语言大模型 / LLM

An empirical study of LLaMA3 quantization: from LLMs to MLLMs

Wei Huang, Xingyu Zheng, Xudong Ma, Haotong Qin, Chengtao Lv, Hong Chen, Jie Luo, Xiaojuan Qi, Xianglong Liu, Michele Magno

机构 * The University of Hong Kong（香港大学） ； Beihang University（北京航空航天大学） ； ETH Zurich（苏黎世联邦理工学院） 纠错

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；post-training(abstract)

FASTNav: Fine-tuned Adaptive Small-language-models Trained for Multi-point Robot Navigation

Yuxuan Chen, Yixin Han, Xiao Li

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；small language model(abstract)

Journal ref in IEEE Robotics and Automation Letters, vol. 10, no. 1, pp. 390-397, Jan. 2025

SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations

Zhaorun Chen, Francesco Pinto, Minzhou Pan, Bo Li

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 43 pages, 20 figures

Generative AI on the Edge: Architecture and Performance Evaluation

Zeinab Nezami, Maryam Hafeez, Karim Djemame, Syed Ali Raza Zaidi

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Tianyu Guo, Druv Pai, Yu Bai, Jiantao Jiao, Michael I. Jordan, Song Mei

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；pretraining(abstract)

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control

Huayu Chen, Kaiwen Zheng, Hang Su, Jun Zhu

专题命中 效率与部署 ：LLM(abstract)；language model(abstract)；pretraining(abstract)；preference optimization(abstract)

Comments Accepted by NeurIPS 2024

Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach

Qingchuan Li, Jiatong Li, Tongxuan Liu, Yuting Zeng, Mingyue Cheng, Weizhe Huang, Qi Liu

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection

Jielin Song, Siyu Liu, Bin Zhu, Yanghui Rao

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning

Qingqing Cao, Mahyar Najibi, Sachin Mehta

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；foundation model(abstract)；pretraining(abstract)

Intent Detection in the Age of LLMs

Gaurav Arora, Shreya Jain, Srujana Merugu

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted at EMNLP 2024 Industry Track

Efficient Hybrid Inference for LLMs: Reward-Based Token Modelling with Selective Cloud Assistance

Adarsh MS, Jithin VG, Ditto PS

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；SLM(abstract)

LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning

Mingyang Zhang, Hao Chen, Chunhua Shen, Zhen Yang, Linlin Ou, Xinyi Yu, Bohan Zhuang

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；post-training(abstract)

Comments accepted by acl 2024 findings

Graph-Structured Speculative Decoding

Zhuocheng Gong, Jiahao Liu, Ziyue Wang, Pengfei Wu, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；small language model(abstract)

BatchPrompt: Accomplish more with less

Jianzhe Lin, Maurice Diesendruck, Liang Du, Robin Abraham

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 20 pages, 5 figures

mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs

Gregor Geigle, Abhay Jain, Radu Timofte, Goran Glavaš

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；pretraining(abstract)

Comments ALVR Workshop 2024

Expert-Guided Extinction of Toxic Tokens for Debiased Generation

Xueyao Sun, Kaize Shi, Haoran Tang, Guandong Xu, Qing Li

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation

Chen Wang, Minpeng Liao, Zhongqiang Huang, Jiajun Zhang

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；pretraining(abstract)

Efficient Model-agnostic Alignment via Bayesian Persuasion

Fengshuo Bai, Mingzhi Wang, Zhaowei Zhang, Boyuan Chen, Yinda Xu, Ying Wen, Yaodong Yang

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；SFT(abstract)；RLHF(abstract)

AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs

Alireza Ghaffari, Sharareh Younesian, Vahid Partovi Nia, Boxing Chen, Masoud Asgharian

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；post-training(abstract)

"Ask Me Anything": How Comcast Uses LLMs to Assist Agents in Real Time

Scott Rome, Tianwen Chen, Raphael Tang, Luwei Zhou, Ferhan Ture

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly

Herbert Woisetschläger, Alexander Isenko, Shiqiang Wang, Ruben Mayer, Hans-Arno Jacobsen

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

Comments Camera-ready version for DEEM'24. Please cite the official ACM paper via https://doi.org/10.1145/3650203.3663331

Cost-Efficient Prompt Engineering for Unsupervised Entity Resolution

Navapat Nananukul, Khanin Sisaengsuwanchai, Mayank Kejriwal

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Uncovering the Hidden Cost of Model Compression

Diganta Misra, Muawiz Chaudhary, Agam Goyal, Bharat Runwal, Pin Yu Chen

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；foundation model(abstract)；prompting(abstract)

Comments Preprint

MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT

Omkar Thawakar, Ashmal Vayani, Salman Khan, Hisham Cholakal, Rao M. Anwer, Michael Felsberg, Tim Baldwin, Eric P. Xing, Fahad Shahbaz Khan

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；small language model(abstract)；SLM(abstract)

Comments Code available at : https://github.com/mbzuai-oryx/MobiLlama

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance

Pengyu Wang, Dong Zhang, Linyang Li, Chenkun Tan, Xinghao Wang, Ke Ren, Botian Jiang, Xipeng Qiu

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；SFT(abstract)；RLHF(abstract)

SPEED: Speculative Pipelined Execution for Efficient Decoding

Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Hasan Genc, Kurt Keutzer, Amir Gholami, Sophia Shao

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

Comments NeurIPS Workshop on Efficient Natural Language and Speech Processing (2023)

PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers' Workflows

Savvas Petridis, Michael Terry, Carrie J. Cai

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Dataset Quantization

Daquan Zhou, Kai Wang, Jianyang Gu, Xiangyu Peng, Dongze Lian, Yifan Zhang, Yang You, Jiashi Feng

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments 9 pages

Log Parsing: How Far Can ChatGPT Go?

Van-Hoang Le, Hongyu Zhang

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments This paper is accepted by ASE 2023, NIER Track

GPT-3-driven pedagogical agents for training children's curious question-asking skills

Rania Abdelghani, Yen-Hsiang Wang, Xingdi Yuan, Tong Wang, Pauline Lucas, Hélène Sauzéon, Pierre-Yves Oudeyer

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)