SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 501–550 of 5629 papers

TitleStatusHype
SparseTransX: Efficient Training of Translation-Based Knowledge Graph Embeddings Using Sparse Matrix OperationsCode0
Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space—0
LettuceDetect: A Hallucination Detection Framework for RAG ApplicationsCode4
A Split-Window Transformer for Multi-Model Sequence Spammer Detection using Multi-Model Variational Autoencoder—0
SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place RecognitionCode3
Fine-Tuning Qwen 2.5 3B for Realistic Movie Dialogue Generation—0
A Universal Framework for Compressing Embeddings in CTR PredictionCode0
Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference—0
KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio GenerationCode2
Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective—0
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton OperatorsCode2
Towards Efficient Automatic Self-Pruning of Large Language Models—0
Distributed U-net model and Image Segmentation for Lung Cancer Detection—0
Dynamic Low-Rank Sparse Adaptation for Large Language ModelsCode1
Exploring RWKV for Sentence Embeddings: Layer-wise Analysis and Baseline Comparison for Semantic SimilarityCode0
Building reliable sim driving agents by scaling self-playCode4
ParallelComp: Parallel Long-Context Compressor for Length Extrapolation—0
Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence ModelingCode0
Learning conformational ensembles of proteins based on backbone geometry—0
FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference—0
Slamming: Training a Speech Language Model on One GPU in a DayCode3
LSR-Adapt: Ultra-Efficient Parameter Tuning with Matrix Low Separation Rank Kernel Adaptation—0
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression—0
SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin—0
MEX: Memory-efficient Approach to Referring Multi-Object Tracking—0
Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language ModelsCode2
Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference—0
Astra: Efficient and Money-saving Automatic Parallel Strategies Search on Heterogeneous GPUs—0
GPU-Friendly Laplacian Texture Blending—0
YOLOv12: Attention-Centric Real-Time Object DetectorsCode7
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
An Experimental Study of SOTA LiDAR Segmentation Models—0
Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear DistillationCode2
BaKlaVa -- Budgeted Allocation of KV cache for Long-context Inference—0
GPU Memory Usage Optimization for Backward Propagation in Deep Network Training—0
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic EmbeddingsCode0
Myna: Masking-Based Contrastive Learning of Musical RepresentationsCode1
Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer—0
Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer GateCode0
AdaSplash: Adaptive Sparse Flash AttentionCode1
Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption—0
Massively Scaling Explicit Policy-conditioned Value Functions—0
Real-time Neural Rendering of LiDAR Point Clouds—0
GPU-accelerated Multi-relational Parallel Graph Retrieval for Web-scale Recommendations—0
JExplore: Design Space Exploration Tool for Nvidia Jetson BoardsCode0
TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules—0
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
An Efficient Large Recommendation Model: Towards a Resource-Optimal Scaling Law—0
KernelBench: Can LLMs Write Efficient GPU Kernels?Code4
Efficient solution validation of constraint satisfaction problems on neuromorphic hardware: the case of Sudoku puzzlesCode0
Show:102550
← PrevPage 11 of 113Next →

No leaderboard results yet.