DiScoFormer: One Transformer for Density and Score, Across Distributions⭐9

The DiScoFormer Transformer unifies density estimation and score functions across arbitrary distributions, enabling single-model generative AI without retrainin...

A Deep Reinforcement Learning (DRL)-Based Transformer Method for Solving the Open Shop Scheduling Problem⭐7

A Transformer model trained on small OSSP instances generalizes to 100x100 problems, rivaling heuristics with 12-15% optimality gaps.

Zyphra Releases Zamba2-VL: Hybrid Mamba2–Transformer Vision-Language Models Cut Time-to-First-Token by an Order of Magnitude⭐7

Zyphra launches Zamba2-VL, hybrid Mamba2-Transformer VLMs that cut time-to-first-token by 10x for faster real-time vision-language tasks.