语言大模型 / LLM

Inspecting the Representation Manifold of Differentially-Private Text

Stefan Arnold

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

Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance

Somnath Banerjee, Avik Halder, Rajarshi Mandal, Sayan Layek, Ian Soboroff, Rima Hazra, Animesh Mukherjee

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

Comments Accepted at NAACL 2025 (Industry track)

PASTA: Part-Aware Sketch-to-3D Shape Generation with Text-Aligned Prior

Seunggwan Lee, Hwanhee Jung, Byoungsoo Koh, Qixing Huang, Sangho Yoon, Sangpil Kim

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

Comments 19 pages, 18 figures

Treble Counterfactual VLMs: A Causal Approach to Hallucination

Shawn Li, Jiashu Qu, Yuxiao Zhou, Yuehan Qin, Tiankai Yang, Yue Zhao

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

LabelCoRank: Revolutionizing Long Tail Multi-Label Classification with Co-Occurrence Reranking

Yan Yan, Junyuan Liu, Bo-Wen Zhang

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

Revisiting the Othello World Model Hypothesis

Yifei Yuan, Anders Søgaard

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

Comments ICLR World Models Workshop

How can representation dimension dominate structurally pruned LLMs?

Mingxue Xu, Lisa Alazraki, Danilo P. Mandic

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

Comments ICLR 2025 Workshop on Sparsity in LLMs (SLLM)

BotUmc: An Uncertainty-Aware Twitter Bot Detection with Multi-view Causal Inference

Tao Yang, Yang Hu, Feihong Lu, Ziwei Zhang, Qingyun Sun, Jianxin Li

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

Comments 10 pages, 5 figures

On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning

Bokun Wang, Yunwen Lei, Yiming Ying, Tianbao Yang

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

Comments To appear in ICLR 2025

MindSimulator: Exploring Brain Concept Localization via Synthetic FMRI

Guangyin Bao, Qi Zhang, Zixuan Gong, Zhuojia Wu, Duoqian Miao

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

Comments 23 pages, ICLR 2025

UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation

Alexander H. Liu, Sang-gil Lee, Chao-Han Huck Yang, Yuan Gong, Yu-Chiang Frank Wang, James R. Glass, Rafael Valle, Bryan Catanzaro

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

Comments ICLR 2025; demo page at https://alexander-h-liu.github.io/uniwav-demo.github.io/

Sylber: Syllabic Embedding Representation of Speech from Raw Audio

Cheol Jun Cho, Nicholas Lee, Akshat Gupta, Dhruv Agarwal, Ethan Chen, Alan W Black, Gopala K. Anumanchipalli

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

Comments Accepted at ICLR 2025

Split Adaptation for Pre-trained Vision Transformers

Lixu Wang, Bingqi Shang, Yi Li, Payal Mohapatra, Wei Dong, Xiao Wang, Qi Zhu

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

Comments This paper has been accepted by CVPR 2025. The first two authors contributed equally

Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding

Wei Suo, Lijun Zhang, Mengyang Sun, Lin Yuanbo Wu, Peng Wang, Yanning Zhang

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

Mechanistic Permutability: Match Features Across Layers

Nikita Balagansky, Ian Maksimov, Daniil Gavrilov

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

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think

Liang Chen, Shuai Bai, Wenhao Chai, Weichu Xie, Haozhe Zhao, Leon Vinci, Junyang Lin, Baobao Chang

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

Comments 13 pages, 9 figures, codebase in https://github.com/chenllliang/DreamEngine

Decoding Reading Goals from Eye Movements

Omer Shubi, Cfir Avraham Hadar, Yevgeni Berzak

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

`Generalization is hallucination' through the lens of tensor completions

Liang Ze Wong

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

Beyond Pattern Recognition: Probing Mental Representations of LMs

Moritz Miller, Kumar Shridhar

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

Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue

Jiahui Xu, Feng Jiang, Anningzhe Gao, Luis Fernando D'Haro, Haizhou Li

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

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

Zhiyu Zhu, Zhibo Jin, Jiayu Zhang, Nan Yang, Jiahao Huang, Jianlong Zhou, Fang Chen

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

Comments Accepted by ICLR 2025

Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions

Ming Shan Hee, Roy Ka-Wei Lee

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

Comments Preprint. Accepted at ICWSM'25

Meta-INR: Efficient Encoding of Volumetric Data via Meta-Learning Implicit Neural Representation

Maizhe Yang, Kaiyuan Tang, Chaoli Wang

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

Comments Accepted by PVIS Short Paper Track

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

Lin Zhang, Lijie Hu, Di Wang

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

Comments Accepted by NAACL2025

Uncovering Intermediate Variables in Transformers using Circuit Probing

Michael A. Lepori, Thomas Serre, Ellie Pavlick

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

Linear Correlation in LM's Compositional Generalization and Hallucination

Letian Peng, Chenyang An, Shibo Hao, Chengyu Dong, Jingbo Shang

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

Unravelling Causal Genetic Biomarkers of Alzheimer's Disease via Neuron to Gene-token Backtracking in Neural Architecture: A Groundbreaking Reverse-Gene-Finder Approach

Victor OK Li, Yang Han, Jacqueline CK Lam

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

MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

Jingjing Hu, Dan Guo, Zhan Si, Deguang Liu, Yunfeng Diao, Jing Zhang, Jinxing Zhou, Meng Wang

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

Comments Accepted by AAAI2025

Control-oriented Clustering of Visual Latent Representation

Han Qi, Haocheng Yin, Heng Yang

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

Comments Website: https://computationalrobotics.seas.harvard.edu/ControlOriented_NC

SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model

Siavash Shams, Sukru Samet Dindar, Xilin Jiang, Nima Mesgarani

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

Comments Code at https://github.com/SiavashShams/ssamba

Journal ref 2024 IEEE Spoken Language Technology Workshop (SLT), Macao, pp. 1053-1059