语言大模型 / LLM

Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing

Hongyu Shen, Junfeng Ni, Yixin Chen, Weishuo Li, Mingtao Pei, Siyuan Huang

机构 * Beijing Institute of Technology（北京理工大学） ； State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室） ； Tsinghua University（清华大学） 纠错

专题命中 知识编辑与模型理解 ：prompting(abstract)

Optimizing Vision-Language Consistency via Cross-Layer Regional Attention Alignment

Yifan Wang, Hongfeng Ai, Quangao Liu, Maowei Jiang, Ruiyuan Kang, Ruiqi Li, Jiahua Dong, Mengting Xiao, Cheng Jiang, Chenzhong Li

机构 * School of Medicine, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）医学院） ； Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所） ； Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） ； Wave and Machine Intelligence Department, Technology Innovation Institute（技术创新研究院波浪与机器智能部门） ； University of the Chinese Academy of Sciences（中国科学院大学） ； 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)

Comments 10 pages

$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models

Dahye Kim, Xavier Thomas, Deepti Ghadiyaram

机构 * Boston University（波士顿大学） ； Runway 纠错

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

Comments ICCV 2025

Details Matter for Indoor Open-vocabulary 3D Instance Segmentation

Sanghun Jung, Jingjing Zheng, Ke Zhang, Nan Qiao, Albert Y. C. Chen, Lu Xia, Chi Liu, Yuyin Sun, Xiao Zeng, Hsiang-Wei Huang, Byron Boots, Min Sun, Cheng-Hao Kuo

机构 * University of Washington（华盛顿大学） ； Amazon Lab126（亚马逊实验室126） ； National Tsing Hua University（国立清华大学） 纠错

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

Comments ICCV 2025

MatSSL: Robust Self-Supervised Representation Learning for Metallographic Image Segmentation

Hoang Hai Nam Nguyen, Phan Nguyen Duc Hieu, Ho Won Lee

机构 * Korea Institute of Materials Science（韩国材料科学研究院） ； University of Science and Technology（科学技术大学） 纠错

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection

Francesco Tonini, Lorenzo Vaquero, Alessandro Conti, Cigdem Beyan, Elisa Ricci

机构 * University of Trento（特伦托大学） ； University of Verona（威尼斯大学） ； 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 Accepted to ACM Multimedia 2025

Point'n Move: Interactive Scene Object Manipulation on Gaussian Splatting Radiance Fields

Jiajun Huang, Hongchuan Yu

机构 * Bournemouth University（伯恩茅斯大学） 纠错

专题命中 知识编辑与模型理解 ：prompting(abstract)

Comments Code: https://github.com/jhuangBU/pnm

Ultrafast ps--TALIF and streak camera diagnostics of atomic hydrogen in a helium microplasma jet

Dimitrios Stefas, Yanis Agha, Laurent Invernizzi, João Santos Sousa, Swaminathan Prasanna, Joachim Franzke, Charalambos Anastassiou, Guillaume Lombardi, Kristaq Gazeli

专题命中 知识编辑与模型理解 ：SLM(abstract)

SemAlignVC: Enhancing zero-shot timbre conversion using semantic alignment

Shivam Mehta, Yingru Liu, Zhenyu Tang, Kainan Peng, Vimal Manohar, Shun Zhang, Mike Seltzer, Qing He, Mingbo Ma

机构 * KTH Royal Institute of Technology（皇家理工学院） ； Meta 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)

Comments 6 pages, 2 figures, Accepted at the ISCA Speech Synthesis Workshop (SSW) 2025

Energy-Guided Decoding for Object Hallucination Mitigation

Xixi Liu, Ailin Deng, Christopher Zach

机构 * Chalmers University of Technology（查尔姆斯理工大学） ； National University of Singapore（新加坡国立大学） 纠错

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

Mix-Geneformer: Unified Representation Learning for Human and Mouse scRNA-seq Data

Yuki Nishio, Takayoshi Yamashita, Keita Ito, Tsubasa Hirakawa, Hironobu Fujiyoshi

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

Evolutionary and Coevolutionary Multi-Agent Design Choices and Dynamics

Erik Hemberg, Eric Liu, Lucille Fuller, Stephen Moskal, Una-May O'Reilly

专题命中 知识编辑与模型理解 ：LLM(abstract)

Comments 12 pages, 8 Figures

Gaussian Process-Based Active Exploration Strategies in Vision and Touch

Ho Jin Choi, Nadia Figueroa

机构 * Mechanical Engineering and Applied Mechanics（机械工程与应用力学） 纠错

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Comments Master's Thesis, Mechanical Engineering and Applied Mechanics, University of Pennsylvania - April 2024 (https://events.seas.upenn.edu/event/meam-masters-thesis-defense-gaussian-process-based-active-exploration-strategies-in-vision-and-touch/) (https://blog.me.upenn.edu/ho-jin-choi-successfully-defends-masters-thesis/)

A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields

Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua

机构 * Computer Vision Laboratory, EPFL, Switzerland（瑞士联邦理工学院计算机视觉实验室） 纠错

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

Comments ICCV 2025 accepted

OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction

Pablo Alonso-Jiménez, Pedro Ramoneda, R. Oguz Araz, Andrea Poltronieri, Dmitry Bogdanov

机构 * Music Technology Group, Universitat Pompeu Fabra（音乐技术组，庞培法布拉大学） 纠错

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

Assessing the Uncertainty and Robustness of the Laptop Refurbishing Software

Chengjie Lu, Jiahui Wu, Shaukat Ali, Mikkel Labori Olsen

机构 * Simula Research Laboratory and University of Oslo（Simula研究实验室和奥斯陆大学） ； Danish Technological Institute（丹麦技术研究所） 纠错

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

Comments 17 pages, 6 figures, 4 tables

Journal ref 2025 IEEE Conference on Software Testing, Verification and Validation (ICST)

HyperPath: Knowledge-Guided Hyperbolic Semantic Hierarchy Modeling for WSI Analysis

Peixiang Huang, Yanyan Huang, Weiqin Zhao, Junjun He, Lequan Yu

机构 * The University of Hong Kong（香港大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Shanghai Innovation Institute（上海创新研究院） 纠错

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

AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration

Javier Tirado-Garín, Javier Civera

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

Comments Accepted to ICCV 2025

HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs

Zijian Zhang, Xuecheng Wu, Danlei Huang, Siyu Yan, Chong Peng, Xuezhi Cao

机构 * Xi'an Jiaotong University（西安交通大学） ； East China Normal University（华东师范大学） 纠错

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

Bridging Data-Driven and Physics-Based Models: A Consensus Multi-Model Kalman Filter for Robust Vehicle State Estimation

Farid Mafi, Ladan Khoshnevisan, Mohammad Pirani, Amir Khajepour

机构 * Department of Mechanical and Mechatronics Engineering, University of Waterloo（滑铁卢大学机械与机电工程系） ； Department of Mechanical Engineering, University of Ottawa（渥太华大学机械工程系） 纠错

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Efficient Visual Representation Learning with Heat Conduction Equation

Zhemin Zhang, Xun Gong

机构 * School of Computing and Artificial Intelligence, Southwest Jiaotong University（计算与人工智能学院，西南交通大学） 纠错

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

Comments Accepted by IJCAI2025

PointGS: Point Attention-Aware Sparse View Synthesis with Gaussian Splatting

Lintao Xiang, Hongpei Zheng, Yating Huang, Qijun Yang, Hujun Yin

机构 * Department of Electrical and Electronic Engineering, The University of Manchester（曼彻斯特大学电子与电气工程系） 纠错

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

Improving Personalized Search with Regularized Low-Rank Parameter Updates

Fiona Ryan, Josef Sivic, Fabian Caba Heilbron, Judy Hoffman, James M. Rehg, Bryan Russell

机构 * Georgia Tech（佐治亚理工学院） ； Adobe Research（Adobe研究） ； CIIRC CTU（查理大学CIIRC） ； UIUC（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments CVPR 2025 Highlight. Code: http://github.com/adobe-research/polar-vl

Where Journalism Silenced Voices: Exploring Discrimination in the Representation of Indigenous Communities in Bangladesh

Abhijit Paul, Adity Khisa, Zarif Masud, Sharif Md. Abdullah, Ahmedul Kabir, Shebuti Rayana

专题命中 知识编辑与模型理解 ：LLM(abstract)

Diffusion Sequence Models for Enhanced Protein Representation and Generation

Logan Hallee, Nikolaos Rafailidis, David B. Bichara, Jason P. Gleghorn

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

Comments 20 pages, 15 figures

The symbolic partition with generalized Koopman analysis

Haipeng Li, Pengfei Guo, Yueheng Lan

专题命中 知识编辑与模型理解 ：prompting(abstract)

On the Importance of Text Preprocessing for Multimodal Representation Learning and Pathology Report Generation

Ruben T. Lucassen, Tijn van de Luijtgaarden, Sander P. J. Moonemans, Gerben E. Breimer, Willeke A. M. Blokx, Mitko Veta

机构 * Dept. of Pathology, University Medical Center Utrecht（病理学系，乌得勒支大学医学中心） ； Dept. of Biomedical Engineering, Eindhoven University of Technology（生物医学工程系，埃因霍温理工大学） ； Dept. of Mathematics and Computer Science, Eindhoven University of Technology（数学与计算机科学系，埃因霍温理工大学） 纠错

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

Comments 11 pages, 1 figure

Using ChatGPT-4 for the Identification of Common UX Factors within a Pool of Measurement Items from Established UX Questionnaires

Stefan Graser, Stephan Böhm, Martin Schrepp

专题命中 知识编辑与模型理解 ：LLM(abstract)

Comments 10 pages, 1 figure, The Sixteenth International Conference on Advances in Human-oriented and Personalized Mechanisms, Technologies, and Services CENTRIC 2023

Journal ref Proceedings of the Sixteenth International Conference on Advances in Human-oriented and Personalized Mechanisms, Technologies, and Services CENTRIC 2023, Valencia, pp 19 - 28, ISSN 2308-3492

Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation

Yongqi Wang, Chunlei Zhang, Hangting Chen, Zhou Zhao, Dong Yu

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

HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement

Amir Hussein, Sameer Khurana, Gordon Wichern, Francois G. Germain, Jonathan Le Roux

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