Researcher urges the community to stop using PickScore as a reward model, recommends HPSv3 instead
gowthami_s · x · 2026-10-21
Researcher soumitrashukla9 called on the community to stop using PickScore as a human-preference reward model, calling it a very bad RM and saying she won't read papers that still use it. She recommends HPSv3 and newer open-source alternatives for image-preference evaluation — a practical pitfall warning for text-to-image eval and RLHF researchers.
More from Models
- OpenAI API adds 12-hour prompt caching option alongside 30-minute default — OpenAIDevs · 2026-10-21
- antirez on model upgrades: 4.0→4.1 knowledge transfers unless attention changes — teortaxesTex · 2026-10-21
- DeepSeek reportedly profits at $0.15/$0.60 off-peak pricing — the price Western labs must beat — arthurcolle · 2026-10-21
- SpecterOps Researchers Show Adversarial ML Evading EDR, LLMs Speeding Reverse Engineering — dyn___ · 2026-10-21
- AWS fine-tunes GPT-OSS-20B for multilingual reasoning: base model reasoned in French 0% of the time — AWS ML Blog · 2026-10-21
- Riemann-bench: frontier models jump from under 5% to over 70% in six months, NS and UGC solved — echen · 2026-10-21