arXiv subjects

Baqiao Liu

Publications and source records attributed to Baqiao Liu.

4 recordsLinked to original sources

arXiv2026

VIVECaption: A Split Approach to Caption Quality Improvement

Caption quality has emerged as a critical bottleneck in training high-quality text-to-image (T2I) and text-to-video (T2V) generative models. While visual language models (VLMs) are commonly deployed to generate captions from visual data, they suffer from hallucinations, poor compositional reasoning, and limited fine-grained understanding, resulting in misaligned image-caption pairs that degrade downstream model performance. This technical report introduces VIVECaption, a systematic two-sided approach to caption quality improvement. We first establish a comprehensive taxonomy of caption evaluation metrics, distinguishing between "universal" and "instance-grounded" metrics, with the ultimate goal of showcasing the use-cases and tradeoffs between different caption quality metrics. We then use this language to describe our two-sided approach to caption quality improvement: (1) a gold-standard dataset creation methodology using stratified sampling and (2) a model alignment strategy encompassing context alignment and parameter-level finetuning using SFT. We demonstrate our methodology on open-source models, focusing on structured caption formats that enable better parsing and downstream utilization. We ultimately show that using a finetuned character detection model in an image captioning pipeline significantly improves holistic image-caption alignment quality. Our work addresses the growing need for high-quality "vegan" training data in enterprise AI development, providing practical solutions for teams seeking to improve caption-image alignment without relying on potentially copyright-protected web-scraped content.

cs.CV↗

arXiv2024

HARIVO: Harnessing Text-to-Image Models for Video Generation

We present a method to create diffusion-based video models from pretrained Text-to-Image (T2I) models. Recently, AnimateDiff proposed freezing the T2I model while only training temporal layers. We advance this method by proposing a unique architecture, incorporating a mapping network and frame-wise tokens, tailored for video generation while maintaining the diversity and creativity of the original T2I model. Key innovations include novel loss functions for temporal smoothness and a mitigating gradient sampling technique, ensuring realistic and temporally consistent video generation despite limited public video data. We have successfully integrated video-specific inductive biases into the architecture and loss functions. Our method, built on the frozen StableDiffusion model, simplifies training processes and allows for seamless integration with off-the-shelf models like ControlNet and DreamBooth. project page: https://kwonminki.github.io/HARIVO

cs.CV↗

arXiv2023

Well-Connected Communities in Real-World and Synthetic Networks

Integral to the problem of detecting communities through graph clustering is the expectation that they are "well connected". In this respect, we examine five different community detection approaches optimizing different criteria: the Leiden algorithm optimizing the Constant Potts Model, the Leiden algorithm optimizing modularity, Iterative K-Core Clustering (IKC), Infomap, and Markov Clustering (MCL). Surprisingly, all these methods produce, to varying extents, communities that fail even a mild requirement for well connectedness. To remediate clusters that are not well connected, we have developed the "Connectivity Modifier" (CM), which, at the cost of coverage, iteratively removes small edge cuts and re-clusters until all communities produced are well connected. Results from real-world and synthetic networks illustrate a tradeoff users make between well connected clusters and coverage, and raise questions about the "clusterability" of networks and models of community structure.

cs.SI↗

arXiv2022

AOC; Assembling Overlapping Communities

Through discovery of meso-scale structures, community detection methods contribute to the understanding of complex networks. Many community finding methods, however, rely on disjoint clustering techniques, in which node membership is restricted to one community or cluster. This strict requirement limits the ability to inclusively describe communities since some nodes may reasonably be assigned to many communities. We have previously reported Iterative K-core Clustering (IKC), a scalable and modular pipeline that discovers disjoint research communities from the scientific literature. We now present Assembling Overlapping Clusters (AOC), a complementary meta-method for overlapping communities as an option that addresses the disjoint clustering problem. We present findings from the use of AOC on a network of over 13 million nodes that captures recent research in the very rapidly growing field of extracellular vesicles in biology.

cs.SI↗