SOTAVerified

Computational Efficiency

Methods and optimizations to reduce the computational resources (e.g., time, memory, or power) needed for training and inference in models. This involves techniques that streamline processing, optimize algorithms, or leverage hardware to enhance performance without compromising accuracy.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 4891 papers

TitleStatusHype
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial AttacksCode2
PP-OCR: A Practical Ultra Lightweight OCR SystemCode2
I^2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene ForecastingCode2
Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing DetectionCode2
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene RepresentationCode2
Integrating Neural Operators with Diffusion Models Improves Spectral Representation in Turbulence ModelingCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
AdaFisher: Adaptive Second Order Optimization via Fisher InformationCode2
Harder Tasks Need More Experts: Dynamic Routing in MoE ModelsCode2
InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction FeaturesCode2
GotenNet: Rethinking Efficient 3D Equivariant Graph Neural NetworksCode2
Latent Modulated Function for Computational Optimal Continuous Image RepresentationCode2
SparseLLM: Towards Global Pruning for Pre-trained Language ModelsCode2
LEGNet: Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object DetectionCode2
Accelerating Direct Preference Optimization with Prefix SharingCode2
LHU-Net: A Light Hybrid U-Net for Cost-Efficient, High-Performance Volumetric Medical Image SegmentationCode2
BiFormer: Vision Transformer with Bi-Level Routing AttentionCode2
A Simple Baseline for Efficient Hand Mesh ReconstructionCode2
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV CacheCode2
Balancing LoRA Performance and Efficiency with Simple Shard SharingCode2
A Survey on Diffusion Models for Anomaly DetectionCode2
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-MeshCode2
An Unforgeable Publicly Verifiable Watermark for Large Language ModelsCode2
FuXi Weather: A data-to-forecast machine learning system for global weatherCode2
Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-ResolutionCode2
Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMsCode2
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language ModelsCode2
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive SurveyCode2
Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary DomainsCode2
MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation ModelsCode2
Grappa -- A Machine Learned Molecular Mechanics Force FieldCode2
MultiBooth: Towards Generating All Your Concepts in an Image from TextCode2
Fast-SNARF: A Fast Deformer for Articulated Neural FieldsCode2
FastBlend: a Powerful Model-Free Toolkit Making Video Stylization EasierCode2
Fast and Accurate Blind Flexible DockingCode2
Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning ModelsCode2
Fast Adversarial Attacks on Language Models In One GPU MinuteCode2
Outlier-robust Kalman Filtering through Generalised BayesCode2
Fast FullSubNet: Accelerate Full-band and Sub-band Fusion Model for Single-channel Speech EnhancementCode2
Parameter-Inverted Image Pyramid NetworksCode2
FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow MatchingCode2
Emulating Self-attention with Convolution for Efficient Image Super-ResolutionCode2
AlphaNet: Scaling Up Local-frame-based Atomistic Interatomic PotentialCode2
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular FusionCode2
Enhancing Autonomous Driving Systems with On-Board Deployed Large Language ModelsCode2
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge DistillationCode2
Re-thinking Temporal Search for Long-Form Video UnderstandingCode2
Retinexmamba: Retinex-based Mamba for Low-light Image EnhancementCode2
Data-Driven Parametrization of Molecular Mechanics Force Fields for Expansive Chemical Space CoverageCode2
A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint SpaceCode2
Show:102550
← PrevPage 4 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified