SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 5629 papers

TitleStatusHype
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise RewardCode3
Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM EvaluationCode1
From Hand-Crafted Metrics to Evolved Training-Free Performance Predictors for Neural Architecture Search via Genetic Programming—0
Flash Invariant Point AttentionCode1
HessFormer: Hessians at Foundation Scale—0
Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity—0
Entropy-Driven Genetic Optimization for Deep-Feature-Guided Low-Light Image EnhancementCode0
Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training—0
Group-in-Group Policy Optimization for LLM Agent TrainingCode5
Accelerating Visual-Policy Learning through Parallel Differentiable SimulationCode4
VRSplat: Fast and Robust Gaussian Splatting for Virtual RealityCode2
SpecOffload: Unlocking Latent GPU Capacity for LLM Inference on Resource-Constrained DevicesCode1
Single-shot prediction of parametric partial differential equations—0
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image AnalysisCode7
FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUsCode1
AI Accelerators for Large Language Model In-ference: Architecture Analysis and Scaling Strategies—0
Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles—0
Generative Molecular Design with Steerable and Granular Synthesizability ControlCode0
SLAG: Scalable Language-Augmented Gaussian Splatting—0
On the Cost and Benefits of Training Context with Utterance or Full Conversation Training: A Comparative Stud—0
Fused3S: Fast Sparse Attention on Tensor CoresCode0
OnPrem.LLM: A Privacy-Conscious Document Intelligence ToolkitCode4
Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains—0
Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption—0
L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers—0
Matrix Is All You Need—0
Streaming Krylov-Accelerated Stochastic Gradient Descent—0
JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 MinutesCode1
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration—0
Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference—0
FloE: On-the-Fly MoE Inference on Memory-constrained GPU—0
Fast Differentiable Modal Simulation of Non-linear Strings, Membranes, and PlatesCode1
Boosting Performance on ARC is a Matter of Perspective—0
UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes—0
Steepest Descent Density Control for Compact 3D Gaussian Splatting—0
Leveraging Simultaneous Usage of Edge GPU Hardware Engines for Video Face Detection and Recognition—0
FastMap: Revisiting Dense and Scalable Structure from MotionCode3
Plexus: Taming Billion-edge Graphs with 3D Parallel GNN Training—0
Edge-GPU Based Face Tracking for Face Detection and Recognition Acceleration—0
Supporting renewable energy planning and operation with data-driven high-resolution ensemble weather forecast—0
LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders—0
Prism: Unleashing GPU Sharing for Cost-Efficient Multi-LLM Serving—0
Can Large Language Models Predict Parallel Code Performance?—0
NBF at SemEval-2025 Task 5: Light-Burst Attention Enhanced System for Multilingual Subject Recommendation—0
Anant-Net: Breaking the Curse of Dimensionality with Scalable and Interpretable Neural Surrogate for High-Dimensional PDEs—0
AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active LearningCode0
RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference—0
Quantitative Analysis of Performance Drop in DeepSeek Model QuantizationCode0
A UNet Model for Accelerated Preprocessing of CRISM Hyperspectral Data for Mineral Identification on Mars—0
Sparfels: Fast Reconstruction from Sparse Unposed Imagery—0
Show:102550
← PrevPage 5 of 113Next →

No leaderboard results yet.