A hybrid ANN-SNN pipeline uses pretrained EfficientNet encoders and converts their activations to spike trains via rate-coding. The system trains a CoLaNET spiking classifier with local plasticity rules, achieving 99.09% accuracy on ImageNet's 64-class benchmark, matching conventional deep networks.
arxiv
arXiv cs.AI
·
51d ago
·
research
Hybrid ANN-SNN Pipeline with Local Plasticity
from English
Importance 2/3
New harness with differentiators
arXiv cs.AI
Allen AI
Hugging Face
NVIDIA
Hardware & chips
Image generation
Training methods
Related articles
arxiv
arXiv cs.LG
·
51d ago
Repurposing Speech Classifier for Diffusion-Based Generation
A pretrained speech classifier is repurposed as a backbone for guided diffusion-based speech generation. By attaching a lightweight subnetwork and training it under denoising score matching, the approach achieves high speech quality with reduced memory and computational cost, using a single model instead of two separately trained components.
arxiv
arXiv cs.AI
·
51d ago
·
1 view
Learnable Global Merging for Variable-Length Tokenization in Diffusion Transformers
A novel variable-length tokenizer uses learnable global merging to enable cross-length representation alignment in diffusion models. This data-independent approach overcomes position-dependent semantics and improves the quality-compute trade-off on ImageNet 256×25-6 generation compared to prior methods.
arxiv
arXiv cs.AI
·
17d ago
·
4 views
SLAI T-Rex enables full-parameter post-training of DeepSeek-V4 on Ascend SuperPOD
SLAI introduces T-Rex, an end-to-end optimization framework for the full-parameter post-training of trillion-parameter-scale MoE models on Ascend NPU SuperPOD. Using the DeepSeek-V4 model family as the target workload, the system addresses memory pressure and communication overhead through hierarchical parallelism and kernel execution optimizations.
arxiv
arXiv cs.CL
·
18d ago
·
1 view
SLAI T-Rex enables full-parameter post-training of DeepSeek-V4 on Ascend SuperPOD
SLAI introduces T-Rex, an end-to-end optimization framework for the full-parameter post-training of trillion-parameter-scale MoE models on Ascend NPU SuperPOD. Using the DeepSeek-V4 model family as the target workload, the system addresses memory pressure and communication overhead through hierarchical parallelism and kernel execution optimizations.
lab
Hugging Face Blog
·
23d ago
·
5 views
NVIDIA NeMo Automodel enables distributed diffusion model fine-tuning with Hugging Face Diffusers
NVIDIA and Hugging Face have integrated NVIDIA NeMo Automodel with the 🤗 Diffusers library to provide production-grade, distributed training for open-source diffusion models. This collaboration allows users to fine-tune any Diffusers-format model on the Hugging Face Hub without requiring checkpoint conversion or model code rewrites.