语言大模型 / LLM

The Power of Small LLMs in Geometry Generation for Physical Simulations

Ossama Shafiq, Bahman Ghiassi, Alessio Alexiadis

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)

Comments 24 pages, 17 figures

Language-specific Neurons Do Not Facilitate Cross-Lingual Transfer

Soumen Kumar Mondal, Sayambhu Sen, Abhishek Singhania, Preethi Jyothi

机构 * Indian Institute of Technology Bombay（印度理工学院孟买分校） ； Amazon Alexa（亚马逊Alexa部门） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted (oral) at NAACL 2025 (InsightsNLP)

DroidTTP: Mapping Android Applications with TTP for Cyber Threat Intelligence

Dincy R Arikkat, Vinod P., Rafidha Rehiman K. A., Serena Nicolazzo, Marco Arazzi, Antonino Nocera, Mauro Conti

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)

TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On

Zhenchen Wan, Yanwu Xu, Zhaoqing Wang, Feng Liu, Tongliang Liu, Mingming Gong

机构 * University of Melbourne（墨尔本大学） ； The University of Sydney（悉尼大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)

Comments Project page: https://github.com/ZhenchenWan/TED-VITON

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks

Samuele Poppi, Zheng-Xin Yong, Yifei He, Bobbie Chern, Han Zhao, Aobo Yang, Jianfeng Chi

机构 * Meta ； University of Pisa（比萨大学） ； University of Modena and Reggio Emilia（摩德纳与雷焦艾米利亚大学） ； Brown University（布朗大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 15 pages, 6 figures, 7 tables

M4SC: An MLLM-based Multi-modal, Multi-task and Multi-user Semantic Communication System

Feibo Jiang, Siwei Tu, Li Dong, Kezhi Wang, Kun Yang, Cunhua Pan

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)

Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code

Jiho Shin, Clark Tang, Tahmineh Mohati, Maleknaz Nayebi, Song Wang, Hadi Hemmati

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 11 pages + reference. Accepted in 22nd International Conference on Mining Software Repositories, 2025. Technical Papers Track (MSR'25)

LIMR: Less is More for RL Scaling

Xuefeng Li, Haoyang Zou, Pengfei Liu

机构 * SJTU（上海交通大学） ； SII（上海交通大学智能研究院） ； GAIR（人工智能研究院） 纠错

专题命中 指令微调 ：language model(abstract)；SFT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 6pages

Tamper-Resistant Safeguards for Open-Weight LLMs

Rishub Tamirisa, Bhrugu Bharathi, Long Phan, Andy Zhou, Alice Gatti, Tarun Suresh, Maxwell Lin, Justin Wang, Rowan Wang, Ron Arel, Andy Zou, Dawn Song, Bo Li, Dan Hendrycks, Mantas Mazeika

机构 * Lapis Labs（拉皮斯实验室） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Center for AI Safety（AI安全中心） ； University of California, San Diego（加利福尼亚大学圣迭戈分校） ； Gray Swan AI（格雷天鹅人工智能公司） ； Carnegie Mellon University（卡内基梅隆大学） ； Harvard University（哈佛大学） ； University of California, Berkeley（加利福尼亚大学伯克利分校） ； University of Chicago（芝加哥大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Website: https://www.tamper-resistant-safeguards.com

A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL

Yingqi Gao, Yifu Liu, Xiaoxia Li, Xiaorong Shi, Yin Zhu, Yiming Wang, Shiqi Li, Wei Li, Yuntao Hong, Zhiling Luo, Jinyang Gao, Liyu Mou, Yu Li

机构 * Alibaba Group（阿里巴巴集团） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

House of Cards: Massive Weights in LLMs

Jaehoon Oh, Seungjun Shin, Dokwan Oh

机构 * Samsung Advanced Institute of Technology（三星先进技术研究院） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Under review

Ensembles of Low-Rank Expert Adapters

Yinghao Li, Vianne Gao, Chao Zhang, MohamadAli Torkamani

机构 * Amazon Web Service（亚马逊网络服务） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 29 pages, 5 figures, 5 tables; proceedings in ICLR 2025

Addressing Popularity Bias in Third-Party Library Recommendations Using LLMs

Claudio Di Sipio, Juri Di Rocco, Davide Di Ruscio, Vladyslav Bulhakov

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；foundation model(abstract)

Comments Accepted at the 1st International Workshop on Fairness in Software Systems, co-located with SANER2025

Omni-Emotion: Extending Video MLLM with Detailed Face and Audio Modeling for Multimodal Emotion Analysis

Qize Yang, Detao Bai, Yi-Xing Peng, Xihan Wei

机构 * Tongyi Lab, Alibaba Group（阿里巴巴集团通义实验室） ； Sun Yat-sen University（中山大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；instruction tuning(abstract)

SpaLLM-Guard: Pairing SMS Spam Detection Using Open-source and Commercial LLMs

Muhammad Salman, Muhammad Ikram, Nardine Basta, Mohamed Ali Kaafar

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 17 pages

Towards Interactive Deepfake Analysis

Lixiong Qin, Ning Jiang, Yang Zhang, Yuhan Qiu, Dingheng Zeng, Jiani Hu, Weihong Deng

机构 * Mashang Consumer Finance Co., Ltd（马上消费金融股份有限公司） ； Beijing University of Posts and Telecommunications（北京邮电大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；instruction tuning(abstract)

SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Information

Kaiye Zhou, Shucheng Wang, Jun Xu

机构 * China Mobile (Suzhou) Software Technology Co. Ltd.（中国移动（苏州）软件技术有限公司） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments SwitchLoRA introduces an innovative parameter-efficient training method that dynamically switches parameters throughout the entire training period, achieving significant memory and communication overhead while preserving accuracy

RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions

Wanlong Liu, Junying Chen, Ke Ji, Li Zhou, Wenyu Chen, Benyou Wang

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； University of Electronic Science and Technology of China（电子科技大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection

Xutao Liao, Shaohui Li, Yuhui Xu, Zhi Li, Yu Liu, You He

机构 * Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院） ； Salesforce AI Research（Salesforce AI研究院） ； Tsinghua University（清华大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

FaGeL: Fabric LLMs Agent empowered Embodied Intelligence Evolution with Autonomous Human-Machine Collaboration

Jia Liu, Min Chen

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)

MMFactory: A Universal Solution Search Engine for Vision-Language Tasks

Wan-Cyuan Fan, Tanzila Rahman, Leonid Sigal

机构 * University of British Columbia（不列颠哥伦比亚大学） ； Vector Institute for AI（向量人工智能研究院） 纠错

专题命中 指令微调 ：LLM(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Frontier AI systems have surpassed the self-replicating red line

Xudong Pan, Jiarun Dai, Yihe Fan, Min Yang

机构 * School of Computer Science, Fudan University（复旦大学计算机科学学院） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 47 pages, 10 figures

Compositional Image Retrieval via Instruction-Aware Contrastive Learning

Wenliang Zhong, Weizhi An, Feng Jiang, Hehuan Ma, Yuzhi Guo, Junzhou Huang

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)

Comments 9 pages, 8 figures

Mimir: Improving Video Diffusion Models for Precise Text Understanding

Shuai Tan, Biao Gong, Yutong Feng, Kecheng Zheng, Dandan Zheng, Shuwei Shi, Yujun Shen, Jingdong Chen, Ming Yang

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Cosmos-LLaVA: Chatting with the Visual Cosmos-LLaVA: Görselle Sohbet Etmek

Ahmed Zeer, Eren Dogan, Yusuf Erdem, Elif Ince, Osama Shbib, M. Egemen Uzun, Atahan Uz, M. Kaan Yuce, H. Toprak Kesgin, M. Fatih Amasyali

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments in Turkish language, 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP)

Variational Low-Rank Adaptation Using IVON

Bai Cong, Nico Daheim, Yuesong Shen, Daniel Cremers, Rio Yokota, Mohammad Emtiyaz Khan, Thomas Möllenhoff

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published at 38th Workshop on Fine-Tuning in Machine Learning (NeurIPS 2024). Code available at https://github.com/team-approx-bayes/ivon-lora. In version 2 we fixed a typo in the equation of prior in section 2

Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding

Jaeyoo Park, Jin Young Choi, Jeonghyung Park, Bohyung Han

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments NeurIPS 2024

MoVA: Adapting Mixture of Vision Experts to Multimodal Context

Zhuofan Zong, Bingqi Ma, Dazhong Shen, Guanglu Song, Hao Shao, Dongzhi Jiang, Hongsheng Li, Yu Liu

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)

Comments NeurIPS 2024

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

Adib Hasan, Ileana Rugina, Alex Wang

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP

PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures

Tianxiang Wu, Minxin Nie, Ziqiang Cao

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)