CFP: Interpretability for Discovery Workshop at NeurIPS 2026
begusgasper · x · 2026-08-21
Call for Papers for the "Interpretability for Discovery" workshop @NeurIPSConf 2026 in Atlanta. Deadline is Aug 29.
Looking for submissions on:
- Methods for using interpretability to drive discovery in any field
- Case studies of using interpretability to discover/validate patterns and mechanisms in scientific models (including failure cases and negative results)
- Comparing interpretability to black-box approaches for extraction of model knowledge
- Position papers on where this can and can't work
Failure cases and negative results are welcome too!
More from Research
- Xiaohongshu's FireRedTTS3 Unifies Speech Generation and Editing, Tops Benchmarks — 机器之心 · 2026-08-21
- Tutorial: Training a local LLM on a new domain via continued pretraining — funJS · 2026-08-21
- Reviewing the Pearl vs. Imbens Causal Models Feud — soumitrashukla9 · 2026-08-21
- Fixing confident agents acting on bad retrieved context with hybrid search and self-checks — camerongreen95 · 2026-08-21
- Zhipu's SAO: single-rollout async RL trains stably for 1,000 steps, beats GRPO — teortaxesTex · 2026-08-21
- "An introduction to graph theory" available on ChapterPal with AI tutor — burkov · 2026-08-21