Training Conditions for Subliminal Learning
AdtRaghunathan · x · 2026-07-09
This repost discusses the training conditions under which "subliminal learning" occurs. The author notes that while previous research suggested it doesn't happen during low-rank LoRA or FFT training, their work has identified new conditions where it does. This is research-oriented content, primarily offering deeper empirical exploration into the training conditions that trigger the subliminal learning phenomenon.
Related event: Subliminal Learning Hinges on Data Efficiency, Study Says(2 posts)→
More from Research
- GigaChat Audio targets long-form audio grounding with timestamps across 120-minute inputs — ai-sage · 2026-07-21
- Paper models Transformer components as stochastic geometry and tests five architectures — Zhihua Liang · 2026-07-21
- LTX 2.3 LoRA demo changes a video’s camera angle — CQDSN · 2026-07-21
- OpenForecaster uses daily news to improve language-model forecasting — Cohere_Labs · 2026-07-21
- Baseten study finds new facts in LLM weights are fragile unless trained from many restatements — alex_verem · 2026-07-21
- uv-scripts/ocr returns to the top of Hugging Face datasets with a JSON model picker — vanstriendaniel · 2026-07-21