ICML 2025PastEfficiency
Tiny Titans: The next wave of On-Device Learning for Foundational Models (TTODLer-FM)
TTODLer-FM @ ICML 2025
- Submission deadline
- May 27, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (32)
Fetched from OpenReview (v2) on 2026-06-10.
Addition is almost all you need: Compressing neural networks with double binary factorization
Capability Transfer from Large to Small Models with Synthetically-Generated Data
Compression of Large Language Models by Condensed Weight Representation
DiffusionBlocks: Blockwise Training for Generative Models via Score-Based Diffusion
Dynamic Guardian Models: Realtime Content Moderation With User-Defined Policies
Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
FAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training
FGFP: A Fractional Gaussian Filter and Pruning for Deep Neural Networks Compression
First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
Gatekeeper: Improving Model Cascades Through Confidence Tuning
Higher Acceptance Rates for Speculative Decoding with Randomised Drafting
Kinetics: Rethinking Test-Time Scaling Laws
Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order LLM Fine-Tuning
Lion Cub: Minimizing Communication Overhead in Distributed Lion
LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
MatMuls are Enough for Efficient and Performant Linear-Time Attention
Offloaded Reasoning: Efficient Inference for Large Language Models via Modular Reasoning and Refinement
Overcoming label shift in targeted federated learning
Predictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models
Preserve then Quantize: Dominant-Subspace Guided Low-Rank Reconstruction
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation for Federated Learning
SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding
TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices
Token-Efficient RL for LLM Reasoning
Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers
Towards understanding of orthogonalization in Muon
Unlocking the Potential of Extremely Low-Bit Sparse Transformers through Adaptive Multi-bit Supermasks and Random Weights
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
Zeroth-Order Optimization is Secretly Single-Step Policy Optimization
Zoop it! Efficient Zero-Order Optimization with Output Perturbation