang He

专题命中 知识编辑与模型理解 ：foundation model(abstract)；分类 cs.AI

Comments 30 Pages, 3 figures, 1 table

Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text

Jinpeng Li, Yu Pu, Qi Sun, Wei-Qiang Zhang

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL

Comments Accepted by INTERSPEECH 2024;Minor typo correction

Journal ref INTERSPEECH (2024) 2514-2518

Fill the Gap: Quantifying and Reducing the Modality Gap in Image-Text Representation Learning

François Role, Sébastien Meyer, Victor Amblard

机构 * Université Paris-Cité（巴黎-cite大学） ； Pôle d’Expertise de la Régulation Numérique (PEReN)（数字监管专家中心） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.LG

Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment

Jin Chen, Kaijing Ma, Haojian Huang, Han Fang, Hao Sun, Mehdi Hosseinzadeh, Zhe Liu

机构 * School of Computer Science, Duy Tan University（计算机科学学院，杜益坦大学） ； School of Computer Sciences, Universiti Sains Malaysia（计算机科学学院，马来亚大学） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；分类 cs.AI

Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling

Yu-hsuan Chen, Jing Bi, Cyril Ngo Ngoc, Victor Oancea, Jonathan Cagan, Levent Burak Kara

专题命中 知识编辑与模型理解 ：foundation model(abstract)；分类 cs.LG

Self-Ablating Transformers: More Interpretability, Less Sparsity

Jeremias Ferrao, Luhan Mikaelson, Keenan Pepper, Natalia Perez-Campanero Antolin

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.LG

Comments Poster Presentation at Building Trust Workshop at ICLR 2025

CSE-SFP: Enabling Unsupervised Sentence Representation Learning via a Single Forward Pass

Bowen Zhang, Zixin Song, Chunping Li

机构 * Tsinghua University（清华大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL

Comments Accepted by SIGIR 2025 (Full)

Graphemic Normalization of the Perso-Arabic Script

Raiomond Doctor, Alexander Gutkin, Cibu Johny, Brian Roark, Richard Sproat

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL

Comments Pre-print to appear in the Proceedings of Grapholinguistics in the 21st Century (G21C), 2022. Telecom Paris, Palaiseau, France, June 8-10, 2022. 41 pages, 38 tables, 3 figures

You Are What You Bought: Generating Customer Personas for E-commerce Applications

Yimin Shi, Yang Fei, Shiqi Zhang, Haixun Wang, Xiaokui Xiao

机构 * National University of Singapore（新加坡国立大学） ； PyroWis AI ； EvenUp 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；分类 cs.AI

Comments SIGIR 2025

Physiological neural representation for personalised tracer kinetic parameter estimation from dynamic PET

Kartikay Tehlan, Thomas Wendler

机构 * Department of diagnostic and interventional Radiology and Neuroradiology, University Hospital Augsburg（诊断与介入放射学及神经放射学系，奥格斯堡大学医院） ； Computer-Aided Medical Procedures and Augmented Reality, Technical University of Munich（医学辅助程序与增强现实，慕尼黑技术大学） ； Digital Medicine, University Hospital Augsburg（数字医学，奥格斯堡大学医院） ； Center of Advanced Analytics and Predictive Sciences, University of Augsburg（高级分析与预测科学中心，奥格斯堡大学） 纠错

专题命中 知识编辑与模型理解 ：foundation model(abstract)；分类 cs.AI

Comments The code is available at: https://github.com/tkartikay/PhysNRPET

Decoding Vision Transformers: the Diffusion Steering Lens

Ryota Takatsuki, Sonia Joseph, Ippei Fujisawa, Ryota Kanai

机构 * Araya Inc.（Araya公司） ； AI Alignment Network（AI对齐网络） ； The University of Tokyo（东京大学） ； Mila - Quebec AI Institute（魁北克AI研究所） ； McGill University（麦吉尔大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.AI

Comments 12 pages, 17 figures. Accepted to the CVPR 2025 Workshop on Mechanistic Interpretability for Vision (MIV)

Real-World Depth Recovery via Structure Uncertainty Modeling and Inaccurate GT Depth Fitting

Delong Suzhang, Meng Yang

专题命中 知识编辑与模型理解 ：foundation model(abstract)；分类 cs.AI

Probing Visual Language Priors in VLMs

Tiange Luo, Ang Cao, Gunhee Lee, Justin Johnson, Honglak Lee

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.LG

Comments Project Page: https://vilp-team.github.io/

Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond

Frank Yingjie Huo, Neil F. Johnson

专题命中 知识编辑与模型理解 ：LLM(abstract)；分类 cs.AI

Comments Comments welcome to neiljohnson@gwu.edu

Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing

Mayank Kothyari, Sunita Sarawagi, Soumen Chakrabarti, Gaurav Arora, Srujana Merugu

专题命中 知识编辑与模型理解 ：LLM(abstract)；分类 cs.CL

Comments To appear at NAACL 2025 (Main)

Automated Feature Labeling with Token-Space Gradient Descent

Julian Schulz, Seamus Fallows

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.LG

Comments 10 pages, 4 figures, Building Trust Workshop ICLR 2025

Self-Evolving Visual Concept Library using Vision-Language Critics

Atharva Sehgal, Patrick Yuan, Ziniu Hu, Yisong Yue, Jennifer J. Sun, Swarat Chaudhuri

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.LG

Comments CVPR camera ready

FTS: A Framework to Find a Faithful TimeSieve

Songning Lai, Ninghui Feng, Haochen Sui, Ze Ma, Hao Wang, Zichen Song, Hang Zhao, Yutao Yue

专题命中 知识编辑与模型理解 ：prompting(abstract)；分类 cs.LG

Journal ref IJCAI2024 workshop

A Geometric Notion of Causal Probing

Clément Guerner, Tianyu Liu, Anej Svete, Alexander Warstadt, Ryan Cotterell

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL

TARDIS: Mitigating Temporal Misalignment via Representation Steering

Changho Shin, Xinya Yan, Suenggwan Jo, Sungjun Cho, Shourjo Aditya Chaudhuri, Frederic Sala

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.LG

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

Xiang Xu, Lingdong Kong, Hui Shuai, Liang Pan, Ziwei Liu, Qingshan Liu

专题命中 知识编辑与模型理解 ：pretraining(abstract)；分类 cs.LG

Comments CVPR 2025; 27 pages, 17 figures, 10 tables; Project Page at https://ldkong.com/LiMoE