Feng Hu

Jay Zhangjie Wu, Xiuyu Li, Difei Gao et al. · berkeley

Humans watch more than a billion hours of video per day. Most of this video was edited manually, which is a tedious process. However, AI-enabled video-generation and video-editing is on the rise. Building on text-to-image models like Stable Diffusion and Imagen, generative AI has improved dramatically on video tasks. But it's hard to evaluate progress in these video tasks because there is no standard benchmark. So, we propose a new dataset for text-guided video editing (TGVE), and we run a competition at CVPR to evaluate models on our TGVE dataset. In this paper we present a retrospective on the competition and describe the winning method. The competition dataset is available at https://sites.google.com/view/loveucvpr23/track4.

Rui He, Yuanxi Sun, Youzeng Li et al.

Generic Event Boundary Detection (GEBD) tasks aim at detecting generic, taxonomy-free event boundaries that segment a whole video into chunks. In this paper, we apply Masked Autoencoders to improve algorithm performance on the GEBD tasks. Our approach mainly adopted the ensemble of Masked Autoencoders fine-tuned on the GEBD task as a self-supervised learner with other base models. Moreover, we also use a semi-supervised pseudo-label method to take full advantage of the abundant unlabeled Kinetics-400 data while training. In addition, we propose a soft-label method to partially balance the positive and negative samples and alleviate the problem of ambiguous labeling in this task. Lastly, a tricky segmentation alignment policy is implemented to refine boundaries predicted by our models to more accurate locations. With our approach, we achieved 85.94% on the F1-score on the Kinetics-GEBD test set, which improved the F1-score by 2.31% compared to the winner of the 2021 Kinetics-GEBD Challenge. Our code is available at https://github.com/ContentAndMaterialPortrait/MAE-GEBD.

Yuanxi Sun, Rui He, Youzeng Li et al.

The Generic Event Boundary Detection (GEBD) task aims to build a model for segmenting videos into segments by detecting general event boundaries applicable to various classes. In this paper, based on last year's MAE-GEBD method, we have improved our model performance on the GEBD task by adjusting the data processing strategy and loss function. Based on last year's approach, we extended the application of pseudo-label to a larger dataset and made many experimental attempts. In addition, we applied focal loss to concentrate more on difficult samples and improved our model performance. Finally, we improved the segmentation alignment strategy used last year, and dynamically adjusted the segmentation alignment method according to the boundary density and duration of the video, so that our model can be more flexible and fully applicable in different situations. With our method, we achieve an F1 score of 86.03% on the Kinetics-GEBD test set, which is a 0.09% improvement in the F1 score compared to our 2022 Kinetics-GEBD method.

Alan Wake, Bei Chen, C. X. Lv et al. · tsinghua

This technical report presents Yi-Lightning, our latest flagship large language model (LLM). It achieves exceptional performance, ranking 6th overall on Chatbot Arena, with particularly strong results (2nd to 4th place) in specialized categories including Chinese, Math, Coding, and Hard Prompts. Yi-Lightning leverages an enhanced Mixture-of-Experts (MoE) architecture, featuring advanced expert segmentation and routing mechanisms coupled with optimized KV-caching techniques. Our development process encompasses comprehensive pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF), where we devise deliberate strategies for multi-stage training, synthetic data construction, and reward modeling. Furthermore, we implement RAISE (Responsible AI Safety Engine), a four-component framework to address safety issues across pre-training, post-training, and serving phases. Empowered by our scalable super-computing infrastructure, all these innovations substantially reduce training, deployment and inference costs while maintaining high-performance standards. With further evaluations on public academic benchmarks, Yi-Lightning demonstrates competitive performance against top-tier LLMs, while we observe a notable disparity between traditional, static benchmark results and real-world, dynamic human preferences. This observation prompts a critical reassessment of conventional benchmarks' utility in guiding the development of more intelligent and powerful AI systems for practical applications. Yi-Lightning is now available through our developer platform at https://platform.lingyiwanwu.com.