语言大模型 / LLM

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

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

MALT: Mechanistic Ablation of Lossy Translation in LLMs for a Low-Resource Language: Urdu

Taaha Saleem Bajwa

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

No Foundations without Foundations -- Why semi-mechanistic models are essential for regulatory biology

Luka Kovačević, Thomas Gaudelet, James Opzoomer, Hagen Triendl, John Whittaker, Caroline Uhler, Lindsay Edwards, Jake P. Taylor-King

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

Comments 19 pages, 8 figures

Boosting Weak Positives for Text Based Person Search

Akshay Modi, Ashhar Aziz, Nilanjana Chatterjee, A V Subramanyam

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

Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters

Parth Padalkar, Jaeseong Lee, Shiyi Wei, Gopal Gupta

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

Scaling Structure Aware Virtual Screening to Billions of Molecules with SPRINT

Andrew T. McNutt, Abhinav K. Adduri, Caleb N. Ellington, Monica T. Dayao, Eric P. Xing, Hosein Mohimani, David R. Koes

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

Graph-level Representation Learning with Joint-Embedding Predictive Architectures

Geri Skenderi, Hang Li, Jiliang Tang, Marco Cristani

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

Comments Accepted in Transactions of Machine Learning Research (TMLR)

Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM

Xin Hu, Janet Wang, Jihun Hamm, Rie R Yotsu, Zhengming Ding

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

Comments This paper is accepted by WACV 2025

BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptation

Pablo Morales-Álvarez, Stergios Christodoulidis, Maria Vakalopoulou, Pablo Piantanida, Jose Dolz

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

Comments 30 pages, 5 figures, 23 tables

Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning

Lanqing Li, Hai Zhang, Xinyu Zhang, Shatong Zhu, Yang Yu, Junqiao Zhao, Pheng-Ann Heng

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

Comments 26 pages, 8 figures, 7 tables. TLDR: We propose a novel information theoretic framework of the context-based offline meta-RL paradigm, which unifies several mainstream methods and leads to two robust algorithm implementations

Journal ref 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Label-free Concept Based Multiple Instance Learning for Gigapixel Histopathology

Susu Sun, Leslie Tessier, Frédérique Meeuwsen, Clément Grisi, Dominique van Midden, Geert Litjens, Christian F. Baumgartner

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

U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario

Jiaxin Song, Xinyu Wang, Yihao Wang, Yifan Tang, Ru Zhang, Jianyi Liu, Gongshen Liu

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

Comments 16 pages, 6 figures and 10 tables. Comments are welcome

SSL Framework for Causal Inconsistency between Structures and Representations

Hang Chen, Xinyu Yang, Keqing Du, Wenya Wang

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

Comments 29 pages

Extract Free Dense Misalignment from CLIP

JeongYeon Nam, Jinbae Im, Wonjae Kim, Taeho Kil

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

Comments 16 pages, 14 figures, AAAI 2025

Reversed Attention: On The Gradient Descent Of Attention Layers In GPT

Shahar Katz, Lior Wolf

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

Representation Learning of Daily Movement Data Using Text Encoders

Alexander Capstick, Tianyu Cui, Yu Chen, Payam Barnaghi

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

Comments Accepted at ICLR 2024 Workshop on Learning from Time Series For Health: https://openreview.net/forum?id=mmxNNwxvWG

Journal ref International Conference on Learning Representations 2024 Workshop on Learning from Time Series For Health

Variability Need Not Imply Error: The Case of Adequate but Semantically Distinct Responses

Evgenia Ilia, Wilker Aziz

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

Comments 26 pages

Provably Secure Disambiguating Neural Linguistic Steganography

Yuang Qi, Kejiang Chen, Kai Zeng, Weiming Zhang, Nenghai Yu

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

Comments 12 pages. Accepted by IEEE Transactions on Dependable and Secure Computing (TDSC)

Dynamic Entity-Masked Graph Diffusion Model for histopathological image Representation Learning

Zhenfeng Zhuang, Min Cen, Yanfeng Li, Fangyu Zhou, Lequan Yu, Baptiste Magnier, Liansheng Wang

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

A Grounded Typology of Word Classes

Coleman Haley, Sharon Goldwater, Edoardo Ponti

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

Comments 19 pages, 5 figures

CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection

Qibo Chen, Weizhong Jin, Jianyue Ge, Mengdi Liu, Yuchao Yan, Jian Jiang, Li Yu, Xuanjiang Guo, Shuchang Li, Jianzhong Chen

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

Comments Accepted by AAAI2025

Take Package as Language: Anomaly Detection Using Transformer

Jie Huang

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

A surprisal oracle for when every layer counts

Xudong Hong, Sharid Loáiciga, Asad Sayeed

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

Multi-Scale Representation Learning for Protein Fitness Prediction

Zuobai Zhang, Pascal Notin, Yining Huang, Aurélie Lozano, Vijil Chenthamarakshan, Debora Marks, Payel Das, Jian Tang

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

Learning Spatially-Aware Language and Audio Embeddings

Bhavika Devnani, Skyler Seto, Zakaria Aldeneh, Alessandro Toso, Elena Menyaylenko, Barry-John Theobald, Jonathan Sheaffer, Miguel Sarabia

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

Comments 26 pages, 7 figures, accepted at NeurIPS 2024

Morphosyntactic probing of multilingual BERT models

Judit Acs, Endre Hamerlik, Roy Schwartz, Noah A. Smith, Andras Kornai

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

Comments to appear in the Journal of Natural Language Engineering

Journal ref Nat. Lang. Eng. 30 (2024) 753-792

Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representation

Juan-Ni Wu, Tong Wang, Li-Juan Tang, Hai-Long Wu, Ru-Qin Yu

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

Comments 26pages, 6 figures

Understanding The Effect Of Temperature On Alignment With Human Opinions

Maja Pavlovic, Massimo Poesio

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

STARS: Sensor-agnostic Transformer Architecture for Remote Sensing

Ethan King, Jaime Rodriguez, Diego Llanes, Timothy Doster, Tegan Emerson, James Koch

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

The American Sign Language Knowledge Graph: Infusing ASL Models with Linguistic Knowledge

Lee Kezar, Nidhi Munikote, Zian Zeng, Zed Sehyr, Naomi Caselli, Jesse Thomason

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