Entities · Locations
NVIDIA
12 articles tagged with this entity.
-
FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
-
An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU
-
OpenAI unveils its first custom chip, built by Broadcom
-
Introducing the FFASR Leaderboard: Benchmarking ASR in the Real World
-
Mixed-Precision Communication-Avoiding SGD for Generalized Linear Models on GPUs
-
MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs
-
DYNA-PRUNER: Input-Adaptive Data-Model Co-Pruning for Efficient and Scalable Spatio-Temporal Media Prediction
-
YOLO-AMC: An Improved YOLO Architecture with Attention Mechanisms for Building Crack Detection
-
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
-
Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)
-
MVSegNet: A Lightweight Boundary-Aware Network for Fetal Lateral Ventricle Segmentation and Atrial Width Estimation in Prenatal Ultrasound
-
Introducing the Third Generation of Apple’s Foundation Models