Hy-Nomas: open-weight 8B interactive world model with open benchmark

Shows how to keep a video model's actions scoped to their time window across turns, with open weights, a LoRA adaptation recipe and a reproducible multi-turn benchmark. Useful if you build on or evaluate world models.

• attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
• distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
• open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
• LoRA — A cheap way to fine-tune a model by training a small add-on layer instead of changing all of the model's weights.

• articleTencent open-sources Hy-SimulMT, a streaming Chinese-English interpreter
• articleTencent open-sources Hy-Nomas interactive video world model
• articleWorkForge scales verifiable real-workspace environments for work agents
• articleTencent open-sources Hy Memory 2.0 with RL-trained memory writer

Checking sign-in…

Loading comments…