Researcher presenting Latent Policy States in Reasoning Models at COLM this week
hunarbatra · x · 2026-10-06
- hunarbatra will present work on Latent Policy States in Reasoning Models at COLM this week.
- Topics of interest include actionable interpretability, AI control, reward hacking, meta models, safety post-training and evals; the author invites attendees to chat.
More from Research
- SLIM paper at COLM: design principles for long-horizon agentic search systems — xiye_nlp · 2026-10-06
- The Nobel optogenetics drama: forgotten inventor Zhuo-Hua Pan had the stronger claim — _onionesque · 2026-10-06
- COLM 2026: PhD students in synthetic supervision, deep info seeking hit job market — tongshuangwu · 2026-10-06
- Kyutai's 100M PocketTTS trains with Kaiming He's Drifting, WER under 1% — serrjoa · 2026-10-06
- Google's SHIFT Builds Per-Query Multi-Agent Harnesses, Beats 17 Baselines by 7.2 Points — google · 2026-10-06
- Diagnosing LLM Math Reasoning: Discovery Is the Bottleneck, and It's Fixable — TexasAMUniversity · 2026-10-06