ICML 2024 Past EfficiencyOptimization
2nd Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ICML 2024)
WANT@ICML 2024
- Submission deadline
- Jun 3, 2024, 12:00 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (42)
Fetched from OpenReview (v2) on 2026-06-10.
-
Accelerating Best-of-N via Speculative Rejection
-
AdaMeM: Memory Efficient Momentum for Adafactor
-
Adaptive Model Pruning in Federated Learning through Loss Exploration
-
Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
-
An Analytical Approach to Enhancing DNN Efficiency and Accuracy Using Approximate Multiplication
-
Asynchronous Local-SGD Training for Language Modeling
-
Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates
-
Boolean Logic for Low-Energy Deep Learning
-
Can LLMs Enhance Performance Prediction for Deep Learning Models?
-
Class-aware Initialization of Early Exits for Pre-training Large Language Models
-
Coarse-to-Fine Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition
-
Communication Efficient Federated Learning with Differentiated Aggregation
-
DASH: Warm-Starting Neural Network Training Without Loss of Plasticity Under Stationarity
-
DiLoCo: Distributed Low-Communication Training of Language Models
-
DrJAX: Scalable and Differentiable MapReduce Primitives in JAX
-
ECO: Efficient Computational Optimization for Exact Machine Unlearning in Deep Neural Networks
-
Effective Layer Pruning Through Similarity Metric Perspective
-
Efficient Adaptive Federated Optimization
-
Efficient Document Ranking with Learnable Late Interactions
-
Enhancing Fine-grained Multi-modal Alignment via Adapters: A Parameter-Efficient Training Framework for Referring Image Segmentation
-
Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
-
Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough
-
Liouna: Biologically Plausible Learning for Efficient Pre-Training of Transferrable Deep Models
-
LoQT: Low Rank Adapters for Quantized Training
-
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
-
Lowering PyTorch's Memory Consumption for Selective Differentiation
-
Memory and Bandwidth are All You Need for Fully Sharded Data Parallel
-
Model-Agnostic Graph Dataset Compression with the Tree Mover’s Distance
-
MoReDrop: Dropout without Dropping
-
Multi-objective Differentiable Neural Architecture Search
-
Optimistic Asynchrony Control: Achieving Synchronous Convergence With Asynchronous Throughput for Embedding Model Training
-
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
-
Resource-constrained Neural Architecture Search on Language Models: A Case Study
-
SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models
-
Scalify: scale propagation for efficient low-precision LLM training
-
Single Train Multi Deploy on Topology Search Spaces using Kshot-Hypernet
-
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
-
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
-
Towards Efficient and Scalable Training of Differentially Private Deep Learning
-
u-μP: The Unit-Scaled Maximal Update Parametrization
-
Variational Stochastic Gradient Descent for Deep Neural Networks
-
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity