arXiv subjects

Yihao Chen

Publications and source records attributed to Yihao Chen.

At least 37 records · Page 2Linked to original sources

arXiv2025

Wav2DF-TSL: Two-stage Learning with Efficient Pre-training and Hierarchical Experts Fusion for Robust Audio Deepfake Detection

In recent years, self-supervised learning (SSL) models have made significant progress in audio deepfake detection (ADD) tasks. However, existing SSL models mainly rely on large-scale real speech for pre-training and lack the learning of spoofed samples, which leads to susceptibility to domain bias during the fine-tuning process of the ADD task. To this end, we propose a two-stage learning strategy (Wav2DF-TSL) based on pre-training and hierarchical expert fusion for robust audio deepfake detection. In the pre-training stage, we use adapters to efficiently learn artifacts from 3000 hours of unlabelled spoofed speech, improving the adaptability of front-end features while mitigating catastrophic forgetting. In the fine-tuning stage, we propose the hierarchical adaptive mixture of experts (HA-MoE) method to dynamically fuse multi-level spoofing cues through multi-expert collaboration with gated routing. Experimental results show that the proposed method significantly outperforms the baseline system on all four benchmark datasets, especially on the cross-domain In-the-wild dataset, achieving a 27.5% relative improvement in equal error rate (EER), outperforming the existing state-of-the-art systems. Index Terms: audio deepfake detection, self-supervised learning, parameter-efficient fine-tuning, mixture of experts

cs.SD↗

arXiv2025

Denoising GER: A Noise-Robust Generative Error Correction with LLM for Speech Recognition

In recent years, large language models (LLM) have made significant progress in the task of generation error correction (GER) for automatic speech recognition (ASR) post-processing. However, in complex noisy environments, they still face challenges such as poor adaptability and low information utilization, resulting in limited effectiveness of GER. To address these issues, this paper proposes a noise-robust multi-modal GER framework (Denoising GER). The framework enhances the model's adaptability to different noisy scenarios through a noise-adaptive acoustic encoder and optimizes the integration of multi-modal information via a heterogeneous feature compensation dynamic fusion (HFCDF) mechanism, improving the LLM's utilization of multi-modal information. Additionally, reinforcement learning (RL) training strategies are introduced to enhance the model's predictive capabilities. Experimental results demonstrate that Denoising GER significantly improves accuracy and robustness in noisy environments and exhibits good generalization abilities in unseen noise scenarios.

cs.SD↗

arXiv2025

RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale

Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present RepoForge, an autonomous, end-to-end pipeline that generates, evaluates, and trains SWE agents at scale. Our key contributions include: (1) RepoForge-8B-Agent, achieving 17.4\% on SWE-Bench-Verified~\citep{swebench_verified2024}, establishing new state-of-the-art for $\leq$8B non-thinking LLMs; (2) 7,304 executable environments auto-generated from real GitHub commits with zero manual intervention; (3) 14$\times$ storage reduction (1.4GB $\rightarrow$ 102MB per instance) via intelligent dependency management and image pruning; (4) $>$70\% faster evaluation using a Ray-powered~\citep{ray2018} distributed RepoForge harness; (5) 19,000$\times$ cheaper labeling through our automated SPICE~\citep{spice2024} difficulty assessment technique. By unifying storage-efficient sandboxing, Ray-powered evaluation harness, automated data generation, SPICE-based labeling, and bubble-free RL scaffold, we demonstrate that even $\leq$8B models can reach new state-of-the-art performance on demanding benchmarks like SWE-Bench-Verified. Our approach addresses critical bottlenecks in SWE agent training: high storage costs of container-based evaluation, inefficient sequential reward pipelines, limited availability of high-quality training data, expensive manual labeling, and multi-turn RL pipeline bottlenecks.

cs.SE↗

arXiv2025

Physics-Constrained Diffusion Reconstruction with Posterior Correction for Quantitative and Fast PET Imaging

Deep learning-based reconstruction of positron emission tomography(PET) data has gained increasing attention in recent years. While these methods achieve fast reconstruction,concerns remain regarding quantitative accuracy and the presence of artifacts,stemming from limited model interpretability,data driven dependence, and overfitting risks.These challenges have hindered clinical adoption.To address them,we propose a conditional diffusion model with posterior physical correction (PET-DPC) for PET image reconstruction. An innovative normalization procedure generates the input Geometric TOF Probabilistic Image (GTP-image),while physical information is incorporated during the diffusion sampling process to perform posterior scatter,attenuation,and random corrections. The model was trained and validated on 300 brain and 50 whole-body PET datasets,a physical phantom,and 20 simulated brain datasets. PET-DPC produced reconstructions closely aligned with fully corrected OSEM images,outperforming end-to-end deep learning models in quantitative metrics and,in some cases, surpassing traditional iterative methods. The model also generalized well to out-of-distribution(OOD) data. Compared to iterative methods,PET-DPC reduced reconstruction time by 50% for brain scans and 85% for whole-body scans. Ablation studies confirmed the critical role of posterior correction in implementing scatter and attenuation corrections,enhancing reconstruction accuracy. Experiments with physical phantoms further demonstrated PET-DPC's ability to preserve background uniformity and accurately reproduce tumor-to-background intensity ratios. Overall,these results highlight PET-DPC as a promising approach for rapid, quantitatively accurate PET reconstruction,with strong potential to improve clinical imaging workflows.

physics.med-ph↗

arXiv2025

An RRAM compute-in-memory architecture for high energy-efficient processing of binary matrix-vector multiplication in cryptography

Binary matrix-vector multiplication (BMVM) is a key operation in post-quantum cryptography schemes like the Classic McEliece cryptosystem. Conventional computing architectures incur significant energy efficiency loss due to data movement of large matrices when handling such tasks. Resistive memory (RRAM) non-volatile compute-in-memory (nvCIM) is an ideal technology for high energy-efficient BMVM processing but faces challenges, including signal margin degradation in high input-parallelism arrays due to device non-idealities and high hardware overhead from current readout and XOR operations. This work presents a RRAM nvCIM architecture featuring: 1) 1T1R cells with high-resistive-state compensation modules; and 2) pulsed current-sensing parity checkers. Based on the 180nm process and test results from RRAM devices, the computing accuracy and efficiency of the architecture are verified by simulation. The proposed architecture performs high-precision current accumulation with a maximum MAC value of 10 and achieves an energy efficiency of 1.51TOPS/W, offering approximately 1.62 times improvement compared to an advanced 28nm FPGA platform.

cs.ET↗

arXiv2025

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding

In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.5 to pursue an object-level representation for open-world object understanding. To make long-tailed object detection easy, DINO-X extends its input options to support text prompt, visual prompt, and customized prompt. With such flexible prompt options, we develop a universal object prompt to support prompt-free open-world detection, making it possible to detect anything in an image without requiring users to provide any prompt. To enhance the model's core grounding capability, we have constructed a large-scale dataset with over 100 million high-quality grounding samples, referred to as Grounding-100M, for advancing the model's open-vocabulary detection performance. Pre-training on such a large-scale grounding dataset leads to a foundational object-level representation, which enables DINO-X to integrate multiple perception heads to simultaneously support multiple object perception and understanding tasks, including detection, segmentation, pose estimation, object captioning, object-based QA, etc. Experimental results demonstrate the superior performance of DINO-X. Specifically, the DINO-X Pro model achieves 56.0 AP, 59.8 AP, and 52.4 AP on the COCO, LVIS-minival, and LVIS-val zero-shot object detection benchmarks, respectively. Notably, it scores 63.3 AP and 56.5 AP on the rare classes of LVIS-minival and LVIS-val benchmarks, improving the previous SOTA performance by 5.8 AP and 5.0 AP. Such a result underscores its significantly improved capacity for recognizing long-tailed objects.

cs.CV↗

arXiv2025

Referring to Any Person

Humans are undoubtedly the most important participants in computer vision, and the ability to detect any individual given a natural language description, a task we define as referring to any person, holds substantial practical value. However, we find that existing models generally fail to achieve real-world usability, and current benchmarks are limited by their focus on one-to-one referring, that hinder progress in this area. In this work, we revisit this task from three critical perspectives: task definition, dataset design, and model architecture. We first identify five aspects of referable entities and three distinctive characteristics of this task. Next, we introduce HumanRef, a novel dataset designed to tackle these challenges and better reflect real-world applications. From a model design perspective, we integrate a multimodal large language model with an object detection framework, constructing a robust referring model named RexSeek. Experimental results reveal that state-of-the-art models, which perform well on commonly used benchmarks like RefCOCO/+/g, struggle with HumanRef due to their inability to detect multiple individuals. In contrast, RexSeek not only excels in human referring but also generalizes effectively to common object referring, making it broadly applicable across various perception tasks. Code is available at https://github.com/IDEA-Research/RexSeek

cs.CV↗

arXiv2025

The Fourth Monocular Depth Estimation Challenge

This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. In this edition, we revised the evaluation protocol to use least-squares alignment with two degrees of freedom to support disparity and affine-invariant predictions. We also revised the baselines and included popular off-the-shelf methods: Depth Anything v2 and Marigold. The challenge received a total of 24 submissions that outperformed the baselines on the test set; 10 of these included a report describing their approach, with most leading methods relying on affine-invariant predictions. The challenge winners improved the 3D F-Score over the previous edition's best result, raising it from 22.58% to 23.05%.

cs.CV↗

arXiv2025

ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

Perception and understanding are two pillars of computer vision. While multimodal large language models (MLLM) have demonstrated remarkable visual understanding capabilities, they arguably lack accurate perception abilities, e.g. the stage-of-the-art model Qwen2-VL only achieves a 43.9 recall rate on the COCO dataset, limiting many tasks requiring the combination of perception and understanding. In this work, we aim to bridge this perception gap from both model designing and data development perspectives. We first introduce ChatRex, an MLLM with a decoupled perception design. Instead of having the LLM directly predict box coordinates, we feed the output boxes from a universal proposal network into the LLM, allowing it to output the corresponding box indices to represent its detection results, turning the regression task into a retrieval-based task that LLM handles more proficiently. From the data perspective, we build a fully automated data engine and construct the Rexverse-2M dataset which possesses multiple granularities to support the joint training of perception and understanding. After a three-stage training approach, ChatRex demonstrates strong perception and understanding performance, and the combination of these two capabilities also unlocks many attractive applications, demonstrating their complementary roles in MLLM. Code is available at https://github.com/IDEA-Research/ChatRex.

cs.CV↗

arXiv2025

TinySAM: Pushing the Envelope for Efficient Segment Anything Model

Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed various applications based on the pre-trained SAM and achieved impressive performance on downstream vision tasks. However, SAM consists of heavy architectures and requires massive computational capacity, which hinders the further application of SAM on computation constrained edge devices. To this end, in this paper we propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance. We first propose a full-stage knowledge distillation method with hard prompt sampling and hard mask weighting strategy to distill a lightweight student model. We also adapt the post-training quantization to the prompt-based segmentation task and further reduce the computational cost. Moreover, a hierarchical segmenting everything strategy is proposed to accelerate the everything inference by $2\times$ with almost no performance degradation. With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task. Extensive experiments on various zero-shot transfer tasks demonstrate the significantly advantageous performance of our TinySAM against counterpart methods. Codes are available at https://github.com/xinghaochen/TinySAM and https://gitee.com/mindspore/models/tree/master/research/cv/TinySAM.

cs.CV↗

arXiv2024

A High-Throughput FPGA Accelerator for Lightweight CNNs With Balanced Dataflow

FPGA accelerators for lightweight neural convolutional networks (LWCNNs) have recently attracted significant attention. Most existing LWCNN accelerators focus on single-Computing-Engine (CE) architecture with local optimization. However, these designs typically suffer from high on-chip/off-chip memory overhead and low computational efficiency due to their layer-by-layer dataflow and unified resource mapping mechanisms. To tackle these issues, a novel multi-CE-based accelerator with balanced dataflow is proposed to efficiently accelerate LWCNN through memory-oriented and computing-oriented optimizations. Firstly, a streaming architecture with hybrid CEs is designed to minimize off-chip memory access while maintaining a low cost of on-chip buffer size. Secondly, a balanced dataflow strategy is introduced for streaming architectures to enhance computational efficiency by improving efficient resource mapping and mitigating data congestion. Furthermore, a resource-aware memory and parallelism allocation methodology is proposed, based on a performance model, to achieve better performance and scalability. The proposed accelerator is evaluated on Xilinx ZC706 platform using MobileNetV2 and ShuffleNetV2.Implementation results demonstrate that the proposed accelerator can save up to 68.3% of on-chip memory size with reduced off-chip memory access compared to the reference design. It achieves an impressive performance of up to 2092.4 FPS and a state-of-the-art MAC efficiency of up to 94.58%, while maintaining a high DSP utilization of 95%, thus significantly outperforming current LWCNN accelerators.

cs.AR↗

arXiv2024

Machine Learning-Informed Scattering Correlation Analysis of Sheared Colloids

We carry out theoretical analysis, Monte Carlo simulations and Machine Learning analysis to quantify microscopic rearrangements of dilute dispersions of spherical colloidal particles from coherent scattering intensity. Both monodisperse and polydisperse dispersions of colloids are created and undergo a rearrangement consisting of an affine simple shear and non-affine rearrangement using Monte Carlo method. We calculate the coherent scattering intensity of the dispersions and the correlation function of intensity before and after the rearrangement, and generate a large data set of angular correlation functions for varying system parameters, including number density, polydispersity, shear strain, and non-affine rearrangement. Singular value decomposition of the data set shows the feasibility of machine learning inversion from the correlation function for the polydispersity, shear strain, and non-affine rearrangement using only three parameters. A Gaussian process regressor is then trained based on the data set and can retrieve the affine shear strain, non-affine rearrangement, and polydispersity with a relative error of 3\%, 1\% and 6\%, respectively. Together, our model provides a framework for quantitative studies of both steady and non-steady microscopic dynamics of colloidal dispersions using coherent scattering methods.

cond-mat.soft↗

arXiv2024

Deep reinforcement learning for tracking a moving target in jellyfish-like swimming

We develop a deep reinforcement learning method for training a jellyfish-like swimmer to effectively track a moving target in a two-dimensional flow. This swimmer is a flexible object equipped with a muscle model based on torsional springs. We employ a deep Q-network (DQN) that takes the swimmer's geometry and dynamic parameters as inputs, and outputs actions which are the forces applied to the swimmer. In particular, we introduce an action regulation to mitigate the interference from complex fluid-structure interactions. The goal of these actions is to navigate the swimmer to a target point in the shortest possible time. In the DQN training, the data on the swimmer's motions are obtained from simulations conducted using the immersed boundary method. During tracking a moving target, there is an inherent delay between the application of forces and the corresponding response of the swimmer's body due to hydrodynamic interactions between the shedding vortices and the swimmer's own locomotion. Our tests demonstrate that the swimmer, with the DQN agent and action regulation, is able to dynamically adjust its course based on its instantaneous state. This work extends the application scope of machine learning in controlling flexible objects within fluid environments.

physics.flu-dyn↗

arXiv2024

USTC-KXDIGIT System Description for ASVspoof5 Challenge

This paper describes the USTC-KXDIGIT system submitted to the ASVspoof5 Challenge for Track 1 (speech deepfake detection) and Track 2 (spoofing-robust automatic speaker verification, SASV). Track 1 showcases a diverse range of technical qualities from potential processing algorithms and includes both open and closed conditions. For these conditions, our system consists of a cascade of a frontend feature extractor and a back-end classifier. We focus on extensive embedding engineering and enhancing the generalization of the back-end classifier model. Specifically, the embedding engineering is based on hand-crafted features and speech representations from a self-supervised model, used for closed and open conditions, respectively. To detect spoof attacks under various adversarial conditions, we trained multiple systems on an augmented training set. Additionally, we used voice conversion technology to synthesize fake audio from genuine audio in the training set to enrich the synthesis algorithms. To leverage the complementary information learned by different model architectures, we employed activation ensemble and fused scores from different systems to obtain the final decision score for spoof detection. During the evaluation phase, the proposed methods achieved 0.3948 minDCF and 14.33% EER in the close condition, and 0.0750 minDCF and 2.59% EER in the open condition, demonstrating the robustness of our submitted systems under adversarial conditions. In Track 2, we continued using the CM system from Track 1 and fused it with a CNN-based ASV system. This approach achieved 0.2814 min-aDCF in the closed condition and 0.0756 min-aDCF in the open condition, showcasing superior performance in the SASV system.

cs.SD↗

arXiv2024

An Effective Information Theoretic Framework for Channel Pruning

Channel pruning is a promising method for accelerating and compressing convolutional neural networks. However, current pruning algorithms still remain unsolved problems that how to assign layer-wise pruning ratios properly and discard the least important channels with a convincing criterion. In this paper, we present a novel channel pruning approach via information theory and interpretability of neural networks. Specifically, we regard information entropy as the expected amount of information for convolutional layers. In addition, if we suppose a matrix as a system of linear equations, a higher-rank matrix represents there exist more solutions to it, which indicates more uncertainty. From the point of view of information theory, the rank can also describe the amount of information. In a neural network, considering the rank and entropy as two information indicators of convolutional layers, we propose a fusion function to reach a compromise of them, where the fusion results are defined as ``information concentration''. When pre-defining layer-wise pruning ratios, we employ the information concentration as a reference instead of heuristic and engineering tuning to provide a more interpretable solution. Moreover, we leverage Shapley values, which are a potent tool in the interpretability of neural networks, to evaluate the channel contributions and discard the least important channels for model compression while maintaining its performance. Extensive experiments demonstrate the effectiveness and promising performance of our method. For example, our method improves the accuracy by 0.21% when reducing 45.5% FLOPs and removing 40.3% parameters for ResNet-56 on CIFAR-10. Moreover, our method obtains loss in Top-1/Top-5 accuracies of 0.43%/0.11% by reducing 41.6% FLOPs and removing 35.0% parameters for ResNet-50 on ImageNet.

cs.IT↗

arXiv2024

Microstructural and rheological training and memory of nanocolloidal soft glasses under cyclic shear

An intrinsic feature of disordered and out-of-equilibrium materials, such as glasses, is the dependence of their properties on their history. An important example is rheological memory, in which disordered solids obtain properties based on their mechanical history. Here, we employ x-ray photon correlation spectroscopy (XPCS) with \textit{in situ} rheometry to characterize memory formation in a nanocolloidal soft glass due to cyclic shear. During a cycle, particles undergo irreversible displacements composed of a combination of shear-induced diffusion and strain fields. The magnitudes of these displacements decrease with each cycle before reaching a steady state where the microstructure has become trained to achieve enhanced reversibility. The displacements resemble a random walk in which the directions in each cycle are independent of those in preceding cycles. Accompanying the training is a steady decrease in the dissipation during each cycle towards a steady state value. Memory of this training is revealed by measurements in which the amplitude of the shear is changed after steady state is reached. The magnitude of the particle displacements as well as the dissipation and the change in residual stress vary non-monotonically with the new strain amplitude, having minima near the training amplitude, thereby revealing both microscopic and macroscopic signatures of memory.

cond-mat.soft↗

arXiv2024

Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection

This paper introduces Grounding DINO 1.5, a suite of advanced open-set object detection models developed by IDEA Research, which aims to advance the "Edge" of open-set object detection. The suite encompasses two models: Grounding DINO 1.5 Pro, a high-performance model designed for stronger generalization capability across a wide range of scenarios, and Grounding DINO 1.5 Edge, an efficient model optimized for faster speed demanded in many applications requiring edge deployment. The Grounding DINO 1.5 Pro model advances its predecessor by scaling up the model architecture, integrating an enhanced vision backbone, and expanding the training dataset to over 20 million images with grounding annotations, thereby achieving a richer semantic understanding. The Grounding DINO 1.5 Edge model, while designed for efficiency with reduced feature scales, maintains robust detection capabilities by being trained on the same comprehensive dataset. Empirical results demonstrate the effectiveness of Grounding DINO 1.5, with the Grounding DINO 1.5 Pro model attaining a 54.3 AP on the COCO detection benchmark and a 55.7 AP on the LVIS-minival zero-shot transfer benchmark, setting new records for open-set object detection. Furthermore, the Grounding DINO 1.5 Edge model, when optimized with TensorRT, achieves a speed of 75.2 FPS while attaining a zero-shot performance of 36.2 AP on the LVIS-minival benchmark, making it more suitable for edge computing scenarios. Model examples and demos with API will be released at https://github.com/IDEA-Research/Grounding-DINO-1.5-API

cs.CV↗

arXiv2024

An Empirical Study of Challenges in Machine Learning Asset Management

In machine learning (ML), efficient asset management, including ML models, datasets, algorithms, and tools, is vital for resource optimization, consistent performance, and a streamlined development lifecycle. This enables quicker iterations, adaptability, reduced development-to-deployment time, and reliable outputs. Despite existing research, a significant knowledge gap remains in operational challenges like model versioning, data traceability, and collaboration, which are crucial for the success of ML projects. Our study aims to address this gap by analyzing 15,065 posts from developer forums and platforms, employing a mixed-method approach to classify inquiries, extract challenges using BERTopic, and identify solutions through open card sorting and BERTopic clustering. We uncover 133 topics related to asset management challenges, grouped into 16 macro-topics, with software dependency, model deployment, and model training being the most discussed. We also find 79 solution topics, categorized under 18 macro-topics, highlighting software dependency, feature development, and file management as key solutions. This research underscores the need for further exploration of identified pain points and the importance of collaborative efforts across academia, industry, and the research community.

cs.SE↗