Issue 2026-11-12 · Industry · 开源 · 研究 · 模型发布
Hugging Face releases fine-tuning guide for 3D model TRELLIS.2

Hugging Face released fine-tuning scripts and containers for TRELLIS.2 that run locally or on Hugging Face Jobs. On 188 GSO footwear samples, the pretrained model often got shoe soles wrong, and LoRA fine-tuning was tested to improve that detail accuracy.
Read original ↗- Opinion: AI Has Crossed a Line and Should Be Regulated Like Banks
- Open-source inside-llm visualizes LLM internals and quantization gaps
- Perplexity releases Decider v1.3 decision models
- Hugging Face tutorial builds robot pick-and-place simulation with SimReady assets
- XYBench benchmark tests whether AI assistants correct users' mistaken assumptions