New Work Formalizes Continual Learning's Stability-Plasticity Trade-off via Probability Paths
hbouammar · x · 2026-09-25
A new continual learning paper led by Ahmed K Khamis formalizes the stability vs plasticity trade-off as solution paths in probability space between student and teacher distributions. Paper, code and checkpoints are all released openly.
More from Research
- DARLING, a paper fixing repetitive LLM outputs after post-training, accepted at NeurIPS — DanielKhashabi · 2026-09-25
- A 1978 logic puzzle book is catching chatbots that memorize instead of reason — JafarNajafov · 2026-09-25
- Dev reproduces zero-shot classifier benchmark to 4 decimals, loses to keyword rules — JhouHate · 2026-09-25
- AVIS paper accepted at NeurIPS 2026: jointly scaling visual context and reasoning per query — CSProfKGD · 2026-09-25
- ICLR hits 62,000 abstract submissions as NeurIPS decisions drop a day before deadline — yoavgo · 2026-09-25
- Weco preprint: agent self-improves its own software 7 times over 8 days, gains transfer to 4 benchmarks — VraserX · 2026-09-25