conftrace_
← Application Areas
Machine Learning › Application Areas ›

Efficient Computing

6,876 papers

Papers per year

Papers

Active Learning with LLMs for Partially Observed and Cost-Aware Scenarios NIPS 2024
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning NIPS 2024
Derivative-enhanced Deep Operator Network NIPS 2024
RelBench: A Benchmark for Deep Learning on Relational Databases NIPS 2024
Efficient multi-prompt evaluation of LLMs NIPS 2024
Out-Of-Distribution Detection with Diversification (Provably) NIPS 2024
SnapKV: LLM Knows What You are Looking for Before Generation NIPS 2024
Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information NIPS 2024
SIRIUS : Contexual Sparisty with Correction for Efficient LLMs NIPS 2024
SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization NIPS 2024
Grammar-Aligned Decoding NIPS 2024
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization NIPS 2024
Learning-Augmented Approximation Algorithms for Maximum Cut and Related Problems NIPS 2024
Efficiency for Free: Ideal Data Are Transportable Representations NIPS 2024
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization NIPS 2024
Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models NIPS 2024
Accelerating Transformers with Spectrum-Preserving Token Merging NIPS 2024
Neural Network Reparametrization for Accelerated Optimization in Molecular Simulations NIPS 2024
Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models NIPS 2024
Adaptive Depth Networks with Skippable Sub-Paths NIPS 2024
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training NIPS 2024
Sparse maximal update parameterization: A holistic approach to sparse training dynamics NIPS 2024
Accelerating Blockwise Parallel Language Models with Draft Refinement NIPS 2024
SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation NIPS 2024
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum NIPS 2024