语言大模型 / LLM

Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulation

Hang Li, Qian Feng, Zhi Zheng, Jianxiang Feng, Zhaopeng Chen, Alois Knoll

机构 * Technical University of Munich（慕尼黑工业大学） ； Agile Robots SE（敏捷机器人公司） 纠错

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments ICRA 2025

LLMs are Bug Replicators: An Empirical Study on LLMs' Capability in Completing Bug-prone Code

Liwei Guo, Sixiang Ye, Zeyu Sun, Xiang Chen, Yuxia Zhang, Bo Wang, Jie M. Zhang, Zheng Li, Yong Liu

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

GRADE: Quantifying Sample Diversity in Text-to-Image Models

Royi Rassin, Aviv Slobodkin, Shauli Ravfogel, Yanai Elazar, Yoav Goldberg

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments For project page and code see https://royira.github.io/GRADE

A General Purpose Spectral Foundational Model for Both Proximal and Remote Sensing Spectral Imaging

William Michael Laprade, Jesper Cairo Westergaard, Svend Christensen, Mads Nielsen, Anders Bjorholm Dahl

机构 * Technical University of Denmark（丹麦技术大学） ； University of Copenhagen（哥本哈根大学） 纠错

专题命中 预训练与数据 ：foundation model(abstract)；pretraining(abstract)

STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning

Palaash Agrawal, Haidi Azaman, Cheston Tan

机构 * Center for Frontier AI Research（前沿人工智能研究中心） ； Agency for Science, Technology, and Research（科学、技术与研究局） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 预训练与数据 ：language model(abstract)；pretraining(abstract)

(Mis)Fitting: A Survey of Scaling Laws

Margaret Li, Sneha Kudugunta, Luke Zettlemoyer

专题命中 预训练与数据 ：foundation model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 41 pages, 3 figure, first two authors contributed equally. ICLR, 2025

Scaling Optimal LR Across Token Horizons

Johan Bjorck, Alon Benhaim, Vishrav Chaudhary, Furu Wei, Xia Song

机构 * Microsoft（微软） ； Nvidia（英伟达） ； Meta 纠错

专题命中 预训练与数据 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at ICLR 2025

CODE-ACCORD: A Corpus of building regulatory data for rule generation towards automatic compliance checking

Hansi Hettiarachchi, Amna Dridi, Mohamed Medhat Gaber, Pouyan Parsafard, Nicoleta Bocaneala, Katja Breitenfelder, Gonçal Costa, Maria Hedblom, Mihaela Juganaru-Mathieu, Thamer Mecharnia, Sumee Park, He Tan, Abdel-Rahman H. Tawil, Edlira Vakaj

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments This is a preprint of an article published in the Scientific Data Journal

cosmosage: A Natural-Language Assistant for Cosmologists

Tijmen de Haan

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Journal ref Astronomy and Computing, Volume 51, 2025, 100934, ISSN 2213-1337

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?

Rylan Schaeffer, Hailey Schoelkopf, Brando Miranda, Gabriel Mukobi, Varun Madan, Adam Ibrahim, Herbie Bradley, Stella Biderman, Sanmi Koyejo

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Language Bias in Self-Supervised Learning For Automatic Speech Recognition

Edward Storey, Naomi Harte, Peter Bell

机构 * Trinity College Dublin（都柏林圣三一学院） ； The University of Edinburgh（爱丁堡大学） 纠错

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to Speech and Language Technology Workshop (SLT) 2024 accessible on IEEE Xplore

ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension

Tianren Ma, Lingxi Xie, Yunjie Tian, Boyu Yang, Qixiang Ye

机构 * CMRI 纠错

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments ICLR 2025. Code is available at github.com/martian422/ClawMachine

A Domain Adaptation Framework for Speech Recognition Systems with Only Synthetic data

Minh Tran, Yutong Pang, Debjyoti Paul, Laxmi Pandey, Kevin Jiang, Jinxi Guo, Ke Li, Shun Zhang, Xuedong Zhang, Xin Lei

机构 * University of Southern California（南加州大学） ； Meta AI 纠错

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments ICASSP 2025

Towards Standards-Compliant Assistive Technology Product Specifications via LLMs

Chetan Arora, John Grundy, Louise Puli, Natasha Layton

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion

Sho Inoue, Shuai Wang, Wanxing Wang, Pengcheng Zhu, Mengxiao Bi, Haizhou Li

机构 * Fuxi AI Lab, NetEase Inc.（网易伏羲人工智能实验室） ； Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电气与计算机工程系） 纠错

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments This is accepted to IEEE ICASSP 2025; Project page with Speech Demo: https://github.com/shinshoji01/MacST-project-page

TED: Turn Emphasis with Dialogue Feature Attention for Emotion Recognition in Conversation

Junya Ono, Hiromi Wakaki

机构 * Sony Group Corporation（索尼集团公司） 纠错

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments past activity in 2021

Revisiting MLLMs: An In-Depth Analysis of Image Classification Abilities

Huan Liu, Lingyu Xiao, Jiangjiang Liu, Xiaofan Li, Ze Feng, Sen Yang, Jingdong Wang

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning

Brandon Huang, Chancharik Mitra, Assaf Arbelle, Leonid Karlinsky, Trevor Darrell, Roei Herzig

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published in NeurIPS 2024

ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation

Shiqi Huang, Shuting He, Bihan Wen

专题命中 预训练与数据 ：language model(abstract)；pretraining(abstract)

Comments AAAI 2025, code see https://github.com/HuangShiqi128/ZoRI

Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining

Hansa Meghwani

专题命中 预训练与数据 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Master's thesis

Understanding Token Probability Encoding in Output Embeddings

Hakaze Cho, Yoshihiro Sakai, Kenshiro Tanaka, Mariko Kato, Naoya Inoue

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 15 pages, 17 figures, 3 tables. COLING 2025 Accepted

DiffCLIP: Few-shot Language-driven Multimodal Classifier

Jiaqing Zhang, Mingxiang Cao, Xue Yang, Kai Jiang, Yunsong Li

专题命中 预训练与数据 ：language model(abstract)；pretraining(abstract)

TLDR: Text Based Last-layer Retraining for Debiasing Image Classifiers

Juhyeon Park, Seokhyeon Jeong, Taesup Moon

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments WACV 2025

AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks

You Li, Fan Ma, Yi Yang

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication

Huao Li, Hossein Nourkhiz Mahjoub, Behdad Chalaki, Vaishnav Tadiparthi, Kwonjoon Lee, Ehsan Moradi-Pari, Charles Michael Lewis, Katia P Sycara

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments Accepted to Neurips 2024, 19 pages, 10 figures

DynamicAvatars: Accurate Dynamic Facial Avatars Reconstruction and Precise Editing with Diffusion Models

Yangyang Qian, Yuan Sun, Yu Guo

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models

Wei Wang, Zhaowei Li, Qi Xu, Linfeng Li, YiQing Cai, Botian Jiang, Hang Song, Xingcan Hu, Pengyu Wang, Li Xiao

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Self-learning Monte Carlo with equivariant Transformer

Yuki Nagai, Akio Tomiya

专题命中 预训练与数据 ：large language model(abstract)；language model(abstract)

Comments 10 pates, 6 figures, Full paper version

Journal ref J. Phys. Soc. Jpn. 93, 114007 (2024

DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models

Zijian Zhang, Vinay Setty, Yumeng Wang, Avishek Anand

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

AM Flow: Adapters for Temporal Processing in Action Recognition

Tanay Agrawal, Abid Ali, Antitza Dantcheva, Francois Bremond

专题命中 预训练与数据 ：foundation model(abstract)；pretraining(abstract)