语言大模型 / LLM

Probing the Robustness Properties of Neural Speech Codecs

Wei-Cheng Tseng, David Harwath

机构 * Department of Computer Science（计算机科学系） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)

Comments Interspeech 2025

Advancing high-fidelity 3D and Texture Generation with 2.5D latents

Xin Yang, Jiantao Lin, Yingjie Xu, Haodong Li, Yingcong Chen

机构 * HKUST(GZ)（香港科技大学（广州）） 纠错

专题命中 知识编辑与模型理解 ：foundation model(abstract)

Multimodal Fusion with Relational Learning for Molecular Property Prediction

Zhengyang Zhou, Yunrui Li, Pengyu Hong, Hao Xu

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Locality-Aware Zero-Shot Human-Object Interaction Detection

Sanghyun Kim, Deunsol Jung, Minsu Cho

机构 * Pohang University of Science and Technology (POSTECH)（釜山科学技术大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)

Comments Accepted to CVPR2025; Code is available at: https://github.com/OreoChocolate/LAIN

Clapper: Compact Learning and Video Representation in VLMs

Lingyu Kong, Hongzhi Zhang, Jingyuan Zhang, Jianzhao Huang, Kunze Li, Qi Wang, Fuzheng Zhang

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Kuaishou Technology（快手科技） ； Xi’an Jiaotong University（西安交通大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)

Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment

Yang Hu, Runchen Wang, Stephen Chong Zhao, Xuhui Zhan, Do Hun Kim, Mark Wallace, David A. Tovar

机构 * Data Science Institute（数据科学研究所） ； Vanderbilt University（范德比大学） ； Department of Computer Science（计算机科学系） ； Department of Psychology（心理学系） 纠错

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Comments 10 pages, 5 figures, 2 tables

Utilizing Provenance as an Attribute for Visual Data Analysis: A Design Probe with ProvenanceLens

Arpit Narechania, Shunan Guo, Eunyee Koh, Alex Endert, Jane Hoffswell

专题命中 知识编辑与模型理解 ：prompting(abstract)

Comments 14 pages, 6 figures, 1 table, accepted in IEEE TVCG 2025

ir_explain: a Python Library of Explainable IR Methods

Sourav Saha, Harsh Agarwal, V Venktesh, Avishek Anand, Swastik Mohanty, Debapriyo Majumdar, Mandar Mitra

专题命中 知识编辑与模型理解 ：language model(abstract)

Comments To appear as a Resources and Reproducibility Track paper in Proc. ACM SIGIR 2025

Gene finding revisited: improved robustness through structured decoding from learned embeddings

Frederikke I. Marin, Dennis Pultz, Wouter Boomsma

专题命中 知识编辑与模型理解 ：language model(abstract)

Comments 8 pages, 3 figures, 2 tables

Interpretable Zero-shot Learning with Infinite Class Concepts

Zihan Ye, Shreyank N Gowda, Shiming Chen, Yaochu Jin, Kaizhu Huang, Xiaobo Jin

机构 * Xian Jiaotong-Liverpool University（西安交通大学利物浦大学） ； University of Nottingham（诺丁汉大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； Westlake University（西湖大学） ； Duke Kunshan University（杜克-昆山大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)

Superallowed $0^+ \rightarrow 0^+$ $β$ decay studies at GANIL and upcoming opportunities with DESIR and S$^3$-LEB

B. M. Rebeiro, J. -C. Thomas, B. Blank

专题命中 知识编辑与模型理解 ：prompting(abstract)

Comments 16 pages, 5 figures

DiffusionInv: Prior-enhanced Bayesian Full Waveform Inversion using Diffusion models

Yuanyuan Li, Hao Zhang, Zhuoqi Yan, Tariq Alkhalifah

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Comments 19 pages, 16 figures

Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysis

Alexei Kaltchenko

机构 * Wilfrid Laurier University（威尔弗里德·劳里埃大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)

Comments 22 pages

EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observations and Wikipedia

Valerie Zermatten, Javiera Castillo-Navarro, Pallavi Jain, Devis Tuia, Diego Marcos

机构 * EPFL（瑞士联邦理工学院） ； CNAM（法国国家科学与技术研究中心） ； INRIA（法国国家信息与自动化研究所） ； CIHEAM-IAMM（CIHEAM- IAMM） ； Univ. of Montpellier（蒙彼利埃大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)

Comments Accepted at EarthVision 2025 (CVPRW 2025)

Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation

Shahad Albastaki, Anabia Sohail, Iyyakutti Iyappan Ganapathi, Basit Alawode, Asim Khan, Sajid Javed, Naoufel Werghi, Mohammed Bennamoun, Arif Mahmood

机构 * Department of Computer Science（计算机科学系） ； ARIC ； Khalifa University of Science and Technology（科技大学） ； Information Technology University of the Punjab（旁遮普信息科技大学） ； University of the Western Australia（西澳大学） 纠错

专题命中 知识编辑与模型理解 ：language model(abstract)

CLIC: Contrastive Learning Framework for Unsupervised Image Complexity Representation

Shipeng Liu, Liang Zhao, Dengfeng Chen

机构 * XAUAT（西安理工大学） 纠错

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Comments under review

Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance

Xuchan Bao, Judith Yue Li, Zhong Yi Wan, Kun Su, Timo Denk, Joonseok Lee, Dima Kuzmin, Fei Sha

机构 * University of Toronto（多伦多大学） ； Google Research（谷歌研究） ； Google DeepMind（谷歌DeepMind） ； Seoul National University（首尔国立大学） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)

Comments NeurIPS 2024 Creative AI Track

Journal ref Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025

TrustMap: Mapping Truthfulness Stance of Social Media Posts on Factual Claims for Geographical Analysis

Zhengyuan Zhu, Haiqi Zhang, Zeyu Zhang, Chengkai Li

专题命中 知识编辑与模型理解 ：language model(abstract)

First-Order Intuitionistic Linear Logic and Hypergraph Languages

Tikhon Pshenitsyn

专题命中 知识编辑与模型理解 ：language model(abstract)

Comments Accepted for presentation at ICALP 2025

CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning

Yang Yue, Yulin Wang, Chenxin Tao, Pan Liu, Shiji Song, Gao Huang

机构 * Tsinghua University（清华大学） ； PLA General Hospital（中国人民解放军总医院） 纠错

专题命中 知识编辑与模型理解 ：foundation model(abstract)

Comments Accepted by CVPR 2025

ACE: Attentional Concept Erasure in Diffusion Models

Finn Carter

专题命中 知识编辑与模型理解 ：prompting(abstract)

Comments Under Review

Towards Robust Trajectory Embedding for Similarity Computation: When Triangle Inequality Violations in Distance Metrics Matter

Jianing Si, Haitao Yuan, Nan Jiang, Minxiao Chen, Xiao Ma, Shangguang Wang

专题命中 知识编辑与模型理解 ：prompting(abstract)

Comments 14 pages, 8 figures

Multimodal Representation Learning Techniques for Comprehensive Facial State Analysis

Kaiwen Zheng, Xuri Ge, Junchen Fu, Jun Peng, Joemon M. Jose

专题命中 知识编辑与模型理解 ：foundation model(abstract)

Comments Accepted by ICME2025

Journal ref ICME2025

ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis

Yun Chang, Leonor Fermoselle, Duy Ta, Bernadette Bucher, Luca Carlone, Jiuguang Wang

专题命中 知识编辑与模型理解 ：LLM(abstract)

VADIS: A Visual Analytics Pipeline for Dynamic Document Representation and Information-Seeking

Rui Qiu, Yamei Tu, Po-Yin Yen, Han-Wei Shen

专题命中 知识编辑与模型理解 ：language model(abstract)

Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation

Tianshui Chen, Jianman Lin, Zhijing Yang, Chumei Qing, Yukai Shi, Liang Lin

专题命中 知识编辑与模型理解 ：language model(abstract)

REVEAL: Relation-based Video Representation Learning for Video-Question-Answering

Sofian Chaybouti, Walid Bousselham, Moritz Wolter, Hilde Kuehne

专题命中 知识编辑与模型理解 ：language model(abstract)

Comments 18 pages, 7 figures

Activation Patching for Interpretable Steering in Music Generation

Simone Facchiano, Giorgio Strano, Donato Crisostomi, Irene Tallini, Tommaso Mencattini, Fabio Galasso, Emanuele Rodolà

专题命中 知识编辑与模型理解 ：language model(abstract)

Preference-Driven Active 3D Scene Representation for Robotic Inspection in Nuclear Decommissioning

Zhen Meng, Kan Chen, Xiangmin Xu, Erwin Jose Lopez Pulgarin, Emma Li, Philip G. Zhao, David Flynn

专题命中 知识编辑与模型理解 ：RLHF(abstract)

Comments This work has been submitted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025

Scaling Language-Free Visual Representation Learning

David Fan, Shengbang Tong, Jiachen Zhu, Koustuv Sinha, Zhuang Liu, Xinlei Chen, Michael Rabbat, Nicolas Ballas, Yann LeCun, Amir Bar, Saining Xie

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Comments Project page at https://davidfan.io/webssl/