Hanwen Shen

Hanwen Shen, Jiajie Lu, Yupeng Cao et al.

Recent advances in AI-generated video have shown strong performance on \emph{text-to-video} tasks, particularly for short clips depicting a single scene. However, current models struggle to generate longer videos with coherent scene transitions, primarily because they cannot infer when a transition is needed from the prompt. Most open-source models are trained on datasets consisting of single-scene video clips, which limits their capacity to learn and respond to prompts requiring multiple scenes. Developing scene transition awareness is essential for multi-scene generation, as it allows models to identify and segment videos into distinct clips by accurately detecting transitions. To address this, we propose the \textbf{Transition-Aware Video} (TAV) dataset, which consists of preprocessed video clips with multiple scene transitions. Our experiment shows that post-training on the \textbf{TAV} dataset improves prompt-based scene transition understanding, narrows the gap between required and generated scenes, and maintains image quality.

Hanwen Shen, Ting Ying, Jiajie Lu et al.

Although debiased LLMs perform well on known bias patterns, they often fail to generalize to unfamiliar bias prompts, producing toxic outputs. We first validate that such high-bias prompts constitute a \emph{distribution shift} via OOD detection, and show static models degrade under this shift. To adapt on-the-fly, we propose \textbf{CAP-TTA}, a test-time adaptation framework that performs context-aware LoRA updates only when the bias-risk \emph{trigger} exceeds a threshold, using a precomputed diagonal \emph{preconditioner} for fast and stable updates. Across toxic-prompt settings and benchmarks, CAP-TTA reduces bias (confirmed by human evaluation) while achieving much lower update latency than AdamW/SGD; it also mitigates catastrophic forgetting by significantly improving narrative fluency over SOTA debiasing baseline while maintaining comparable debiasing effectiveness.

Hanwen Shen, Ting Ying

A two stage novel generation framework (outline -> section outline -> manuscript) is widely used in long novel generation,(e.g., \textsc{DOME}, \textsc{Plan\&Write}, \textsc{Long Writer}), but study of such framework in ultra long novel(>1M words) reconstruction is little. Building on recent text compression methods (\textsc{LLMZip}, \textsc{LLM2Vec}), we conduct an information-theoretic analysis to quantify semantic distortion under different compression-expansion ratios. We examine how outline length affects information preservation. Experiments on ultra-long novels show that the optimal compression-expansion ratio significantly reduces semantic distortion compared to other non-optimal compression-expansion ratio.