Transformer-based multimodal models are widely used in industrial-scale recommendation, search, and advertising systems for content understanding and relevance ranking. Enhancing labeled training data quality and cross-modal fusion significantly improves model performance, influencing key metrics such as quality view rates and ad revenue. High-quality annotations are crucial for advancing content modeling, yet traditional statistical-based active learning (AL) methods face limitations: they struggle to detect overconfident misclassifications and are less effective in distinguishing semantically similar items in deep neural networks. Additionally, audio information plays an increasing role, especially in short-video platforms, yet most pre-trained multimodal architectures primarily focus on text and images. While training from scratch across all three modalities is possible, it sacrifices the benefits of leveraging existing pre-trained visual-language (VL) and audio models. To address these challenges, we propose kNN-based Latent Space Broadening (LSB) to enhance AL efficiency and Vision-Language Modeling with Audio Enhancement (VLMAE), a mid-fusion approach integrating audio into VL models. This system deployed in production systems, leading to significant business gains.

Negative feedback signals are crucial to guardrail content recommendations and improve user experience. When these signals are effectively integrated into recommendation systems, they play a vital role in preventing the promotion of harmful or undesirable content, thereby contributing to a healthier online environment. However, the challenges associated with negative signals are noteworthy. Due to the limited visibility of options for users to express negative feedback, these signals are often sparse compared to positive signals. This imbalance can lead to a skewed understanding of user preferences, resulting in recommendations that prioritize short-term engagement over long-term satisfaction. Moreover, an over-reliance on positive signals can create a filter bubble, where users are continuously exposed to content that aligns with their immediate preferences but may not be beneficial in the long run. This scenario can ultimately lead to user attrition as audiences become disillusioned with the quality of the content provided. Additionally, existing user signals frequently fail to meet specific customized requirements, such as understanding the underlying reasons for a user's likes or dislikes regarding a video. This lack of granularity hinders our ability to tailor content recommendations effectively, as we cannot identify the particular attributes of content that resonate with individual users.

The advanced processing and reasoning capabilities of multimodal large language models (MLLMs) have driven substantial progress in vision-language (VL) understanding tasks. However, while effective for tasks governed by straightforward logic, MLLMs often encounter challenges when reasoning over complex, interdependent logic structures. To address this limitation, we introduce \textit{AgentPS}, a novel framework that integrates Agentic Process Supervision into MLLMs via multi-round question answering during fine-tuning. \textit{AgentPS} demonstrates significant performance improvements over baseline MLLMs on proprietary TikTok datasets, due to its integration of process supervision and structured sequential reasoning. Furthermore, we show that replacing human-annotated labels with LLM-generated labels retains much of the performance gain, highlighting the framework's practical scalability in industrial applications. These results position \textit{AgentPS} as a highly effective and efficient architecture for multimodal classification tasks. Its adaptability and scalability, especially when enhanced by automated annotation generation, make it a powerful tool for handling large-scale, real-world challenges.

Recently, with the emergence of recent Multimodal Large Language Model (MLLM) technology, it has become possible to exploit its video understanding capability on different classification tasks. In practice, we face the difficulty of huge requirements for GPU resource if we need to deploy MLLMs online. In this paper, we propose COEF-VQ, a novel cascaded MLLM framework for better video quality understanding on TikTok. To this end, we first propose a MLLM fusing all visual, textual and audio signals, and then develop a cascade framework with a lightweight model as pre-filtering stage and MLLM as fine-consideration stage, significantly reducing the need for GPU resource, while retaining the performance demonstrated solely by MLLM. To demonstrate the effectiveness of COEF-VQ, we deployed this new framework onto the video management platform (VMP) at TikTok, and performed a series of detailed experiments on two in-house tasks related to video quality understanding. We show that COEF-VQ leads to substantial performance gains with limit resource consumption in these two tasks.

Deep convolutional neural networks (DCNNs) have recently demonstrated high-quality results in single-image super-resolution (SR). DCNNs often suffer from over-parametrization and large amounts of redundancy, which results in inefficient inference and high memory usage, preventing massive applications on mobile devices. As a way to significantly reduce model size and computation time, binarized neural network has only been shown to excel on semantic-level tasks such as image classification and recognition. However, little effort of network quantization has been spent on image enhancement tasks like SR, as network quantization is usually assumed to sacrifice pixel-level accuracy. In this work, we explore an network-binarization approach for SR tasks without sacrificing much reconstruction accuracy. To achieve this, we binarize the convolutional filters in only residual blocks, and adopt a learnable weight for each binary filter. We evaluate this idea on several state-of-the-art DCNN-based architectures, and show that binarized SR networks achieve comparable qualitative and quantitative results as their real-weight counterparts. Moreover, the proposed binarized strategy could help reduce model size by 80% when applying on SRResNet, and could potentially speed up inference by 5 times.

A natural language interface (NLI) to structured query is intriguing due to its wide industrial applications and high economical values. In this work, we tackle the problem of domain adaptation for NLI with limited data on target domain. Two important approaches are considered: (a) effective general-knowledge-learning on source domain semantic parsing, and (b) data augmentation on target domain. We present a Structured Query Inference Network (SQIN) to enhance learning for domain adaptation, by separating schema information from NL and decoding SQL in a more structural-aware manner; we also propose a GAN-based augmentation technique (AugmentGAN) to mitigate the issue of lacking target domain data. We report solid results on GeoQuery, Overnight, and WikiSQL to demonstrate state-of-the-art performances for both in-domain and domain-transfer tasks.

Relational database management systems (RDBMSs) are powerful because they are able to optimize and answer queries against any relational database. A natural language interface (NLI) for a database, on the other hand, is tailored to support that specific database. In this work, we introduce a general purpose transfer-learnable NLI with the goal of learning one model that can be used as NLI for any relational database. We adopt the data management principle of separating data and its schema, but with the additional support for the idiosyncrasy and complexity of natural languages. Specifically, we introduce an automatic annotation mechanism that separates the schema and the data, where the schema also covers knowledge about natural language. Furthermore, we propose a customized sequence model that translates annotated natural language queries to SQL statements. We show in experiments that our approach outperforms previous NLI methods on the WikiSQL dataset and the model we learned can be applied to another benchmark dataset OVERNIGHT without retraining.