Feilong Chen

Feilong Chen, Xiuyi Chen, Jiaxin Shi et al. · tsinghua

In the past few years, the emergence of vision-language pre-training (VLP) has brought cross-modal retrieval to a new era. However, due to the latency and computation demand, it is commonly challenging to apply VLP in a real-time online retrieval system. To alleviate the defect, this paper proposes a \textbf{Hi}erarchical \textbf{V}ision-\textbf{}Language \textbf{P}re-Training (\textbf{HiVLP}) for fast Image-Text Retrieval (ITR). Specifically, we design a novel hierarchical retrieval objective, which uses the representation of different dimensions for coarse-to-fine ITR, i.e., using low-dimensional representation for large-scale coarse retrieval and high-dimensional representation for small-scale fine retrieval. We evaluate our proposed HiVLP on two popular image-text retrieval benchmarks, i.e., Flickr30k and COCO. Extensive experiments demonstrate that our HiVLP not only has fast inference speed but also can be easily scaled to large-scale ITR scenarios. The detailed results show that HiVLP is $1,427$$\sim$$120,649\times$ faster than the fusion-based model UNITER and 2$\sim$5 faster than the fastest embedding-based model LightingDot in different candidate scenarios. It also achieves about +4.9 AR on COCO and +3.8 AR on Flickr30K than LightingDot and achieves comparable performance with the state-of-the-art (SOTA) fusion-based model METER.

Feilong Chen, Xiuyi Chen, Shuang Xu et al.

Visual Dialog is a challenging vision-language task since the visual dialog agent needs to answer a series of questions after reasoning over both the image content and dialog history. Though existing methods try to deal with the cross-modal understanding in visual dialog, they are still not enough in ranking candidate answers based on their understanding of visual and textual contexts. In this paper, we analyze the cross-modal understanding in visual dialog based on the vision-language pre-training model VD-BERT and propose a novel approach to improve the cross-modal understanding for visual dialog, named ICMU. ICMU enhances cross-modal understanding by distinguishing different pulled inputs (i.e. pulled images, questions or answers) based on four-way contrastive learning. In addition, ICMU exploits the single-turn visual question answering to enhance the visual dialog model's cross-modal understanding to handle a multi-turn visually-grounded conversation. Experiments show that the proposed approach improves the visual dialog model's cross-modal understanding and brings satisfactory gain to the VisDial dataset.

Minglun Han, Feilong Chen, Jing Shi et al.

Large-scale pre-trained language models (PLMs) have shown great potential in natural language processing tasks. Leveraging the capabilities of PLMs to enhance automatic speech recognition (ASR) systems has also emerged as a promising research direction. However, previous works may be limited by the inflexible structures of PLMs and the insufficient utilization of PLMs. To alleviate these problems, we propose the hierarchical knowledge distillation (HKD) on the continuous integrate-and-fire (CIF) based ASR models. To transfer knowledge from PLMs to the ASR models, HKD employs cross-modal knowledge distillation with contrastive loss at the acoustic level and knowledge distillation with regression loss at the linguistic level. Compared with the original CIF-based model, our method achieves 15% and 9% relative error rate reduction on the AISHELL-1 and LibriSpeech datasets, respectively.

Feilong Chen, Di Wu, Jie Yang et al.

Online streaming feature selection (OSFS), which conducts feature selection in an online manner, plays an important role in dealing with high-dimensional data. In many real applications such as intelligent healthcare platform, streaming feature always has some missing data, which raises a crucial challenge in conducting OSFS, i.e., how to establish the uncertain relationship between sparse streaming features and labels. Unfortunately, existing OSFS algorithms never consider such uncertain relationship. To fill this gap, we in this paper propose an online sparse streaming feature selection with uncertainty (OS2FSU) algorithm. OS2FSU consists of two main parts: 1) latent factor analysis is utilized to pre-estimate the missing data in sparse streaming features before con-ducting feature selection, and 2) fuzzy logic and neighborhood rough set are employed to alleviate the uncertainty between estimated streaming features and labels during conducting feature selection. In the experiments, OS2FSU is compared with five state-of-the-art OSFS algorithms on six real datasets. The results demonstrate that OS2FSU outperforms its competitors when missing data are encountered in OSFS.

Tao Liu, Chenpeng Du, Shuai Fan et al.

Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate representation as a conduit. Still, previous methodologies rely on rough landmarks or are confined to a single speaker, thus limiting their performance. In this paper, we propose DiffDub: Diffusion-based dubbing. We first craft the Diffusion auto-encoder by an inpainting renderer incorporating a mask to delineate editable zones and unaltered regions. This allows for seamless filling of the lower-face region while preserving the remaining parts. Throughout our experiments, we encountered several challenges. Primarily, the semantic encoder lacks robustness, constricting its ability to capture high-level features. Besides, the modeling ignored facial positioning, causing mouth or nose jitters across frames. To tackle these issues, we employ versatile strategies, including data augmentation and supplementary eye guidance. Moreover, we encapsulated a conformer-based reference encoder and motion generator fortified by a cross-attention mechanism. This enables our model to learn person-specific textures with varying references and reduces reliance on paired audio-visual data. Our rigorous experiments comprehensively highlight that our ground-breaking approach outpaces existing methods with considerable margins and delivers seamless, intelligible videos in person-generic and multilingual scenarios.

Loka Li, Duzhen Zhang, Xingbo Du et al.

Large language model (LLM) agents are increasingly capable of automating components of machine learning development, yet existing biomedical benchmarks mainly focus on question answering, reasoning, and tool usage, or evaluate only narrow aspects of biomedical ML coding. We present BioXArena, a biomedical machine learning benchmark designed to evaluate whether agents can generate task-specific model training pipelines for heterogeneous and multi-modal biomedical datasets. BioXArena contains 76 end-to-end tasks across 9 domains, including sequence modeling, single-cell analysis, structural biology, network biology, chemical biology, perturbation dynamics, phenotype-disease modeling, biomedical imaging, and text-integrated learning. Each task is curated from primary biomedical sources into a unified evaluation framework with hidden labels, held-out graders, and biology-aware metrics normalized to a 0 to 1 scale. Agents are required to write executable code, train predictive models, and generate submissions for private test samples. Most tasks involve multiple input modalities, including tabular data, images, natural language, molecular sequences, omics matrices, and protein structures. We evaluate 11 agent configurations in a standardized 2-hour single-GPU environment. MLEvolve with Gemini-3.1-Pro achieves the highest average score of 0.666, followed by GPT-5.4 with 0.636, while no single agent consistently dominates across all domains. We additionally perform extensive ablation studies, robustness evaluations, scaling analyses, cost analyses, and failure-mode investigations to better understand how model backbones, agent scaffolds, inference budgets, and biomedical domains influence BioML coding performance. We will publicly release all benchmark tasks, graders, execution runners, leaderboard results, and agent trajectories.

Tao Liu, Feilong Chen, Shuai Fan et al.

The paper introduces AniTalker, an innovative framework designed to generate lifelike talking faces from a single portrait. Unlike existing models that primarily focus on verbal cues such as lip synchronization and fail to capture the complex dynamics of facial expressions and nonverbal cues, AniTalker employs a universal motion representation. This innovative representation effectively captures a wide range of facial dynamics, including subtle expressions and head movements. AniTalker enhances motion depiction through two self-supervised learning strategies: the first involves reconstructing target video frames from source frames within the same identity to learn subtle motion representations, and the second develops an identity encoder using metric learning while actively minimizing mutual information between the identity and motion encoders. This approach ensures that the motion representation is dynamic and devoid of identity-specific details, significantly reducing the need for labeled data. Additionally, the integration of a diffusion model with a variance adapter allows for the generation of diverse and controllable facial animations. This method not only demonstrates AniTalker's capability to create detailed and realistic facial movements but also underscores its potential in crafting dynamic avatars for real-world applications. Synthetic results can be viewed at https://github.com/X-LANCE/AniTalker.

Tao Liu, Ziyang Ma, Qi Chen et al.

We present VQTalker, a Vector Quantization-based framework for multilingual talking head generation that addresses the challenges of lip synchronization and natural motion across diverse languages. Our approach is grounded in the phonetic principle that human speech comprises a finite set of distinct sound units (phonemes) and corresponding visual articulations (visemes), which often share commonalities across languages. We introduce a facial motion tokenizer based on Group Residual Finite Scalar Quantization (GRFSQ), which creates a discretized representation of facial features. This method enables comprehensive capture of facial movements while improving generalization to multiple languages, even with limited training data. Building on this quantized representation, we implement a coarse-to-fine motion generation process that progressively refines facial animations. Extensive experiments demonstrate that VQTalker achieves state-of-the-art performance in both video-driven and speech-driven scenarios, particularly in multilingual settings. Notably, our method achieves high-quality results at a resolution of 512*512 pixels while maintaining a lower bitrate of approximately 11 kbps. Our work opens new possibilities for cross-lingual talking face generation. Synthetic results can be viewed at https://x-lance.github.io/VQTalker.

Feilong Chen, Yijiang Liu, Yi Huang et al.

We propose MindVL, a multimodal large language model (MLLMs) trained on Ascend NPUs. The training of state-of-the-art MLLMs is often confined to a limited set of hardware platforms and relies heavily on massive, undisclosed data recipes, which hinders reproducibility and open research. To change the common perception that Ascend hardware is unsuitable for efficient full-stage MLLM training, we introduce MindSpeed-MLLM, a highly efficient training framework that supports stable and high-performance training of large-scale Dense and Mixture-of-Experts (MoE) models on Ascend hardware. Based on this, we provide a systematic and open description of the data production methods and mixing strategies for all training stages. Furthermore, we present MindVL, a data-efficient multimodal large language model trained end-to-end on Ascend NPUs. In addition, we find that averaging weights from checkpoints trained with different sequence lengths is particularly effective and yields further gains when combined with test-time resolution search. Our experiments demonstrate superior data efficiency: MindVL-8B matches the performance of Qwen2.5VL-7B using only 10\% of its training data, while our MoE model, MindVL-671B-A37B, matches Qwen2.5VL-72B using only 3\% of the Qwen2.5VL training data, and achieves comparable performance with other leading multimodal MoE models. Our work provides the community with a valuable hardware alternative, open data recipes, and effective performance-enhancing techniques.

Duzhen Zhang, Yong Ren, Wei Cong et al.

Continual Semantic Segmentation (CSS) seeks to incrementally learn to segment novel classes while preserving knowledge of previously encountered ones. Recent advancements in CSS have been largely driven by the adoption of Pre-trained Vision Models (PVMs) as backbones. Among existing strategies, Direct Fine-Tuning (DFT), which sequentially fine-tunes the model across classes, remains the most straightforward approach. Prior work often regards DFT as a performance lower bound due to its presumed vulnerability to severe catastrophic forgetting, leading to the development of numerous complex mitigation techniques. However, we contend that this prevailing assumption is flawed. In this paper, we systematically revisit forgetting in DFT across two standard benchmarks, Pascal VOC 2012 and ADE20K, under eight CSS settings using two representative PVM backbones: ResNet101 and Swin-B. Through a detailed probing analysis, our findings reveal that existing methods significantly underestimate the inherent anti-forgetting capabilities of PVMs. Even under DFT, PVMs retain previously learned knowledge with minimal forgetting. Further investigation of the feature space indicates that the observed forgetting primarily arises from the classifier's drift away from the PVM, rather than from degradation of the backbone representations. Based on this insight, we propose DFT*, a simple yet effective enhancement to DFT that incorporates strategies such as freezing the PVM backbone and previously learned classifiers, as well as pre-allocating future classifiers. Extensive experiments show that DFT* consistently achieves competitive or superior performance compared to sixteen state-of-the-art CSS methods, while requiring substantially fewer trainable parameters and less training time.

Ziyi Ni, Minglun Han, Feilong Chen et al.

Enhancing automatic speech recognition (ASR) performance by leveraging additional multimodal information has shown promising results in previous studies. However, most of these works have primarily focused on utilizing visual cues derived from human lip motions. In fact, context-dependent visual and linguistic cues can also benefit in many scenarios. In this paper, we first propose ViLaS (Vision and Language into Automatic Speech Recognition), a novel multimodal ASR model based on the continuous integrate-and-fire (CIF) mechanism, which can integrate visual and textual context simultaneously or separately, to facilitate speech recognition. Next, we introduce an effective training strategy that improves performance in modal-incomplete test scenarios. Then, to explore the effects of integrating vision and language, we create VSDial, a multimodal ASR dataset with multimodal context cues in both Chinese and English versions. Finally, empirical results are reported on the public Flickr8K and self-constructed VSDial datasets. We explore various cross-modal fusion schemes, analyze fine-grained crossmodal alignment on VSDial, and provide insights into the effects of integrating multimodal information on speech recognition.

Feilong Chen, Minglun Han, Haozhi Zhao et al.

Large language models (LLMs) have demonstrated remarkable language abilities. GPT-4, based on advanced LLMs, exhibits extraordinary multimodal capabilities beyond previous visual language models. We attribute this to the use of more advanced LLMs compared with previous multimodal models. Unfortunately, the model architecture and training strategies of GPT-4 are unknown. To endow LLMs with multimodal capabilities, we propose X-LLM, which converts Multi-modalities (images, speech, videos) into foreign languages using X2L interfaces and inputs them into a large Language model (ChatGLM). Specifically, X-LLM aligns multiple frozen single-modal encoders and a frozen LLM using X2L interfaces, where ``X'' denotes multi-modalities such as image, speech, and videos, and ``L'' denotes languages. X-LLM's training consists of three stages: (1) Converting Multimodal Information: The first stage trains each X2L interface to align with its respective single-modal encoder separately to convert multimodal information into languages. (2) Aligning X2L representations with the LLM: single-modal encoders are aligned with the LLM through X2L interfaces independently. (3) Integrating multiple modalities: all single-modal encoders are aligned with the LLM through X2L interfaces to integrate multimodal capabilities into the LLM. Our experiments show that X-LLM demonstrates impressive multimodel chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 84.5\% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. And we also conduct quantitative tests on using LLM for ASR and multimodal ASR, hoping to promote the era of LLM-based speech recognition.

Feilong Chen, Duzhen Zhang, Minglun Han et al.

In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better overall grasp of VLP, we first review its recent advances from five aspects: feature extraction, model architecture, pre-training objectives, pre-training datasets, and downstream tasks. Then, we summarize the specific VLP models in detail. Finally, we discuss the new frontiers in VLP. To the best of our knowledge, this is the first survey focused on VLP. We hope that this survey can shed light on future research in the VLP field.

Feilong Chen, Fandong Meng, Xiuyi Chen et al.

Visual dialogue is a challenging task since it needs to answer a series of coherent questions on the basis of understanding the visual environment. Previous studies focus on the implicit exploration of multimodal co-reference by implicitly attending to spatial image features or object-level image features but neglect the importance of locating the objects explicitly in the visual content, which is associated with entities in the textual content. Therefore, in this paper we propose a {\bf M}ultimodal {\bf I}ncremental {\bf T}ransformer with {\bf V}isual {\bf G}rounding, named MITVG, which consists of two key parts: visual grounding and multimodal incremental transformer. Visual grounding aims to explicitly locate related objects in the image guided by textual entities, which helps the model exclude the visual content that does not need attention. On the basis of visual grounding, the multimodal incremental transformer encodes the multi-turn dialogue history combined with visual scene step by step according to the order of the dialogue and then generates a contextually and visually coherent response. Experimental results on the VisDial v0.9 and v1.0 datasets demonstrate the superiority of the proposed model, which achieves comparable performance.

Feilong Chen, Xiuyi Chen, Fandong Meng et al.

Visual dialog, which aims to hold a meaningful conversation with humans about a given image, is a challenging task that requires models to reason the complex dependencies among visual content, dialog history, and current questions. Graph neural networks are recently applied to model the implicit relations between objects in an image or dialog. However, they neglect the importance of 1) coreference relations among dialog history and dependency relations between words for the question representation; and 2) the representation of the image based on the fully represented question. Therefore, we propose a novel relation-aware graph-over-graph network (GoG) for visual dialog. Specifically, GoG consists of three sequential graphs: 1) H-Graph, which aims to capture coreference relations among dialog history; 2) History-aware Q-Graph, which aims to fully understand the question through capturing dependency relations between words based on coreference resolution on the dialog history; and 3) Question-aware I-Graph, which aims to capture the relations between objects in an image based on fully question representation. As an additional feature representation module, we add GoG to the existing visual dialogue model. Experimental results show that our model outperforms the strong baseline in both generative and discriminative settings by a significant margin.

Feilong Chen, Xiuyi Chen, Can Xu et al.

Visual dialog is challenging since it needs to answer a series of coherent questions based on understanding the visual environment. How to ground related visual objects is one of the key problems. Previous studies utilize the question and history to attend to the image and achieve satisfactory performance, however these methods are not sufficient to locate related visual objects without any guidance. The inappropriate grounding of visual objects prohibits the performance of visual dialog models. In this paper, we propose a novel approach to Learn to Ground visual objects for visual dialog, which employs a novel visual objects grounding mechanism where both prior and posterior distributions over visual objects are used to facilitate visual objects grounding. Specifically, a posterior distribution over visual objects is inferred from both context (history and questions) and answers, and it ensures the appropriate grounding of visual objects during the training process. Meanwhile, a prior distribution, which is inferred from context only, is used to approximate the posterior distribution so that appropriate visual objects can be grounded even without answers during the inference process. Experimental results on the VisDial v0.9 and v1.0 datasets demonstrate that our approach improves the previous strong models in both generative and discriminative settings by a significant margin.

Feilong Chen, Fandong Meng, Jiaming Xu et al.

Visual Dialog is a vision-language task that requires an AI agent to engage in a conversation with humans grounded in an image. It remains a challenging task since it requires the agent to fully understand a given question before making an appropriate response not only from the textual dialog history, but also from the visually-grounded information. While previous models typically leverage single-hop reasoning or single-channel reasoning to deal with this complex multimodal reasoning task, which is intuitively insufficient. In this paper, we thus propose a novel and more powerful Dual-channel Multi-hop Reasoning Model for Visual Dialog, named DMRM. DMRM synchronously captures information from the dialog history and the image to enrich the semantic representation of the question by exploiting dual-channel reasoning. Specifically, DMRM maintains a dual channel to obtain the question- and history-aware image features and the question- and image-aware dialog history features by a mulit-hop reasoning process in each channel. Additionally, we also design an effective multimodal attention to further enhance the decoder to generate more accurate responses. Experimental results on the VisDial v0.9 and v1.0 datasets demonstrate that the proposed model is effective and outperforms compared models by a significant margin.