ICML 2025 Workshop ES-FoMo-III Submissions

Hardware-Efficient Attention for Fast Decoding
Ted Zadouri, Hubert Strauss, Tri Dao
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III Oral
- Readers: Everyone
Cache Saver: A Modular Framework for Efficient, Affordable, and Reproducible LLM Inference
Nearchos Potamitis, Lars Henning Klein, Chongyang Xu, Attreyee Mukherjee, Bardia Mohammadi, Niket Tandon, Laurent Bindschaedler, Akhil Arora
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Continuous Autoregressive Generation with Mixture of Gaussians
Alex Quach, Tsun-Hsuan Wang, Ramin Hasani, Mathias Lechner, Alexander Amini
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Cost-Efficient Serving of LLM Agents via Test-Time Plan Caching
Qizheng Zhang, Michael Wornow, Kunle Olukotun
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
Liliang Ren, Congcong Chen, Haoran Xu, Young Jin Kim, Adam Atkinson, Zheng Zhan, Jiankai Sun, Baolin Peng, Liyuan Liu, Shuohang Wang, Hao Cheng, Jianfeng Gao, Weizhu Chen, yelong shen
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
Mónika Farsang, Ramin Hasani, Radu Grosu
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Learning Adaptive Parallel Reasoning with Language Models
Jiayi Pan, Xiuyu Li, Long Lian, Charlie Victor Snell, Yifei Zhou, Adam Yala, Trevor Darrell, Kurt Keutzer, Alane Suhr
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs
Beomsik Cho, Jaehyung Kim
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
TinyServe: Query-Aware Cache Selection for Efficient LLM Inference
Dong Liu, Yanxuan Yu
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
Mugilan Ganesan, Shane Segal, Ankur Aggarwal, Nish Sinnadurai, Sean Lie, Vithursan Thangarasa
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Training-free LLM Verification via Recycling Few-shot Examples
Dongseok Lee, JIMYUNG HONG, Dongyoung Kim, Jaehyung Kim
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III Spotlight
- Readers: Everyone
PiKV: KV Cache Management System for MoE Architecture
Dong Liu, Yanxuan Yu, Ben Lengerich, Ying Nian Wu, Xuhong Wang
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture
Shuchen Xue, Tianyu Xie, Tianyang Hu, Zijin Feng, Jiacheng Sun, Kenji Kawaguchi, Zhenguo Li, Zhi-Ming Ma
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III Oral
- Readers: Everyone
BlockBPE: Parallel BPE Tokenization
Amos You
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
SPECS: Faster Test-Time Scaling through Speculative Drafts
Mert Cemri, Nived Rajaraman, Rishabh Tiwari, Xiaoxuan Liu, Kurt Keutzer, Ion Stoica, Kannan Ramchandran, Ahmad Beirami, Ziteng Sun
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Proof-of-Concept for Private Local-to-Cloud LLM Chat via Trusted Execution Environments
Avanika Narayan, Dan Biderman, Christopher Re
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs
Reza Arabpour, Haitz Sáez de Ocáriz Borde, Anastasis Kratsios
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
PoTPTQ: A Two-step Power-of-Two Post-training for LLMs
Xinyu Wang, Vahid Partovi Nia, Peng Lu, Jerry Huang, Xiao-Wen Chang, Boxing Chen, Yufei Cui
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Cartridges: Lightweight and general-purpose long context representations via self-study
Sabri Eyuboglu, Ryan Saul Ehrlich, Simran Arora, Neel Guha, Dylan Zinsley, Emily Ruoyu Liu, Atri Rudra, James Y. Zou, Azalia Mirhoseini, Christopher Re
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III Oral
- Readers: Everyone
TORCHSIM: High Fidelity Runtime and Memory Estimation for Distributed Training
Sanket Purandare, Emma Yang, Andrew Zhao, Qitong Wang, Wei Feng, Alban Desmaison, Andrew Gu, Tianyu Liu, Less Wright, Gokul Nadathur, Stratos Idreos
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness
Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Ser-Nam Lim, Rajiv Ramnath
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations
Marco Federici, Riccardo Del Chiaro, Boris van Breugel, Paul N. Whatmough, Markus Nagel
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Exploring Diffusion Transformer Designs via Grafting
Keshigeyan Chandrasegaran, Michael Poli, Daniel Y Fu, Dongjun Kim, Lea M. Hadzic, Manling Li, Agrim Gupta, Stefano Massaroli, Azalia Mirhoseini, Juan Carlos Niebles, Stefano Ermon, Li Fei-Fei
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Autoregressive Language Modeling by Compressed Sequence Mixing
Jatin Prakash, Aahlad Manas Puli, Rajesh Ranganath
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone
Toward Dataset Distillation for Regression Problems
Jamie Mahowald, Ravi Srinivasan, Zhangyang Wang
- Published: 11 Jun 2025, Last Modified: 10 Jul 2025
- ES-FoMo III
- Readers: Everyone