ELLIS to host "Reflections on XAI" session in Paris before NeurIPS
NicoloCB · x · 2026-11-06
The ELLIS UnConference 2026 will hold a "Reflections on XAI" session on Dec 8 in Paris (before NeurIPS), with a call for posters open. Speakers including Timo Freiesleben and Hadas Orgad will critically assess a decade of explainable AI: whether the field has become insular, if it keeps pace with foundation models (CoT, mechanistic interpretability), where real successes are, and where the next 5–10 years of effort should go — given XAI is now deployed in high-stakes domains and even legally required.
More from Research
- SynthFaces: Arc2Face diffusion plus flow matching build balanced synthetic face dataset — Sergey Karpukhin · 2026-11-06
- Stable AI proposes DPDM: frozen LLM representations plus shared predictor boost agent decisions — stable-ai · 2026-11-06
- Toby Ord: before RLVR, big pre-trains drove most sudden capability jumps — tobyordoxford · 2026-11-06
- DePue: the cited papers each describe very different phenomena — willdepue · 2026-11-06
- OpenAI researcher: 800M-model intuitions are useless for GPT-6-scale training — willdepue · 2026-11-06
- Lightwheel and Synopsys bring CAE-grade contact physics into robot simulation — lukas_m_ziegler · 2026-11-06