ICML 2024 Workshop ES-FoMo-II Submissions

Fast Adaptation and Robust Quantization of Multi-Modal Foundation Models from Associative Memory: A Case Study in SpeechLM
Shang Wu, Yen-Ju Lu, Haozheng Luo, Jerry Yao-Chieh Hu, Jiayi Wang, Najim Dehak, Jesus Villalba, Han Liu
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
OutEffHop: A Principled Outlier-Efficient Attention Layer from Dense Associative Memory Models
Haozheng Luo, Jerry Yao-Chieh Hu, Pei-Hsuan Chang, Hong-Yu Chen, Weijian Li, Wei-Po Wang, Han Liu
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
CLAM: Unifying Finetuning, Quantization, and Pruning by Chaining LLM Adapter Modules
Neelay Velingker, Jason Liu, Amish Sethi, William Dodds, Zhiqiu Xu, Saikat Dutta, Mayur Naik, Eric Wong
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Fewer Truncations Improve Language Modeling
Hantian Ding, Zijian Wang, Giovanni Paolini, Varun Kumar, Anoop Deoras, Dan Roth, Stefano Soatto
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones
Andrey Zhmoginov, Jihwan Lee, Mark Sandler
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Scavenging Hyena: Distilling Transformers into Long Convolution Models
Tokiniaina Raharison Ralambomihanta, Shahrad Mohammadzadeh, Sami Nur Islam, Wassim Jabbour, Laurence Liang
- Published: 21 Jun 2024, Last Modified: 24 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
LAuReL: Learned Augmented Residual Layer
Gaurav Menghani, Ravi Kumar, Sanjiv Kumar
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Revealing the Utilized Rank of Subspaces of Learning in Neural Networks
Isha Garg, Christian Koguchi, Eshan Verma, Daniel Ulbricht
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Block Verification Accelerates Speculative Decoding
Ziteng Sun, Uri Mendlovic, Yaniv Leviathan, Asaf Aharoni, Ahmad Beirami, Jae Hun Ro, Ananda Theertha Suresh
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile Applications
Kshitij Bhardwaj
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
Kaixuan Huang, Xudong Guo, Mengdi Wang
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Unlocking the Global Synergies in Low-Rank Adapters
Zixi Zhang, Cheng Zhang, Xitong Gao, Robert D. Mullins, George Anthony Constantinides, Yiren Zhao
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Janus: An Efficient and Expressive Subquadratic Architecture for Modeling Biological Sequences
Krithik Ramesh, Sameed Muneeb Siddiqui, Michael Mitzenmacher, Pardis Sabeti
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Optimised Grouped-Query Attention Mechanism for Transformers
Yuang Chen, Cheng Zhang, Xitong Gao, Robert D. Mullins, George Anthony Constantinides, Yiren Zhao
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Filip Szatkowski, Bartosz Wójcik, Mikołaj Piórczyński, Simone Scardapane
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
CO2: Precise Attention Score Observation for improving KV Cache Replacement in Large Language Model
Meguru Yamazaki, Shivaram Venkataraman
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis
Darren Yan Key, Andy He, Mason Bulling, Andrew Chang, Skyler Shapiro, Everett Lee
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
Rickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin, Justin Solomon
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Efficient multi-prompt evaluation of LLMs
Felipe Maia Polo, Ronald Xu, Lucas Weber, Mírian Silva, Onkar Bhardwaj, Leshem Choshen, Allysson Flavio Melo de Oliveira, Yuekai Sun, Mikhail Yurochkin
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Train your cake and eat it too! Repurposing collaborative training to tailor LLMs to private data without sharing
Boris Radovič, Mohammed Aljahdali, Marco Canini, Veljko Pejović, Zuhair Khayyat
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Task Addition and Weight Disentanglement in Closed-Vocabulary Models
Adam Hazimeh, Alessandro Favero, Pascal Frossard
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Seeded LoRA: Collaborative Fine-Tuning Through Seed Initialization of Adapters
Alejandro R. Salamanca, Ahmet Üstün, Nicki Skafte Detlefsen, Tim Dettmers
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
GPTVQ: The Blessing of Dimensionality for LLM Quantization
Mart Van Baalen, Andrey Kuzmin, Markus Nagel, Peter Couperus, Artem Bolshakov, Cedric Bastoul, Eric Mahurin, Tijmen Blankevoort, Paul Whatmough
- Published: 21 Jun 2024, Last Modified: 24 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Low Rank Quantization-Aware Training for LLMs
Yelysei Bondarenko, Riccardo Del Chiaro, Markus Nagel
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Optimistic Verifiable Training by Controlling Hardware Nondeterminism
Megha Srivastava, Simran Arora, Dan Boneh
- Published: 21 Jun 2024, Last Modified: 26 Jul 2024
- ES-FoMo-II 2024 Poster
- Readers: Everyone