← Optimization & Theory
Deep Learning › Optimization & Theory ›

Efficient Computing

1253 directly classified papers

Papers per year

Papers

Practical Offloading for Fine-Tuning LLM on Commodity GPU via Learned Sparse Projectors AAAI 2025
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference AAAI 2025
QiMeng-GEMM: Automatically Generating High-Performance Matrix Multiplication Code by Exploiting Large Language Models AAAI 2025
Design Principle Transfer in Neural Architecture Search via Large Language Models AAAI 2025
BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement AAAI 2025
COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025
Multi-Branch Self-Drafting for LLM Inference Acceleration AAAI 2025
Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree AAAI 2025
Building Vision Models upon Heat Conduction CVPR 2025
ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition AAAI 2025
3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding AAAI 2025
Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference AAAI 2025
Segment-Based Attention Masking for GPTs ACL 2025
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity ACL 2025
Error-driven Data-efficient Large Multimodal Model Tuning ACL 2025
CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference ACL 2025
VSSD: Vision Mamba with Non-Causal State Space Duality ICCV 2025
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference ACL 2025
StitchLLM: Serving LLMs, One Block at a Time ACL 2025
LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models ACL 2025
Breaking the Encoder Barrier for Seamless Video-Language Understanding ICCV 2025
KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding ACL 2025
Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free Method ACL 2025
UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation ACL 2025
DiffSkip: Differential Layer Skipping in Large Language Models ACL 2025