First InterpScience workshop on LLM interpretability opens for NeurIPS 2026
sivareddyg · x · 2026-08-04
Researchers are organizing the first InterpScience workshop at NeurIPS 2026 in Sydney, focused on building a more rigorous scientific foundation for LLM interpretability.
The call for papers is open, with submissions due on Aug. 28. The organizers frame the workshop as a way to connect interpretability with complementary systems-level views across the sciences.
More from Research
- OpenAI Reveals How It Built Its Realtime Voice AI System in Just 6 Months — borowcy · 2026-08-04
- Browser MCP scanner flags shell exec, secrets, and unsafe deserialization — KookyTax5493 · 2026-08-04
- AI breakthroughs in math are becoming the benchmark that matters most — Dr_Singularity · 2026-08-04
- Text conditioning scaling paper adds structured prompts to improve visual generation — shangbinfeng · 2026-08-04
- The same model can behave very differently because the harness changes the protocol — remilouf · 2026-08-04
- David Adelani says African languages still need Africa-centric language models — davlanade · 2026-08-04