Running on CPU Upgrade 754 The Ultimate MoE Training Handbook 🧩 754 A hands-on guide to training Mixture-of-Experts models
HYDRA: Unifying Multi-modal Generation and Understanding via Representation-Harmonized Tokenization Paper • 2603.15228 • Published Mar 17 • 2
FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution Paper • 2609.36651 • Published Sep 29 • 20
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published Sep 17 • 209
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers Paper • 2606.13289 • Published Jun 11 • 31
view article Article NEO-unify: Building Native Multimodal Unified Models End to End sensenova • Mar 5 • 181
Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking Paper • 2505.12667 • Published May 19, 2025 • 9
SpikingBrain Technical Report: Spiking Brain-inspired Large Models Paper • 2509.05276 • Published Sep 5, 2025 • 5
FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO Paper • 2503.09158 • Published Mar 12, 2025 • 2
Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images Paper • 2511.07222 • Published Nov 10, 2025 • 1
Universal Image Restoration Pre-training via Masked Degradation Classification Paper • 2510.13282 • Published Oct 15, 2025 • 11
Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking Paper • 2505.12667 • Published May 19, 2025 • 9