NeurIPS 2024 Past Efficiency
Workshop on Machine Learning and Compression, NeurIPS 2024
Compression Workshop @ NeurIPS 2024
- Submission deadline
- Oct 1, 2024, 11:59 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 (95)
Fetched from OpenReview (v2) on 2026-06-10.
-
A Theory for Compressibility of Graph Transformers for Transductive Learning
-
A Tighter Complexity Analysis of SparseGPT
-
Accelerating Memory-Efficient LLM Training and Fine-Tuning via Tracking the Gradient Subspace
-
Adapting Language Models via Token Translation
-
Adaptive Quantization and Pruning of Deep Neural Networks via Layer Importance Estimation
-
AdaQuantLM: LLM Quantization with Adaptive Bit-Widths
-
An image to tailor: I-Frame Domain Adaptation in Neural Video Compression
-
An Information Theory of Compute-Optimal Size Scaling, Emergence, and Plateaus in Language Models
-
Benchmarking neural lossless compression algorithms on multi-purpose astronomical image data
-
BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
-
Breaking Smoothness: The Struggles of Neural Compressors with Discontinuous Mappings
-
Bridging the Gap between Diffusion Models and Universal Quantization for Image Compression
-
CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization
-
Communication Compression for Tensor Parallel LLM Inference
-
Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging
-
Conditional Hallucinations for Image Compression
-
Copula-based Estimation of Continuous Sources for a Class of Constrained Rate-Distortion Functions
-
Deep Clustering with Associative Memories
-
Dense Backpropagation Improves Routing for Sparsely-Gated Mixture-of-Experts
-
Differentiable Attention
-
Diffusion Models With Learned Adaptive Noise
-
Distillation of Discrete Diffusion through Dimensional Correlations
-
Does Representation Matter? Exploring Intermediate Layers in Large Language Models
-
EAMQ: Environment-based Adaptive Model Quantization on Federated Reinforcement Learning
-
Efficient and Robust Spike Ensemble Coding of Signals
-
Efficient Compression of Sparse Accelerator Data Using Implicit Neural Representations and Importance Sampling
-
Efficient Model Compression Techniques with FishLeg
-
Empirical Upper Bounds for Unstructured Sparsity in Compute-Efficient Language Modeling
-
EXAQ: Exponent Aware Quantization For LLMs Acceleration
-
Exploiting Temporal Priors for Efficient Real-time Compression and Feedback of Wireless Channels
-
FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
-
Flexible image decoding in learned image compression
-
Formalizing Limits of Knowledge Distillation Using Partial Information Decomposition
-
Fused-Layer CNNs for Memory-Efficient Inference on Microcontrollers
-
FV-NeRV: Neural Compression for Free Viewpoint Videos
-
Getting free Bits Back from Rotational Symmetries in LLMs
-
Graph Transformation Augmentation for Contrastive Learning of Graph-Level Representation: An Initial Exploration
-
Grow to Compress? Efficient Training of Robust Networks on the Edge
-
How Many Does It Take to Prune a Network: Comparing One-Shot vs. Iterative Pruning Regimes
-
Improving Knowledge Distillation with Teacher's Explanation
-
Information-theoretic Generalization Analysis for Vector-Quantized VAEs
-
Integration of Large Vision Models in Driver Monitoring Systems: Compressing and Distilling for Real-Time Automotive Applications
-
Interactions Across Blocks in Post-Training Quantization of Large Language Models
-
Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations
-
Large Language Model Compression with Neural Architecture Search
-
Latent Probabilistic Dataset Distillation with Theoretical Guarantees
-
Layer-Importance guided Adaptive Quantization for Efficient Speech Emotion Recognition
-
Layer-wise Quantization for Distributed Variational Inequalities
-
Learnable Fourier-based Activations for Implicit Signal Representations
-
Learning to Compress: Local Rank and Information Compression in Deep Neural Networks
-
LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization
-
LLM Vocabulary Compression for Low-Compute Environments
-
LORC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy
-
Losslessly Compressible Neural Network Parameters
-
LSH-E Tells You What To Discard: An Adaptive Locality-Sensitive Strategy for KV Cache Compression
-
M2M-TAG: Training-Free Many-to-Many Token Aggregation for Vision Transformer Acceleration
-
Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training
-
MAPLE: Memory-Aware Predict and Load for Efficient LLM Inference
-
MCUCoder: Adaptive Bitrate Learned Video Compression for IoT Devices
-
Mind the Gap Between Synthetic and Real: Probing Transfer Capabilities of Stable Diffusion Images
-
Neural Compression for Multispectral Satellite Images
-
Neural Normalized Compression Distance and the Disconnect Between Compression and Classification
-
Non-interactive Remote Coordination
-
On the Relationship Between Model Training Dynamics and Early Pruning Periods
-
P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks
-
Partially Frozen Random Networks Contain Compact Strong Lottery Tickets
-
Perception Loss Function Adaptive to Rate for Learned Video Compression
-
PerCo (SD): Open Perceptual Compression
-
Polar Codes for Channel Simulation
-
Prechastic Coding: An Alternative Approach to Neural Network Description Lengths
-
QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models
-
Randomly Pivoted V-optimal Design: Fast Data Selection under Low Intrinsic Dimension
-
Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning
-
Sample compression unleashed : New generalization bounds for real valued losses
-
SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding
-
Self-Data Distillation for Recovering Quality in Pruned Large Language Models
-
Shrinking the Size of Deep Extreme Multi-Label Classification
-
Simple LLM Compression Recovery Using Dynamic Prompting with Theoretical Analysis
-
SNeRV: Scalable Neural Representations for Video Coding
-
SpikingVTG: Saliency Feedback Gating Enabled Spiking Video Temporal Grounding
-
Sustainable AI: Efficient Pruning of Large Language Models in Resource-Limited Environments
-
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
-
The Rate-Distortion-Perception Trade-Off with Algorithmic Realism
-
The Trichromatic Strong Lottery Ticket Hypothesis: Neural Compression With Three Primary Supermasks
-
Towards Scalable Compression with Universally Quantized Diffusion Models
-
Training Block-wise Sparse Models Using Kronecker Product Decomposition
-
Training-Free Visual Token Compression via Delayed Spatial Merging
-
Transformers Learn to Compress Variable-order Markov Chains in-Context
-
Unified Lookup Tables: Privacy-Preserving Foundation Models
-
Unifying Subsampling Pattern Variations for Compressed Sensing MRI with Neural Operators
-
Vector Quantization with Sorting Transformation
-
VRVQ: Variable Bitrate Residual Vector Quantization for Audio Compression
-
Wasserstein Distortion with Intrinsic $\sigma$-Maps
-
Weight-Sharing Method for Upsampling Layer from Feature Embedding Recursive Block
-
What Makes for Good Image Captions?