SOTAVerified

GPU

Papers

Showing 14261450 of 5629 papers

TitleStatusHype
Searching Priors Makes Text-to-Video Synthesis Better0
A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection0
Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate ControlCode2
Scalable MatMul-free Language ModelingCode7
Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal LearningCode1
A Study of Optimizations for Fine-tuning Large Language Models0
Speeding up Policy Simulation in Supply Chain RL0
Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image GenerationCode4
LlamaCare: A Large Medical Language Model for Enhancing Healthcare Knowledge SharingCode1
SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLMCode2
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM TrainingCode1
GPU-Accelerated Rule Evaluation and Evolution0
OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models0
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models0
CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework0
Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-FlowCode2
ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video GenerationCode2
RGFN: Synthesizable Molecular Generation Using GFlowNetsCode1
Multi-Objective Neural Architecture Search by Learning Search Space Partitions0
AudioLCM: Text-to-Audio Generation with Latent Consistency ModelsCode5
Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank0
μLO: Compute-Efficient Meta-Generalization of Learned OptimizersCode1
S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs0
MotionFollower: Editing Video Motion via Lightweight Score-Guided DiffusionCode3
Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback0
Show:102550
← PrevPage 58 of 226Next →

No leaderboard results yet.