ICML 2025 Workshop TTODLer-FM Submissions

Higher Acceptance Rates for Speculative Decoding with Randomised Drafting
William Toner, Martin Asenov, Rajkarn Singh, Artjom Joosen
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
Avetik Karagulyan, Egor Shulgin, Abdurakhmon Sadiev, Peter Richtárik
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Preserve then Quantize: Dominant-Subspace Guided Low-Rank Reconstruction
Yoonjun Cho, Dongjae Jeon, Soeun Kim, Albert No
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Oral
- Readers: Everyone
Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding
Mingxiao Huo, Jiayi Zhang, Hewei Wang, Jinfeng Xu, Zheyu Chen, Huilin Tai, Ian Yijun Chen
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
Philip Zmushko, Aleksandr Beznosikov, Martin Takáč, Samuel Horváth
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Zoop it! Efficient Zero-Order Optimization with Output Perturbation
Xixi Hu, Bo Liu, qiang liu, Xiaocong Du, Bhargav Bhushanam, Louis Feng, Chengyue Gong, Kaizhao Liang
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
Berkin Durmus, Arda Okan, Eduardo Pacheco, Zach Nagengast, Atila Orhon
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Oral
- Readers: Everyone
Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers
Joshua Barron, Devin White
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Oral
- Readers: Everyone
LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
Nurbek Tastan, Stefanos Laskaridis, Martin Takáč, Karthik Nandakumar, Samuel Horváth
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation for Federated Learning
Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud, Taha Ceritli, Hayder Elesedy, Mete Ozay, Peter Richtárik
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
Egor Shulgin, Grigory Malinovsky, Sarit Khirirat, Peter Richtárik
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Offloaded Reasoning: Efficient Inference for Large Language Models via Modular Reasoning and Refinement
Ishan Jindal, Jayant Taneja, Badrinath chandana, Vikas Kapur, SACHIN DEV SHARMA
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Oral
- Readers: Everyone
Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order LLM Fine-Tuning
Egor Petrov, Evseev Grigoriy, Aleksey Antonov, Andrey Veprikov, Pavel Plyusnin, Nikolay Bushkov, Stanislav Moiseev, Aleksandr Beznosikov
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Unlocking the Potential of Extremely Low-Bit Sparse Transformers through Adaptive Multi-bit Supermasks and Random Weights
Yasuyuki Okoshi, Hikari Otsuka, Junnosuke Suzuki, Daichi Fujiki, Masato Motomura
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices
Mingxue Xu, Yao Lei Xu, Danilo Mandic
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Kinetics: Rethinking Test-Time Scaling Laws
Ranajoy Sadhukhan, Zhuoming Chen, Haizhong Zheng, Yang Zhou, Emma Strubell, Beidi Chen
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Oral
- Readers: Everyone
Zeroth-Order Optimization is Secretly Single-Step Policy Optimization
Junbin Qiu, Zhengpeng Xie, Xiangda Yan, Yongjie Yang, Yao Shu
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
DiffusionBlocks: Blockwise Training for Generative Models via Score-Based Diffusion
Makoto Shing, Takuya Akiba
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Dynamic Guardian Models: Realtime Content Moderation With User-Defined Policies
Monte Hoover, Vatsal Baherwani, Neel Jain, Khalid Saifullah, Joseph James Vincent, Chirag Jain, Melissa Kazemi Rad, C. Bayan Bruss, Ashwinee Panda, Tom Goldstein
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Lion Cub: Minimizing Communication Overhead in Distributed Lion
Satoki Ishikawa, Tal Ben-Nun, Brian Van Essen, Rio Yokota, Nikoli Dryden
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Addition is almost all you need: Compressing neural networks with double binary factorization
Vladimír Boža, Vladimír Macko
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Overcoming label shift in targeted federated learning
Adam Breitholtz, Edvin Listo Zec, Fredrik D. Johansson
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Capability Transfer from Large to Small Models with Synthetically-Generated Data
Lillian Sun, Emma Yang, Arif Kerem Dayi
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
Towards understanding of orthogonalization in Muon
Valentyn Boreiko, Zhiqi Bu, Sheng Zha
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone
MatMuls are Enough for Efficient and Performant Linear-Time Attention
Andrew Argatkiny, Ilya Makarov
- Published: 10 Jun 2025, Last Modified: 01 Jul 2025
- TTODLer-FM @ ICML 2025 Poster
- Readers: Everyone