Jun Huang

Wenhui Liao, Jiapeng Wang, Hongliang Li et al.

Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Models (MLLMs) have achieved fast progress in this domain, existing approaches either demand significant computational resources or struggle with effective multi-modal integration. In this paper, we introduce DocLayLLM, an efficient multi-modal extension of LLMs specifically designed for TDU. By lightly integrating visual patch tokens and 2D positional tokens into LLMs' input and encoding the document content using the LLMs themselves, we fully take advantage of the document comprehension capability of LLMs and enhance their perception of OCR information. We have also deeply considered the role of chain-of-thought (CoT) and innovatively proposed the techniques of CoT Pre-training and CoT Annealing. Our DocLayLLM can achieve remarkable performances with lightweight training settings, showcasing its efficiency and effectiveness. Experimental results demonstrate that our DocLayLLM outperforms existing OCR-dependent methods and OCR-free competitors. Code and model are available at https://github.com/whlscut/DocLayLLM.

Yukang Xie, Chengyu Wang, Junbing Yan et al.

Recently, Large Language Models (LLMs) have achieved amazing zero-shot learning performance over a variety of Natural Language Processing (NLP) tasks, especially for text generative tasks. Yet, the large size of LLMs often leads to the high computational cost of model training and online deployment. In our work, we present ALTER, a system that effectively builds the multi-tAsk Learners with mixTure-of-task-adaptERs upon small language models (with <1B parameters) to address multiple NLP tasks simultaneously, capturing the commonalities and differences between tasks, in order to support domain-specific applications. Specifically, in ALTER, we propose the Mixture-of-Task-Adapters (MTA) module as an extension to the transformer architecture for the underlying model to capture the intra-task and inter-task knowledge. A two-stage training method is further proposed to optimize the collaboration between adapters at a small computational cost. Experimental results over a mixture of NLP tasks show that our proposed MTA architecture and the two-stage training method achieve good performance. Based on ALTER, we have also produced MTA-equipped language models for various domains.

Tongtong Su, Chengyu Wang, Bingyan Liu et al.

In recent years, large text-to-video (T2V) synthesis models have garnered considerable attention for their abilities to generate videos from textual descriptions. However, achieving both high imaging quality and effective motion representation remains a significant challenge for these T2V models. Existing approaches often adapt pre-trained text-to-image (T2I) models to refine video frames, leading to issues such as flickering and artifacts due to inconsistencies across frames. In this paper, we introduce EVS, a training-free Encapsulated Video Synthesizer that composes T2I and T2V models to enhance both visual fidelity and motion smoothness of generated videos. Our approach utilizes a well-trained diffusion-based T2I model to refine low-quality video frames by treating them as out-of-distribution samples, effectively optimizing them with noising and denoising steps. Meanwhile, we employ T2V backbones to ensure consistent motion dynamics. By encapsulating the T2V temporal-only prior into the T2I generation process, EVS successfully leverages the strengths of both types of models, resulting in videos of improved imaging and motion quality. Experimental results validate the effectiveness of our approach compared to previous approaches. Our composition process also leads to a significant improvement of 1.6x-4.5x speedup in inference time. Source codes: https://github.com/Tonniia/EVS.

Yuanhao Yue, Chengyu Wang, Jun Huang et al.

Instruction tuning aims to align large language models (LLMs) with open-domain instructions and human-preferred responses. While several studies have explored autonomous approaches to distilling and annotating instructions from powerful proprietary LLMs, such as ChatGPT, they often neglect the impact of the distributions and characteristics of tasks, together with the varying difficulty of instructions in training sets. This oversight can lead to imbalanced knowledge capabilities and poor generalization powers of student LLMs. To address these challenges, we introduce Task-Aware Curriculum Planning for Instruction Refinement (TAPIR), a multi-round distillation framework that utilizes an oracle LLM to select instructions that are difficult for a student LLM to follow. To balance the student's capabilities, task distributions in training sets are adjusted with responses automatically refined according to their corresponding tasks. In addition, by incorporating curriculum planning, our approach systematically escalates the difficulty levels of tasks, progressively enhancing the student LLM's capabilities. We rigorously evaluate TAPIR using several widely recognized benchmarks (such as AlpacaEval 2.0, MT-Bench, etc.) and multiple student LLMs. Empirical results demonstrate that student LLMs, trained with our method and less training data, outperform larger instruction-tuned models and strong distillation baselines.

Chengyu Wang, Taolin Zhang, Richang Hong et al.

Recently, the reasoning capabilities of large reasoning models (LRMs), such as DeepSeek-R1, have seen significant advancements through the slow thinking process. Despite these achievements, the substantial computational demands of LRMs present considerable challenges. In contrast, small reasoning models (SRMs), often distilled from larger ones, offer greater efficiency and can exhibit distinct capabilities and cognitive trajectories compared to LRMs. This work surveys around 170 recently published papers on SRMs for tackling various complex reasoning tasks. We review the current landscape of SRMs and analyze diverse training and inference techniques related to SRMs. Furthermore, we provide a comprehensive review of SRMs for domain-specific applications and discuss possible future research directions. This survey serves as an essential reference for researchers to leverage or develop SRMs for advanced reasoning functionalities with high efficiency.

Jiapeng Wang, Chengyu Wang, Xiaodan Wang et al.

Large-scale pre-trained text-image models with dual-encoder architectures (such as CLIP) are typically adopted for various vision-language applications, including text-image retrieval. However,these models are still less practical on edge devices or for real-time situations, due to the substantial indexing and inference time and the large consumption of computational resources. Although knowledge distillation techniques have been widely utilized for uni-modal model compression, how to expand them to the situation when the numbers of modalities and teachers/students are doubled has been rarely studied. In this paper, we conduct comprehensive experiments on this topic and propose the fully-Connected knowledge interaction graph (Cona) technique for cross-modal pre-training distillation. Based on our findings, the resulting ConaCLIP achieves SOTA performances on the widely-used Flickr30K and MSCOCO benchmarks under the lightweight setting. An industry application of our method on an e-commercial platform further demonstrates the significant effectiveness of ConaCLIP.

Chengyu Wang, Mengli Cheng, Xu Hu et al.

We present EasyASR, a distributed machine learning platform for training and serving large-scale Automatic Speech Recognition (ASR) models, as well as collecting and processing audio data at scale. Our platform is built upon the Machine Learning Platform for AI of Alibaba Cloud. Its main functionality is to support efficient learning and inference for end-to-end ASR models on distributed GPU clusters. It allows users to learn ASR models with either pre-defined or user-customized network architectures via simple user interface. On EasyASR, we have produced state-of-the-art results over several public datasets for Mandarin speech recognition.

Mengli Cheng, Minghui Qiu, Xing Shi et al.

Structured information extraction from document images usually consists of three steps: text detection, text recognition, and text field labeling. While text detection and text recognition have been heavily studied and improved a lot in literature, text field labeling is less explored and still faces many challenges. Existing learning based methods for text labeling task usually require a large amount of labeled examples to train a specific model for each type of document. However, collecting large amounts of document images and labeling them is difficult and sometimes impossible due to privacy issues. Deploying separate models for each type of document also consumes a lot of resources. Facing these challenges, we explore one-shot learning for the text field labeling task. Existing one-shot learning methods for the task are mostly rule-based and have difficulty in labeling fields in crowded regions with few landmarks and fields consisting of multiple separate text regions. To alleviate these problems, we proposed a novel deep end-to-end trainable approach for one-shot text field labeling, which makes use of attention mechanism to transfer the layout information between document images. We further applied conditional random field on the transferred layout information for the refinement of field labeling. We collected and annotated a real-world one-shot field labeling dataset with a large variety of document types and conducted extensive experiments to examine the effectiveness of the proposed model. To stimulate research in this direction, the collected dataset and the one-shot model will be released1.

Chengyu Wang, Minghui Qiu, Jun Huang et al.

Lexical relations describe how concepts are semantically related, in the form of relation triples. The accurate prediction of lexical relations between concepts is challenging, due to the sparsity of patterns indicating the existence of such relations. We propose the Knowledge-Enriched Meta-Learning (KEML) framework to address the task of lexical relation classification. In KEML, the LKB-BERT (Lexical Knowledge Base-BERT) model is presented to learn concept representations from massive text corpora, with rich lexical knowledge injected by distant supervision. A probabilistic distribution of auxiliary tasks is defined to increase the model's ability to recognize different types of lexical relations. We further combine a meta-learning process over the auxiliary task distribution and supervised learning to train the neural lexical relation classifier. Experiments over multiple datasets show that KEML outperforms state-of-the-art methods.

Chen Qu, Feng Ji, Minghui Qiu et al.

Deep text matching approaches have been widely studied for many applications including question answering and information retrieval systems. To deal with a domain that has insufficient labeled data, these approaches can be used in a Transfer Learning (TL) setting to leverage labeled data from a resource-rich source domain. To achieve better performance, source domain data selection is essential in this process to prevent the "negative transfer" problem. However, the emerging deep transfer models do not fit well with most existing data selection methods, because the data selection policy and the transfer learning model are not jointly trained, leading to sub-optimal training efficiency. In this paper, we propose a novel reinforced data selector to select high-quality source domain data to help the TL model. Specifically, the data selector "acts" on the source domain data to find a subset for optimization of the TL model, and the performance of the TL model can provide "rewards" in turn to update the selector. We build the reinforced data selector based on the actor-critic framework and integrate it to a DNN based transfer learning model, resulting in a Reinforced Transfer Learning (RTL) method. We perform a thorough experimental evaluation on two major tasks for text matching, namely, paraphrase identification and natural language inference. Experimental results show the proposed RTL can significantly improve the performance of the TL model. We further investigate different settings of states, rewards, and policy optimization methods to examine the robustness of our method. Last, we conduct a case study on the selected data and find our method is able to select source domain data whose Wasserstein distance is close to the target domain data. This is reasonable and intuitive as such source domain data can provide more transferability power to the model.

Liu Yang, Minghui Qiu, Chen Qu et al.

Intelligent personal assistant systems with either text-based or voice-based conversational interfaces are becoming increasingly popular around the world. Retrieval-based conversation models have the advantages of returning fluent and informative responses. Most existing studies in this area are on open domain "chit-chat" conversations or task / transaction oriented conversations. More research is needed for information-seeking conversations. There is also a lack of modeling external knowledge beyond the dialog utterances among current conversational models. In this paper, we propose a learning framework on the top of deep neural matching networks that leverages external knowledge for response ranking in information-seeking conversation systems. We incorporate external knowledge into deep neural models with pseudo-relevance feedback and QA correspondence knowledge distillation. Extensive experiments with three information-seeking conversation data sets including both open benchmarks and commercial data show that, our methods outperform various baseline methods including several deep text matching models and the state-of-the-art method on response selection in multi-turn conversations. We also perform analysis over different response types, model variations and ranking examples. Our models and research findings provide new insights on how to utilize external knowledge with deep neural models for response selection and have implications for the design of the next generation of information-seeking conversation systems.

Jianfei Yu, Minghui Qiu, Jing Jiang et al.

In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource- poor target domain. Specifically, since most existing transfer learning methods only focus on learning a shared feature space across domains while ignoring the relationship between the source and target domains, we propose to simultaneously learn shared representations and domain relationships in a unified framework. Furthermore, we propose an efficient and effective hybrid model by combining a sentence encoding- based method and a sentence interaction-based method as our base model. Extensive experiments on both paraphrase identification and natural language inference demonstrate that our base model is efficient and has promising performance compared to the competing models, and our transfer learning method can help to significantly boost the performance. Further analysis shows that the inter-domain and intra-domain relationship captured by our model are insightful. Last but not least, we deploy our transfer learning model for PI into our online chatbot system, which can bring in significant improvements over our existing system. Finally, we launch our new system on the chatbot platform Eva in our E-commerce site AliExpress.