view article Article 180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers tarekziade • 4 days ago • 31
Direct3D-V3: Latent-Free Diffusion Transformers in the Native Voxel Domain Paper • 2611.26511 • Published 3 days ago • 4
A CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained Weights Paper • 2611.26450 • Published 3 days ago • 4
view article Article Harness adapters: Safe RL for efficient agentic development harness-hub • 15 days ago • 129
Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports Paper • 2610.31158 • Published about 1 month ago • 20
Persian-Phi: Efficient Cross-Lingual Adaptation of Compact LLMs via Curriculum Learning Paper • 2512.07454 • Published Dec 8, 2025 • 1
view article Article VideoMamba: State Space Model for Efficient Video Understanding vladbogo • Mar 16, 2024 • 3
USAD: Universal Speech and Audio Representation via Distillation Paper • 2506.18843 • Published Jun 23, 2025 • 13
view article Article Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model mikelabs • Nov 18, 2024 • 3