BMVA symposium on computer vision interpretability opens CFP, London, Jan 2027
HildeKuehne · x · 2026-11-06
The British Machine Vision Association (BMVA) will host a one-day Symposium on Interpretability in computer vision on January 13, 2027 in London, with a call for talks and posters deadline of November 26, 2026; both published and ongoing work are welcome.
- Invited speakers: Oisin Mac Aodha (University of Edinburgh), Elisa Ricci (Trento University), Stephan Alaniz (Telecom Paris)
- Topics include mechanistic interpretability and circuit discovery, post-hoc post-training analysis, interpretable-by-design methods, language-based and multimodal techniques, and white-box models
- Chaired by Davide Moltisanti (University of Bath) and Michael Wray (University of Bristol)
The event targets both academia and industry, aiming to spotlight recent CV interpretability work and spur discussion.
More from Research
- Study: Epigenetic aging accelerated in kids and adults during the Covid pandemic — EricTopol · 2026-11-06
- Memorilla adds latent semantic memory to LLMs, positioned beyond RAG — StanfordAILab · 2026-11-06
- Team finds models trained for collaboration match frontier coding without explicit coding training — gharik · 2026-11-06
- NVIDIA open-sources Dory1.0-4B: looped latent-recurrent LLM beats Qwen3.5-9B on 12 benchmarks — ChengleiSi · 2026-11-06
- Rohit Krishnan maps "AGI institutions" experiments: 11 strong matches, zero at national scale — soumitrashukla9 · 2026-11-06
- Anneal V1 Core released: CPU-native low-parameter state-space architecture under CC0 — True-Beach1906 · 2026-11-06