🏢 NVIDIA

FFN Fusion: Parallelizing sequential computation in large language models for significant speedups!

Cosmos-Transfer1: An adaptable conditional world generation model using multimodal control.

Cosmos-Reason1: Physical AI models that reason and act in the real world, bridging the gap between perception and embodied decision-making.

SANA-Sprint: An efficient diffusion model for ultra-fast text-to-image generation with continuous-time consistency distillation, achieving state-of-the-art performance in speed and quality.

DIFIX3D+ improves 3D reconstructions by reducing artifacts via single-step diffusion models, enhancing novel-view synthesis quality and consistency.

f-distill: One-step diffusion models through f-divergence minimization, outperforming reverse-KL with better mode coverage and lower variance.

V2V-LLM leverages multi-modal LLMs for safer cooperative autonomous driving by fusing perception data from multiple vehicles, answering driving-related questions, and improving trajectory planning.

VLSI: Verbalized Layers-to-Interactions efficiently transfers knowledge from large to small VLMs using layer-wise natural language distillation, achieving significant performance gains without scaling…

Puzzle: a novel framework accelerates large language model inference by using neural architecture search and knowledge distillation, achieving a 2.17x speedup on a single GPU while preserving 98.4% ac…

Star Attention: 11x faster LLM inference on long sequences with 95-100% accuracy!

Hymba: Hybrid-head architecture boosts small language model performance by 11.67x cache size reduction and 3.49x throughput, surpassing existing models.