语言大模型 / LLM

MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants

Hritik Bansal, Daniel Israel, Siyan Zhao, Shufan Li, Tung Nguyen, Aditya Grover

机构 * University of California Los Angeles（加州大学洛杉矶分校） 纠错

专题命中 指令微调 ：instruction tuning(title)；foundation model(abstract)；分类 cs.CL、cs.AI

Comments 29 pages

Bayesian Principles Improve Prompt Learning In Vision-Language Models

Mingyu Kim, Jongwoo Ko, Mijung Park

机构 * UBC CS（不列颠哥伦比亚大学计算机科学系） ； KAIST AI（韩国科学技术院人工智能学院） 纠错

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

Comments AISTATS2025

MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space

Yicheng Chen, Yining Li, Kai Hu, Zerun Ma, Haochen Ye, Kai Chen

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； Fudan University（复旦大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 指令微调 ：instruction tuning(title)；SFT(abstract)；分类 cs.CL、cs.AI

Post-pre-training for Modality Alignment in Vision-Language Foundation Models

Shin'ya Yamaguchi, Dewei Feng, Sekitoshi Kanai, Kazuki Adachi, Daiki Chijiwa

专题命中 指令微调 ：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments Accepted to CVPR 2025; Code: https://github.com/yshinya6/clip-refine

MatterTune: An Integrated, User-Friendly Platform for Fine-Tuning Atomistic Foundation Models to Accelerate Materials Simulation and Discovery

Lingyu Kong, Nima Shoghi, Guoxiang Hu, Pan Li, Victor Fung

专题命中 指令微调 ：foundation model(title,abstract)；分类 cs.AI、cs.LG

Language Models for Automated Classification of Brain MRI Reports and Growth Chart Generation

Maryam Daniali, Shivaram Karandikar, Dabriel Zimmerman, J. Eric Schmitt, Matthew J. Buczek, Benjamin Jung, Laura Mercedes, Jakob Seidlitz, Vanessa Troiani, Lena Dorfschmidt, Eren Kafadar, Remo Williams, Susan Sotardi, Arastoo Vossough, Scott Haag, Jenna M. Schabdach, Aaron Alexander-Bloch

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

HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modules

Neil He, Menglin Yang, Rex Ying

专题命中 指令微调 ：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments 11 pages, 4 figures

FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning

Xiaobing Yu, Jin Yang, Xiao Wu, Peijie Qiu, Xiaofeng Liu

专题命中 指令微调 ：prompting(title,abstract)；分类 cs.AI、cs.LG

Comments 8 Pages, 4 figures

FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations

Cheng-Yu Hsieh, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Chun-Liang Li, Ranjay Krishna, Oncel Tuzel, Hadi Pouransari

专题命中 指令微调 ：instruction tuning(title,abstract)；分类 cs.CL、cs.LG

Benchmarking Image Embeddings for E-Commerce: Evaluating Off-the Shelf Foundation Models, Fine-Tuning Strategies and Practical Trade-offs

Urszula Czerwinska, Cenk Bircanoglu, Jeremy Chamoux

专题命中 指令微调 ：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments accepted at Future Technologies Conference (FTC 2025)

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images

Kyle Stein, Andrew Arash Mahyari, Guillermo Francia, Eman El-Sheikh

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

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

Haochen Wang, Yucheng Zhao, Tiancai Wang, Haoqiang Fan, Xiangyu Zhang, Zhaoxiang Zhang

专题命中 指令微调 ：instruction tuning(title,abstract)；分类 cs.CL、cs.AI

F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics

Pramit Saha, Felix Wagner, Divyanshu Mishra, Can Peng, Anshul Thakur, David Clifton, Konstantinos Kamnitsas, J. Alison Noble

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

Comments Accepted in CVPR 2025

Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video

David Yifan Yao, Albert J. Zhai, Shenlong Wang

专题命中 指令微调 ：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments CVPR 2025. Project page (with code): https://davidyao99.github.io/uni4d

VenusFactory: A Unified Platform for Protein Engineering Data Retrieval and Language Model Fine-Tuning

Yang Tan, Chen Liu, Jingyuan Gao, Banghao Wu, Mingchen Li, Ruilin Wang, Lingrong Zhang, Huiqun Yu, Guisheng Fan, Liang Hong, Bingxin Zhou

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

Comments 12 pages, 1 figure, 8 tables

Gender Encoding Patterns in Pretrained Language Model Representations

Mahdi Zakizadeh, Mohammad Taher Pilehvar

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

Comments Proceedings of the 5th Workshop on Trustworthy Natural Language Processing (TrustNLP 2025)

Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models

Shicheng Xu, Liang Pang, Yunchang Zhu, Huawei Shen, Xueqi Cheng

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

Comments ICLR 2025

Cell-ontology guided transcriptome foundation model

Xinyu Yuan, Zhihao Zhan, Zuobai Zhang, Manqi Zhou, Jianan Zhao, Boyu Han, Yue Li, Jian Tang

专题命中 指令微调 ：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments Accepted to NeurIPS 2024 as Spotlight

Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images

Yubo Wang, Jianting Tang, Chaohu Liu, Linli Xu

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

Comments Accepted to ICLR 2025

Graph Adapter of EEG Foundation Models for Parameter Efficient Fine Tuning

Toyotaro Suzumura, Hiroki Kanezashi, Shotaro Akahori

专题命中 指令微调 ：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments Accepted AAAI W3PHIAI-25 Workshop

DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach

Qin Chen, Liang Wang, Bo Zheng, Guojie Song

专题命中 指令微调 ：prompting(title,abstract)；分类 cs.AI、cs.LG

Comments To be published in WWW '25, April 28-May 2, 2025, Sydney, NSW, Australia

SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs

Mohammad Mozaffari, Amir Yazdanbakhsh, Zhao Zhang, Maryam Mehri Dehnavi

专题命中 指令微调 ：pretraining(title,abstract)；分类 cs.AI、cs.LG

Comments Published at ICLR2025

Compositional Instruction Following with Language Models and Reinforcement Learning

Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew Gombolay, Ray Mooney, Benjamin Rosman

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

Comments TMLR 2024

ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models

Yassir Bendou, Amine Ouasfi, Vincent Gripon, Adnane Boukhayma

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

Comments Code available at https://ybendou.github.io/ProKeR

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model

Huan Ma, Yan Zhu, Changqing Zhang, Peilin Zhao, Baoyuan Wu, Long-Kai Huang, Qinghua Hu, Bingzhe Wu

专题命中 指令微调 ：foundation model(title,abstract)；分类 cs.AI、cs.LG

Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos

Mehmet Saygin Seyfioglu, Wisdom O. Ikezogwo, Fatemeh Ghezloo, Ranjay Krishna, Linda Shapiro

专题命中 指令微调 ：instruction tuning(title,abstract)；分类 cs.CL、cs.AI

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models

Peihai Jiang, Xixiang Lyu, Yige Li, Jing Ma

专题命中 指令微调 ：language model(title)；post-training(abstract)；分类 cs.CL、cs.AI

Comments AAAI 2025

Model Fusion through Bayesian Optimization in Language Model Fine-Tuning

Chaeyun Jang, Hyungi Lee, Jungtaek Kim, Juho Lee

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

FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning

Pramit Saha, Divyanshu Mishra, Felix Wagner, Konstantinos Kamnitsas, J. Alison Noble

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

Comments Accepted for publication in AAAI 2025 (Main Track)

Game Development as Human-LLM Interaction

Jiale Hong, Hongqiu Wu, Hai Zhao

专题命中 指令微调 ：LLM(title,abstract)；分类 cs.CL、cs.AI