Researchers propose DynaKV, a post-training framework that dynamically allocates compression rates to individual tokens based on semantic importance. The method achieves 94% baseline performance while reducing KV cache to just 6% of original size on LongBench benchmarks.
A new study on Qwen2.5-VL reveals reinforcement fine-tuning (RFT) significantly outperforms supervised fine-tuning (SFT) at preserving a model's existing knowledge during post-training adaptation. While SFT enables faster task learning, it causes catastrophic forgetting; RFT learns more slowly but maintains prior knowledge by reinforcing samples naturally aligned with the base model's probability landscape.
Researchers introduce SOLACE, a post-training framework that replaces external reward models with an internal self-confidence signal derived from how accurately a text-to-image model recovers injected noise. The method enables fully unsupervised optimization and shows measurable improvements in compositional generation, text rendering, and text-image alignment.