Top pick  ·  LLMs & Language Models

The Surprising Effectiveness of Deleting Weights in LLM Post-Training

Zeroing less than 0.05% of LLM weights via a learned binary mask matches full fine‑tuning across several post‑training tasks.

Why it matters: Developers can adapt large models with negligible storage and reduced catastrophic forgetting.

Read the breakdown →  Code

Trending  ·  Generative AI & Diffusion

Few-Step Streaming Video Generation via Condition Shifting

APEX removes the fake-score network for few-step streaming video generation by shifting conditions within the generator.

Why it matters: Builders can generate high‑quality streaming video faster and with less GPU memory.

Read the breakdown →