Skip to yearly menu bar Skip to main content


Workshop

Fine-Tuning in Modern Machine Learning: Principles and Scalability

Fanghui Liu ⋅ Grigorios Chrysos ⋅ Beidi Chen ⋅ Rebekka Burkholz ⋅ Saleh Soltan ⋅ Angeliki Giannou ⋅ Masashi Sugiyama ⋅ Volkan Cevher
Project Page [ OpenReview] 

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
8:50 AM
Opening remarks
Fanghui Liu
9:00 AM
Invited talk 1 - Azalia Mirhoseini
Azalia Mirhoseini
9:40 AM
Invited talk 2 - Jason Lee
Jason Lee
10:30 AM
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
Jonas Hübotter ⋅ Sascha Bongni ⋅ Ido Hakimi ⋅ Andreas Krause
10:42 AM
Parameter-Efficient Fine-Tuning of State Space Models
Kevin Galim ⋅ Jungtaek Kim ⋅ Wonjun Kang ⋅ Yuchen Zeng ⋅ HYUNG IL KOO ⋅ Kangwook Lee
10:54 AM
Entropic Distribution Matching for Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity
Ziniu Li ⋅ Congliang Chen ⋅ Tian Xu ⋅ Zeyu Qin ⋅ Jiancong Xiao ⋅ Ruoyu Sun ⋅ Zhiquan Luo
11:06 AM
RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates
Md Kowsher ⋅ Tara Esmaeilbeig ⋅ Chun Nam Yu ⋅ Mojtaba Soltanalian ⋅ Niloofar Yousefi
11:18 AM
COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences
Yixin Liu ⋅ Argyris Oikonomou ⋅ Weiqiang Zheng ⋅ Yang Cai ⋅ Arman Cohan
11:30 AM
Poster session I
2:40 PM
Invited talk 4 - Quanquan Gu
Quanquan Gu
3:30 PM
Panel discussion
Danqi Chen ⋅ Tri Dao ⋅ Taiji Suzuki ⋅ Yuandong Tian ⋅ Quanquan Gu ⋅ Leena Chennuru Vankadara
4:30 PM
Closing remarks
Grigorios Chrysos
DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent
Taiyi Wang ⋅ Zhihao Wu ⋅ Jianheng Liu ⋅ Derek Yuen ⋅ Jianye Hao ⋅ Jun Wang ⋅ Kun Shao
Semi-Supervised Fine-Tuning of Vision Foundation Models with Content-Style Decomposition
Mariia Drozdova ⋅ Vitaliy Kinakh ⋅ Yury Belousov ⋅ Erica Lastufka ⋅ Slava Voloshynovskiy
Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation
Manish Bhattarai ⋅ Javier E. Santos ⋅ Ismael Boureima ⋅ Daniel O'Malley
CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation
Ingo Ziegler ⋅ Abdullatif Köksal ⋅ Desmond Elliott ⋅ Hinrich Schuetze
ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning
Jaedong Hwang ⋅ Brian Cheung ⋅ Zhang-Wei Hong ⋅ Akhilan Boopathy ⋅ Pulkit Agrawal ⋅ Ila Fiete
Parasite Networks: Transfer Learning in Resource-Constrained Domains
Andrew Alini ⋅ Douglas E Sturim ⋅ Kevin Brady ⋅ Pooya Khorrami
PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences
Daiwei Chen ⋅ Yi Chen ⋅ Aniket Rege ⋅ Ramya Korlakai Vinayak
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
Noam Razin ⋅ Sadhika Malladi ⋅ Adithya Bhaskar ⋅ Danqi Chen ⋅ Sanjeev Arora ⋅ Boris Hanin
Adapting Language Models via Token Translation
Zhili Feng ⋅ Tanya Marwah ⋅ Lester Mackey ⋅ David Alvarez-Melis ⋅ Nicolo Fusi
Self-Stitching: Widely Applicable and Efficient Transfer Learning Using Stitching Layer
Tanachai Anakewat ⋅ Yusuke Mukuta ⋅ Thomas Westfechtel ⋅ Tatsuya Harada
Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement
Kotaro Yoshida ⋅ Yuji Naraki ⋅ Takafumi Horie ⋅ Ryosuke Yamaki ⋅ Ryotaro Shimizu ⋅ Yuki Saito ⋅ Julian Mcauley ⋅ Hiroki Naganuma
Uncertainty-Penalized Direct Preference Optimization
Sam Houliston ⋅ Alizée Pace ⋅ Alexander Immer ⋅ Gunnar Rätsch
Learning Robust Representations for Transfer in Reinforcement Learning
Faisal Ahmed Abdelrahman Mohamed ⋅ Roger Creus Castanyer ⋅ Hongyao Tang ⋅ Zahra Sheikhbahaee ⋅ Glen Berseth
Effective Text-to-Image Alignment with Quality Aware Pair Ranking
Kunal Singh ⋅ Mukund Khanna ⋅ Pradeep Moturi
Ensembling Finetuned Language Models for Text Classification
Sebastian Pineda Arango ⋅ Maciej Janowski ⋅ Lennart Purucker ⋅ Arber Zela ⋅ Frank Hutter ⋅ Josif Grabocka
Variational Low-Rank Adaptation Using IVON
Bai Cong ⋅ Nico Daheim ⋅ Yuesong Shen ⋅ Daniel Cremers ⋅ Rio Yokota ⋅ Mohammad Emtiyaz Khan ⋅ Thomas Möllenhoff
UnoLoRA: Single Low-Rank Adaptation for Efficient Multitask Fine-tuning
Akash Kamalesh ⋅ Anirudh Lakhotia ⋅ Nischal S ⋅ Prerana Sanjay Kulkarni ⋅ Gowri Srinivasa
Flat-LoRA: Low-Rank Adaption over a Flat Loss Landscape
Tao Li ⋅ Zhengbao He ⋅ Yujun Li ⋅ Yasheng Wang ⋅ Lifeng Shang ⋅ Xiaolin Huang
TOU: Truncated-factorized reduction for an efficient-parameter model fine-tuning
Phuong Thi-Mai Nguyen ⋅ Minh-Son Dao ⋅ Koji Zettsu
Towards Natural Machine Unlearning
Zhengbao He ⋅ Tao Li ⋅ Xinwen Cheng ⋅ Zhehao Huang ⋅ Xiaolin Huang
Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs
Yung-Chieh Chan ⋅ George Pu ⋅ Apaar Shanker ⋅ Parth Suresh ⋅ Penn Jenks ⋅ John Heyer ⋅ Sam Denton
Investigating the Role of Fine-Tuning in Addressing the Gap Between Synthetic and Real Data in Generative Foundation Models
Leonhard Hennicke ⋅ Christian Medeiros Adriano ⋅ Holger Giese ⋅ Lukas Schott ⋅ Jan Koehler
Skip Transformers: Efficient Inference through Skip-Routing
Matthew Peroni ⋅ Dimitris Bertsimas
Optimizing Small Language Models for In-Vehicle Function-Calling
Yahya SOWTI KHIABANI ⋅ Farris Atif ⋅ Chieh Hsu ⋅ Sven Stahlmann ⋅ Tobias Michels ⋅ Sebastian Kramer ⋅ Benedikt Heidrich ⋅ M. Saquib Sarfraz ⋅ Julian Merten ⋅ Faezeh Tafazzoli
Entropic Distribution Matching for Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity
Ziniu Li ⋅ Congliang Chen ⋅ Tian Xu ⋅ Zeyu Qin ⋅ Jiancong Xiao ⋅ Ruoyu Sun ⋅ Zhiquan Luo
Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
Shuqi Ke ⋅ Charlie Hou ⋅ Sewoong Oh ⋅ Giulia Fanti
Understanding Visual Concepts Across Models
Brandon Trabucco ⋅ Max Gurinas ⋅ Kyle Doherty ⋅ Ruslan Salakhutdinov
Towards Long-Context Time Series Foundation Models With A Handful Of Additional Parameters
Nina Żukowska ⋅ Mononito Goswami ⋅ Michal Wilinski ⋅ Willa Potosnak ⋅ Artur Dubrawski
A Meta-Algorithm for Aligning LLMs with General Preferences
Yixin Liu ⋅ Argyris Oikonomou ⋅ Weiqiang Zheng ⋅ Yang Cai ⋅ Arman Cohan
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
Jonas Hübotter ⋅ Sascha Bongni ⋅ Ido Hakimi ⋅ Andreas Krause
Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
Heyang Zhao ⋅ Chenlu Ye ⋅ Quanquan Gu ⋅ Tong Zhang
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
Simran Kaur ⋅ Simon Park ⋅ Anirudh Goyal ⋅ Sanjeev Arora
One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation
Fabian Paischer ⋅ Lukas Hauzenberger ⋅ Thomas Schmied ⋅ Benedikt Alkin ⋅ Marc Deisenroth ⋅ Sepp Hochreiter
A Layer Selection Approach to Test Time Adaptation
Sabyasachi Sahoo ⋅ Mostafa ElAraby ⋅ JONAS NGNAWE ⋅ Yann Pequignot ⋅ Frederic Precioso ⋅ Christian Gagné
Scalability of memorization-based machine unlearning
KAIRAN ZHAO ⋅ Peter Triantafillou
Efficient Fine-Tuning of CNN-based Foundation Models for Segmentation in 3D Medical Images
Mees Hudepohl ⋅ Suraj Pai ⋅ Heysem Kaya ⋅ Hugo Aerts
TreeTop: Topology-Aware Fine-Tuning for LLM Conversation Tree Understanding
Jashn Arora ⋅ Rahul Madhavan ⋅ Karthikeyan Shanmugam ⋅ John Palowitch ⋅ Manish Jain
Hierarchical Unlearning Framework for Multi-Class Classification
Abraham Chan ⋅ Arpan Gujarati ⋅ Karthik Pattabiraman ⋅ Sathish Gopalakrishnan
Model Soup for Better RLHF: Weight Space Averaging to Improve Alignment in LLMs
Atoosa Chegini ⋅ Hamid Kazemi ⋅ Iman Mirzadeh ⋅ Dong Yin ⋅ Maxwell Horton ⋅ Moin Nabi ⋅ Mehrdad Farajtabar ⋅ Keivan Alizadeh vahid
Improving LLM Generation with Inverse and Forward Alignment: Reward Modeling, Prompting, Fine-Tuning, and Inference-Time Optimization
Hao Sun ⋅ Thomas Pouplin ⋅ Nicolás Astorga ⋅ Tennison Liu ⋅ Mihaela van der Schaar
RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates
Md Kowsher ⋅ Tara Esmaeilbeig ⋅ Chun Nam Yu ⋅ Mojtaba Soltanalian ⋅ Niloofar Yousefi
An empirical study of CLIP fine-tuning with similarity clusters
Shixuan Liu ⋅ Yiwei Lyu ⋅ Honglak Lee ⋅ Todd Hollon
ActNAS : Generating Efficient YOLO Models using Activation NAS
Sudhakar Sah ⋅ Ravish Kumar ⋅ Darshan Ganji ⋅ Ehsan Saboori
Memory retaining finetuning via distillation
Zitong Yang ⋅ Aonan Zhang ⋅ Sam Wiseman ⋅ Xiang Kong ⋅ Ke Ye ⋅ Dong Yin
Faster, More Efficient RLHF through Off-Policy Asynchronous Learning
Michael Noukhovitch ⋅ Shengyi Huang ⋅ Sophie Xhonneux ⋅ Arian Hosseini ⋅ Rishabh Agarwal ⋅ Aaron Courville
Instant Transformer Adaption via HyperLoRA
Rujikorn Charakorn ⋅ Edoardo Cetin ⋅ Yujin Tang ⋅ Robert Lange
Estimating Effects of Tokens in Preference Learning
Hsiao-Ru Pan ⋅ Maximilian Mordig ⋅ Bernhard Schölkopf
HyperDPO: Hypernetwork-based Multi-Objective Fine-Tuning Framework
Yinuo Ren ⋅ Tesi Xiao ⋅ Michael Shavlovsky ⋅ Lexing Ying ⋅ Holakou Rahmanian
Parameter-Efficient Fine-Tuning of State Space Models
Kevin Galim ⋅ Wonjun Kang ⋅ Yuchen Zeng ⋅ HYUNG IL KOO ⋅ Kangwook Lee
Flexora: Flexible Low-Rank Adaptation for Large Language Models
Chenxing Wei ⋅ Yao Shu ⋅ Ying He ⋅ Fei Yu
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Vijay Chandra Lingam ⋅ Atula Neerkaje ⋅ Aditya Vavre ⋅ Aneesh Shetty ⋅ Gautham Krishna Gudur ⋅ Joydeep Ghosh ⋅ Alex Dimakis ⋅ Eunsol Choi ⋅ Aleksandar Bojchevski ⋅ Sujay Sanghavi
Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization
Hritik Bansal ⋅ Ashima Suvarna ⋅ Gantavya Bhatt ⋅ Nanyun Peng ⋅ Kai-Wei Chang ⋅ Aditya Grover
FRACTAL: Fine-Grained Scoring from Aggregate Text Labels
Yukti Makhija ⋅ Priyanka Agrawal ⋅ Rishi Saket ⋅ Aravindan Raghuveer
Teaching LLMs How To Learn with Contextual Fine-Tuning
Younwoo Choi ⋅ Muhammad Adil Asif ⋅ Ziwen Han ⋅ John Willes ⋅ Rahul Krishnan
Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment
Chenliang Li ⋅ Siliang Zeng ⋅ Zeyi Liao ⋅ Jiaxiang Li ⋅ Dongyeop Kang ⋅ Alfredo Garcia ⋅ Mingyi Hong
On Efficient Distillation from LLMs to SLMs
Metod Jazbec ⋅ Menglin Xia ⋅ Ankur Mallick ⋅ Daniel Madrigal ⋅ Dongge Han ⋅ Samuel Kessler ⋅ Victor Ruehle
What Causes a Disparate Impact in a Quantized Model?
Abhimanyu Bellam ⋅ Jung-Eun Kim
Fitness Aware Human Motion Generation with Fine-Tuning
Kiril Bikov ⋅ Shiye Su ⋅ Deepro Choudhury ⋅ Zhilin Guo ⋅ Weihao Xia ⋅ Mehmet Çeliktenyıldız ⋅ Chenliang Zhou ⋅ Param Hanji ⋅ Cengiz Oztireli
Best Unpacking DPO and PPO: Disentangling Practices for Learning from Preference Feedback
Hamish Ivison ⋅ Yizhong Wang ⋅ Jiacheng Liu ⋅ Zeqiu Wu ⋅ Valentina Pyatkin ⋅ Nathan Lambert ⋅ Noah Smith ⋅ Yejin Choi ⋅ Hannaneh Hajishirzi
LLM Alignment Through Successive Policy Re-weighting (SPR)
Xinnan Zhang ⋅ Siliang Zeng ⋅ Jiaxiang Li ⋅ Kaixiang Lin ⋅ Mingyi Hong
Token Pruning using a Lightweight Background Aware Vision Transformer
Sudhakar Sah ⋅ Ravish Kumar ⋅ Honnesh Rohmetra ⋅ Ehsan Saboori
Simultaneous Weight and Architecture Optimization for Neural Networks
Zitong Huang ⋅ Mansooreh Montazerin ⋅ Ajitesh Srivastava
Addax: Resource-Efficient Fine-Tuning of Language Models with a Combination of Forward-Backward and Forward-Only Passes
Zeman Li ⋅ Xinwei Zhang ⋅ Peilin Zhong ⋅ Yuan Deng ⋅ Vahab Mirrokni ⋅ Meisam Razaviyayn
XoRA: Expander Adapted LoRA Finetuning
Amaljith EV ⋅ Arindam Biswas ⋅ Suryam Arnav Kalra ⋅ Pabitra Mitra ⋅ Biswajit Basu
GaLore-mini: Low Rank Gradient Learning with Fewer Learning Rates
WH Huang ⋅ Zhenyu Zhang ⋅ Yushun Zhang ⋅ Zhiquan Luo ⋅ Ruoyu Sun ⋅ Zhangyang "Atlas" Wang
Variational Best-of-N Alignment
Afra Amini ⋅ Tim Vieira ⋅ Elliott Ash ⋅ Ryan Cotterell
Fine-tuning Vision Classifiers On A Budget
Sunil Kumar ⋅ Ted Sandler ⋅ Paulina Varshavskaya
Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples
Noël Vouitsis ⋅ Rasa Hosseinzadeh ⋅ Brendan Ross ⋅ Valentin Villecroze ⋅ Satya Krishna Gorti ⋅ Jesse Cresswell ⋅ Gabriel Loaiza-Ganem
Towards Exploring Continual Fine-Tuning for Enhancing Language Ability in Large Language Model
Divyanshu Aggarwal ⋅ Sankarshan Damle ⋅ Navin Goyal ⋅ Satya Lokam ⋅ Sunayana Sitaram
Analysing Softmax Entropy Minimization for Adaptating Multitask Models at Test-time
Soumyajit Chatterjee ⋅ Abhirup Ghosh ⋅ Fahim Kawsar ⋅ Mohammad Malekzadeh