ICLR 2025PastOther
ICLR 2025 Workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning
MCDC @ ICLR 2025
- Submission deadline
- Feb 13, 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 (35)
Fetched from OpenReview (v2) on 2026-06-10.
A Framework for Double-Blind Federated Adaptation of Foundation Models
Adaptive Local Training in Federated Learning
An Empirical Study of Policy Interpolation via Diffusion Models
Beyond Top-K: Structured Sparsification for Compression in Pipeline Parallel
BICEC: Attachable Classification-Based Intelligent Control for Sustainable Computer Vision Systems
CAMEx: Curvature-aware Merging of Experts
Collective Model Intelligence Requires Compatible Specialization
ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation
Conditioning on Local Statistics for Scalable Heterogeneous Federated Learning (Tiny Paper)
Disentangling Sequence Memorization and General Capability in Large Language Models
Efficient Distributed Optimization under Heavy-Tailed Noise
Exact Unlearning of Finetuning Data via Model Merging at Scale
Exploring Asynchronism in SWARM Parallelism
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
Federated Circuits: A Unified Framework for Scalable and Efficient Federated Learning
FedMoDN: Federated Modular Decision Support Networks
HDEE: Heterogeneous Domain Expert Ensemble
Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning
How to Merge Multimodal Models Over Time?
Improving the Efficiency of Distributed Training using Sparse Parameter Averaging
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling
Momentum Look-Ahead for Asynchronous Distributed Low-Communication Training
Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers (Abridged)
NoEsis: A Modular LLM with Differentially Private Knowledge Transfer
On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
ReMod: Learning Structured Sparsity with ReLU Modulation
Rethinking Decentralized Learning: Towards More Realistic Evaluations with a Metadata-Agnostic Approach
Revisiting Sparse Mixture of Experts for Resource-adaptive Federated Fine-tuning Foundation Models
ROBUST ONLINE INFERENCE USING ADAPTIVE MODEL SWITCHING
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
Tight Clusters Make Specialized Experts
Training Plug n' Play Knowledge Modules with Deep Context Distillation
Truncate without Fear: Module Aggregation and Redistribution in Federated Low-Rank Adaptation