【Short Technical Report & Usage】NexteraBERT: Input-Dependent Gating Liquid Mixer and Length-Adaptive Attention for Fast, Long-Context Bidirectional Encoders RikkaBotan • about 1 hour ago
Awesome MiniMax H3 Max Prompts — Separating a reference collection from an evaluation VulcanFeynman • about 3 hours ago
What Is Pixel Canary? The Free Stealth AI Model That Ties GPT-6 Astra liliruli • about 4 hours ago • 1
JEV is blowing up. 13,000+ repos on GitHub — these 228 are the ones you actually need to see. karmen-beatapi • about 8 hours ago
From PDF and DOCX to LLM-Ready Markdown: Building a Better Document Pipeline dddffgassa • about 8 hours ago
Real-Time Talking Characters from a 22B Video Diffusion Model — on a Single 32 GB GPU, with Plain Diffusers UZUKI • about 9 hours ago
How to Make Videos with Claude Opus 5.5: A Deterministic Render Pipeline karmen-beatapi • 1 day ago • 2
OpenDecider: Open, Calibrated Decision Models That Beat Laya and Jev on Typed-Decisions manjunathshiva • 1 day ago
YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research espnet • 1 day ago • 18