6 papers
Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning
Changhui Sun, Lanbo Liu, Hang Lei +11
On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical gains and can…
Rewarding Creativity: A Human-Aligned Generative Reward Model for Reinforcement Learning in Storytelling
Zhaoyan Li, Hang Lei, Yujia Wang +3
While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution bu…
Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
Kaiwen Zheng, Yuji Wang, Qianli Ma +7
Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to larg…
FrameBridge: Improving Image-to-Video Generation with Bridge Models
Yuji Wang, Zehua Chen, Xiaoyu Chen +3
Diffusion models have achieved remarkable progress on image-to-video (I2V) generation, while their noise-to-data generation process is inherently mismatched with this task, which m…
QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning
Jiun-Man Chen, Yu-Hsuan Chao, Yu-Jie Wang +3
Transformer-based models have gained widespread popularity in both the computer vision (CV) and natural language processing (NLP) fields. However, significant challenges arise duri…
Fight Back Against Jailbreaking via Prompt Adversarial Tuning
Yichuan Mo, Yuji Wang, Zeming Wei +1
While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies h…