Chen Shen

Shen Chen, Yanlong Li, Jiamin Cui et al.

A common approach to digital system design involves transforming a continuous-time (s-domain) transfer function into the discrete-time (z-domain) using methods such as Euler or Tustin. These transformations are shown to be specific cases of the Generalized Bilinear Transformation (GBT), characterized by a design parameter, $α$, whose physical interpretation and optimal selection remain inadequately explored. In this paper, we propose an alternative derivation of the GBT derived by employing a new hexagonal shape to approximate the enclosed area of the error function, and we define the parameter $α$ as a shape factor. We reveal, for the first time, the physical meaning of $α$ as the backward rectangular ratio of the proposed hexagonal shape. Through domain mapping, the stable range of is rigorously established to be [0.5, 1]. Depending on the operating frequency and the chosen $α$, we observe two distinct distortion modes, i.e., the magnitude and phase distortion. We further develop an optimal design method for $α$ by minimizing a normalized magnitude or phase error objective function. The effectiveness of the proposed method is validated through the design and testing of a low-pass filter (LPF), demonstrating strong agreement between theoretical predictions and experimental results.

Ke Sun, Shen Chen, Taiping Yao et al.

Face manipulation techniques have achieved significant advances, presenting serious challenges to security and social trust. Recent works demonstrate that leveraging multimodal models can enhance the generalization and interpretability of face forgery detection. However, existing annotation approaches, whether through human labeling or direct Multimodal Large Language Model (MLLM) generation, often suffer from hallucination issues, leading to inaccurate text descriptions, especially for high-quality forgeries. To address this, we propose Face Forgery Text Generator (FFTG), a novel annotation pipeline that generates accurate text descriptions by leveraging forgery masks for initial region and type identification, followed by a comprehensive prompting strategy to guide MLLMs in reducing hallucination. We validate our approach through fine-tuning both CLIP with a three-branch training framework combining unimodal and multimodal objectives, and MLLMs with our structured annotations. Experimental results demonstrate that our method not only achieves more accurate annotations with higher region identification accuracy, but also leads to improvements in model performance across various forgery detection benchmarks. Our Codes are available in https://github.com/skJack/VLFFD.git.

Minglun Han, Ye Bai, Chen Shen et al.

Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with bidirectional context, and lack sufficient support for downstream streaming models. To address this issue, we introduce the next token prediction based speech pre-training method with random-projection quantizer (NEST-RQ). NEST-RQ employs causal encoders with only left context and uses next token prediction (NTP) as the training task. On the large-scale dataset, compared to BEST-RQ, the proposed NEST-RQ achieves comparable performance on non-streaming automatic speech recognition (ASR) and better performance on streaming ASR. We also conduct analytical experiments in terms of the future context size of streaming ASR, the codebook quality of SSL and the model size of the encoder. In summary, the paper demonstrates the feasibility of the NTP in speech SSL and provides empirical evidence and insights for speech SSL research.

Chen Shen, Chunfeng Lian, Wanqing Zhang et al.

Forensic pathology is critical in determining the cause and manner of death through post-mortem examinations, both macroscopic and microscopic. The field, however, grapples with issues such as outcome variability, laborious processes, and a scarcity of trained professionals. This paper presents SongCi, an innovative visual-language model (VLM) designed specifically for forensic pathology. SongCi utilizes advanced prototypical cross-modal self-supervised contrastive learning to enhance the accuracy, efficiency, and generalizability of forensic analyses. It was pre-trained and evaluated on a comprehensive multi-center dataset, which includes over 16 million high-resolution image patches, 2,228 vision-language pairs of post-mortem whole slide images (WSIs), and corresponding gross key findings, along with 471 distinct diagnostic outcomes. Our findings indicate that SongCi surpasses existing multi-modal AI models in many forensic pathology tasks, performs comparably to experienced forensic pathologists and significantly better than less experienced ones, and provides detailed multi-modal explainability, offering critical assistance in forensic investigations. To the best of our knowledge, SongCi is the first VLM specifically developed for forensic pathological analysis and the first large-vocabulary computational pathology (CPath) model that directly processes gigapixel WSIs in forensic science.

Mingbao Lin, Rongrong Ji, Hong Liu et al.

Online image hashing has attracted increasing research attention recently, which receives large-scale data in a streaming manner to update the hash functions on-the-fly. Its key challenge lies in the difficulty of balancing the learning timeliness and model accuracy. To this end, most works follow a supervised setting, i.e., using class labels to boost the hashing performance, which defects in two aspects: First, strong constraints, e.g., orthogonal or similarity preserving, are used, which however are typically relaxed and lead to large accuracy drop. Second, large amounts of training batches are required to learn the up-to-date hash functions, which largely increase the learning complexity. To handle the above challenges, a novel supervised online hashing scheme termed Hadamard Matrix Guided Online Hashing (HMOH) is proposed in this paper. Our key innovation lies in introducing Hadamard matrix, which is an orthogonal binary matrix built via Sylvester method. In particular, to release the need of strong constraints, we regard each column of Hadamard matrix as the target code for each class label, which by nature satisfies several desired properties of hashing codes. To accelerate the online training, LSH is first adopted to align the lengths of target code and to-be-learned binary code. We then treat the learning of hash functions as a set of binary classification problems to fit the assigned target code. Finally, extensive experiments demonstrate the superior accuracy and efficiency of the proposed method over various state-of-the-art methods. Codes are available at https://github.com/lmbxmu/mycode.

Wentang Song, Zhiyuan Yan, Yuzhen Lin et al.

Detecting AI-generated images, particularly deepfakes, has become increasingly crucial, with the primary challenge being the generalization to previously unseen manipulation methods. This paper tackles this issue by leveraging the forgery quality of training data to improve the generalization performance of existing deepfake detectors. Generally, the forgery quality of different deepfakes varies: some have easily recognizable forgery clues, while others are highly realistic. Existing works often train detectors on a mix of deepfakes with varying forgery qualities, potentially leading detectors to short-cut the easy-to-spot artifacts from low-quality forgery samples, thereby hurting generalization performance. To tackle this issue, we propose a novel quality-centric framework for generic deepfake detection, which is composed of a Quality Evaluator, a low-quality data enhancement module, and a learning pacing strategy that explicitly incorporates forgery quality into the training process. Our framework is inspired by curriculum learning, which is designed to gradually enable the detector to learn more challenging deepfake samples, starting with easier samples and progressing to more realistic ones. We employ both static and dynamic assessments to assess the forgery quality, combining their scores to produce a final rating for each training sample. The rating score guides the selection of deepfake samples for training, with higher-rated samples having a higher probability of being chosen. Furthermore, we propose a novel frequency data augmentation method specifically designed for low-quality forgery samples, which helps to reduce obvious forgery traces and improve their overall realism. Extensive experiments demonstrate that our proposed framework can be applied plug-and-play to existing detection models and significantly enhance their generalization performance in detection.

Chunzheng Zhu, Yangfang Lin, Shen Chen et al.

Accurate medical diagnosis often involves progressive visual focusing and iterative reasoning, characteristics commonly observed in clinical workflows. While recent vision-language models demonstrate promising chain-of-thought (CoT) reasoning capabilities via reinforcement learning with verifiable rewards (RLVR), their purely on-policy learning paradigm tends to reinforce superficially coherent but clinically inaccurate reasoning paths. We propose MedEyes, a novel reinforcement learning framework that dynamically models clinician-style diagnostic reasoning by progressively attending to and interpreting relevant medical image regions. By incorporating off-policy expert guidance, MedEyes converts expert visual search trajectories into structured external behavioral signals, guiding the model toward clinically aligned visual reasoning. We design the Gaze-guided Reasoning Navigator (GRN) to emulate the diagnostic process through a dual-mode exploration strategy, scanning for systematic abnormality localization and drilling for detailed regional analysis. To balance expert imitation and autonomous discovery, we introduce the Confidence Value Sampler (CVS), which employs nucleus sampling and adaptive termination to create diverse yet credible exploration paths. Finally, the dual-stream GRPO optimization framework decouples on-policy and off-policy learning signals, mitigating reward assimilation and entropy collapse. Experiments demonstrate that MedEyes achieves an average performance improvement of +8.5\% across multiple medical VQA benchmarks, validating MedEyes's potential in building interpretable medical AI systems.

Eser Kandogan, Sajjadur Rahman, Nikita Bhutani et al.

Large Language Models (LLMs) have showcased remarkable capabilities surpassing conventional NLP challenges, creating opportunities for use in production use cases. Towards this goal, there is a notable shift to building compound AI systems, wherein LLMs are integrated into an expansive software infrastructure with many components like models, retrievers, databases and tools. In this paper, we introduce a blueprint architecture for compound AI systems to operate in enterprise settings cost-effectively and feasibly. Our proposed architecture aims for seamless integration with existing compute and data infrastructure, with ``stream'' serving as the key orchestration concept to coordinate data and instructions among agents and other components. Task and data planners, respectively, break down, map, and optimize tasks and data to available agents and data sources defined in respective registries, given production constraints such as accuracy and latency.

Chen Shen, Yi Liu, Wenzhi Fan et al.

This paper describes our submission to ICASSP 2022 Multi-channel Multi-party Meeting Transcription (M2MeT) Challenge. For Track 1, we propose several approaches to empower the clustering-based speaker diarization system to handle overlapped speech. Front-end dereverberation and the direction-of-arrival (DOA) estimation are used to improve the accuracy of speaker diarization. Multi-channel combination and overlap detection are applied to reduce the missed speaker error. A modified DOVER-Lap is also proposed to fuse the results of different systems. We achieve the final DER of 5.79% on the Eval set and 7.23% on the Test set. For Track 2, we develop our system using the Conformer model in a joint CTC-attention architecture. Serialized output training is adopted to multi-speaker overlapped speech recognition. We propose a neural front-end module to model multi-channel audio and train the model end-to-end. Various data augmentation methods are utilized to mitigate over-fitting in the multi-channel multi-speaker E2E system. Transformer language model fusion is developed to achieve better performance. The final CER is 19.2% on the Eval set and 20.8% on the Test set.

Qiqi Gu, Shen Chen, Taiping Yao et al.

With the rapid development of facial forgery techniques, forgery detection has attracted more and more attention due to security concerns. Existing approaches attempt to use frequency information to mine subtle artifacts under high-quality forged faces. However, the exploitation of frequency information is coarse-grained, and more importantly, their vanilla learning process struggles to extract fine-grained forgery traces. To address this issue, we propose a progressive enhancement learning framework to exploit both the RGB and fine-grained frequency clues. Specifically, we perform a fine-grained decomposition of RGB images to completely decouple the real and fake traces in the frequency space. Subsequently, we propose a progressive enhancement learning framework based on a two-branch network, combined with self-enhancement and mutual-enhancement modules. The self-enhancement module captures the traces in different input spaces based on spatial noise enhancement and channel attention. The Mutual-enhancement module concurrently enhances RGB and frequency features by communicating in the shared spatial dimension. The progressive enhancement process facilitates the learning of discriminative features with fine-grained face forgery clues. Extensive experiments on several datasets show that our method outperforms the state-of-the-art face forgery detection methods.

Ke Sun, Taiping Yao, Shen Chen et al.

With various facial manipulation techniques arising, face forgery detection has drawn growing attention due to security concerns. Previous works always formulate face forgery detection as a classification problem based on cross-entropy loss, which emphasizes category-level differences rather than the essential discrepancies between real and fake faces, limiting model generalization in unseen domains. To address this issue, we propose a novel face forgery detection framework, named Dual Contrastive Learning (DCL), which specially constructs positive and negative paired data and performs designed contrastive learning at different granularities to learn generalized feature representation. Concretely, combined with the hard sample selection strategy, Inter-Instance Contrastive Learning (Inter-ICL) is first proposed to promote task-related discriminative features learning by especially constructing instance pairs. Moreover, to further explore the essential discrepancies, Intra-Instance Contrastive Learning (Intra-ICL) is introduced to focus on the local content inconsistencies prevalent in the forged faces by constructing local-region pairs inside instances. Extensive experiments and visualizations on several datasets demonstrate the generalization of our method against the state-of-the-art competitors.

Shaoshi Ling, Chen Shen, Meng Cai et al.

In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end speech recognition model. Without any extra loss function, we utilize the Gradient Mask to optimize the model when training on pseudo-label. This method forces the speech recognition model to predict from the masked input to learn strong acoustic representation and make training robust to label noise. In our semi-supervised experiments, the method can improve the model performance when training on pseudo-label and our method achieved competitive results comparing with other semi-supervised approaches on the Librispeech 100 hours experiments.

Shen Chen, Mingwei Zhang, Jiamin Cui et al.

Deep learning (DL) has brought about remarkable breakthrough in processing images, video and speech due to its efficacy in extracting highly abstract representation and learning very complex functions. However, there is seldom operating procedure reported on how to make it for real use cases. In this paper, we intend to address this problem by presenting a generalized operating procedure for DL from the perspective of unconstrained optimal design, which is motivated by a simple intension to remove the barrier of using DL, especially for those scientists or engineers who are new but eager to use it. Our proposed procedure contains seven steps, which are project/problem statement, data collection, architecture design, initialization of parameters, defining loss function, computing optimal parameters, and inference, respectively. Following this procedure, we build a multi-stream end-to-end speaker verification system, in which the input speech utterance is processed by multiple parallel streams within different frequency range, so that the acoustic modeling can be more robust resulting from the diversity of features. Trained with VoxCeleb dataset, our experimental results verify the effectiveness of our proposed operating procedure, and also show that our multi-stream framework outperforms single-stream baseline with 20 % relative reduction in minimum decision cost function (minDCF).