2 papers
cs.AI2026
From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos
Yifeng Luo, Yupeng Li, Liang Lan +1
Recent text-to-video (T2V) generation models enable fake news videos to be synthesized from scratch, shifting the threat beyond cheap fakes assembled from existing footage. Such ne…
cs.LG2026
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Zhilin Huang, Hang Gao, Ziqiang Dong +6
Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes…