arXiv subjects

Zeyu Yang

Publications and source records attributed to Zeyu Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video

Generating dynamic 3D object from a single-view video is challenging due to the lack of 4D labeled data. An intuitive approach is to extend previous image-to-3D pipelines by transferring off-the-shelf image generation models such as score distillation sampling.However, this approach would be slow and expensive to scale due to the need for back-propagating the information-limited supervision signals through a large pretrained model. To address this, we propose an efficient video-to-4D object generation framework called Efficient4D. It generates high-quality spacetime-consistent images under different camera views, and then uses them as labeled data to directly reconstruct the 4D content through a 4D Gaussian splatting model. Importantly, our method can achieve real-time rendering under continuous camera trajectories. To enable robust reconstruction under sparse views, we introduce inconsistency-aware confidence-weighted loss design, along with a lightly weighted score distillation loss. Extensive experiments on both synthetic and real videos show that Efficient4D offers a remarkable 10-fold increase in speed when compared to prior art alternatives while preserving the quality of novel view synthesis. For example, Efficient4D takes only 10 minutes to model a dynamic object, vs 120 minutes by the previous art model Consistent4D.

cs.CV↗

arXiv2026

Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies

Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT with four adaptive actions: Sentence_Cut, Drop, Partial_Summarization and Pronominalization, which enable real-time restructuring, omission, and simplification while preserving semantic fidelity. We adapt these actions in a large language model (LLM) framework and construct training references through action-aware prompting. To evaluate both quality and word-level monotonicity, we further develop a latency-aware TTS pipeline that maps textual outputs to speech with realistic timing. Experiments on the ACL60/60 English-Chinese, English-German and English-Japanese benchmarks show that our framework consistently improves semantic metrics and achieves lower delay compared to reference translations and salami-based baselines. Notably, combining Drop and Sentence_Cut leads to consistent improvements in the balance between fluency and latency. These results demonstrate that enriching the action space of LLM-based SiMT provides a promising direction for bridging the gap between human and machine interpretation.

cs.CL↗

arXiv2025

StrengthSense: A Dataset of IMU Signals Capturing Everyday Strength-Demanding Activities

Tracking strength-demanding activities with wearable sensors like IMUs is crucial for monitoring muscular strength, endurance, and power. However, there is a lack of comprehensive datasets capturing these activities. To fill this gap, we introduce \textit{StrengthSense}, an open dataset that encompasses IMU signals capturing 11 strength-demanding activities, such as sit-to-stand, climbing stairs, and mopping. For comparative purposes, the dataset also includes 2 non-strength demanding activities. The dataset was collected from 29 healthy subjects utilizing 10 IMUs placed on limbs and the torso, and was annotated using video recordings as references. This paper provides a comprehensive overview of the data collection, pre-processing, and technical validation. We conducted a comparative analysis between the joint angles estimated by IMUs and those directly extracted from video to verify the accuracy and reliability of the sensor data. Researchers and developers can utilize \textit{StrengthSense} to advance the development of human activity recognition algorithms, create fitness and health monitoring applications, and more.

cs.CV↗

arXiv2025

Cross-Platform Short-Video Diplomacy: Topic and Sentiment Analysis of China-US Relations on Douyin and TikTok

We examine discussions surrounding China-U.S. relations on the Chinese and American social media platforms \textit{Douyin} and \textit{TikTok}. Both platforms, owned by \textit{ByteDance}, operate under different regulatory and cultural environments, providing a unique perspective for analyzing China-U.S. public discourse. This study analyzed 4,040 videos and 338,209 user comments to assess the public discussions and sentiments on social media regarding China-U.S. relations. Through topic clustering and sentiment analysis, we identified key themes, including economic strength, technological and industrial interdependence, cultural cognition and value pursuits, and responses to global challenges. There are significant emotional differences between China and the US on various themes. Since April 2022, the Chinese government has implemented a new regulation requiring all social media accounts to disclose their provincial-level geolocation information. Utilizing this publicly available data, along with factors such as GDP per capita, minority index, and internet penetration rate, we investigate the changes in sentiment towards the U.S. in mainland China. This study links socioeconomic indicators with online discussions, deeply analyzing how regional and economic factors influence Chinese comments on their views of the US, providing important insights for China-U.S. relationship research and policy making.

cs.SI↗

arXiv2025

DPO-Tuned Large Language Models for Segmentation in Simultaneous Speech Translation

Simultaneous speech translation requires accurate segmentation to balance translation quality and latency. Recent studies such as SHAS have introduced pretrained segmentation models, achieving stronger performance than heuristic rules. However, segmentation models such as SHAS, though pretrained and more robust than heuristic methods, are still constrained by supervised learning objectives and do not incorporate human preference alignment, which is crucial for natural real-time interpretation. In this work, we propose a segmentation framework based on large language models (LLMs) trained with Direct Preference Optimization (DPO). By leveraging preference alignment, our method enables LLMs to predict natural segmentation points that better meet the demands of real-time translation. We evaluate the system on the ACL 60/60 corpus across three language pairs (English-Japanese, Chinese, German), using SeamlessM4T v2 as the translation backbone. Experimental results show that our DPO-tuned LLM achieves higher segmentation accuracy than SHAS and yields consistent improvements in translation quality (BLEU, COMET) as well as latency (Average Lagging). Furthermore, our system benefits from IWSLT baselines for direct comparison. These findings highlight the potential of preference-tuned LLMs to surpass existing pretrained segmentation models and advance adaptive, human-aligned simultaneous interpretation.

cs.CL↗

arXiv2025

To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration

The scaling of Generative AI (GenAI) models into the hundreds of billions of parameters makes low-precision computation indispensable for efficient deployment. We argue that the fundamental solution lies in developing low-precision floating-point formats, which inherently provide numerical stability, memory savings, and hardware efficiency without dequantization overhead. In this paper, we present a theoretical and empirical study of an exponent concentration phenomenon in GenAI weights: exponents consistently exhibit low entropy across architectures and modalities. We show that this arises naturally from $α$-stable distributions induced by stochastic gradient descent, and we prove tight bounds on the entropy of exponents. Our analysis establishes a theoretical compression limit near FP4.67, which motivates the design of a practical FP8 format. Building on these insights, we propose Exponent-Concentrated FP8 (ECF8), a lossless compression framework with entropy-aware encoding and GPU-optimized decoding. Experiments on LLMs and DiTs up to 671B parameters demonstrate up to 26.9% memory savings and 177.1% throughput acceleration, with perfectly lossless computations, i.e., no deviation in model outputs. Our results establish exponent concentration as a statistical law of trained models and open a principled path for lossless low-precision floating-point design in the FP8 era.

cs.LG↗

arXiv2025

SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation

This work proposes a grammar-based chunking strategy that segments input streams into semantically complete units by parsing dependency relations (e.g., noun phrase boundaries, verb-object structures) and punctuation features. The method ensures chunk coherence and minimizes semantic fragmentation. Building on this mechanism, we present SASST (Syntax-Aware Simultaneous Speech Translation), an end-to-end framework integrating frozen Whisper encoder and decoder-only LLM. The unified architecture dynamically outputs translation tokens or symbols to jointly optimize translation timing and content, with target-side reordering addressing word-order divergence. Experiments on CoVoST2 multilingual corpus En-{De, Zh, Ja} demonstrate significant translation quality improvements across languages and validate the effectiveness of syntactic structures in LLM-driven SimulST systems.

cs.CL↗

arXiv2025

EchoAid: Enhancing Livestream Shopping Accessibility for the DHH Community

Livestream shopping platforms often overlook the accessibility needs of the Deaf and Hard of Hearing (DHH) community, leading to barriers such as information inaccessibility and overload. To tackle these challenges, we developed \textit{EchoAid}, a mobile app designed to improve the livestream shopping experience for DHH users. \textit{EchoAid} utilizes advanced speech-to-text conversion, Rapid Serial Visual Presentation (RSVP) technology, and Large Language Models (LLMs) to simplify the complex information flow in live sales environments. We conducted exploratory studies with eight DHH individuals to identify design needs and iteratively developed the \textit{EchoAid} prototype based on feedback from three participants. We then evaluate the performance of this system in a user study workshop involving 38 DHH participants. Our findings demonstrate the successful design and validation process of \textit{EchoAid}, highlighting its potential to enhance product information extraction, leading to reduced cognitive overload and more engaging and customized shopping experiences for DHH users.

cs.HC↗

arXiv2025

4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives

Dynamic 3D scene representation and novel view synthesis are crucial for enabling immersive experiences required by AR/VR and metaverse applications. It is a challenging task due to the complexity of unconstrained real-world scenes and their temporal dynamics. In this paper, we reformulate the reconstruction of a time-varying 3D scene as approximating its underlying spatiotemporal 4D volume by optimizing a collection of native 4D primitives, i.e., 4D Gaussians, with explicit geometry and appearance modeling. Equipped with a tailored rendering pipeline, our representation can be end-to-end optimized using only photometric supervision while free viewpoint viewing at interactive frame rate, making it suitable for representing real world scene with complex dynamic. This approach has been the first solution to achieve real-time rendering of high-resolution, photorealistic novel views for complex dynamic scenes. To facilitate real-world applications, we derive several compact variants that effectively reduce the memory footprint to address its storage bottleneck. Extensive experiments validate the superiority of 4DGS in terms of visual quality and efficiency across a range of dynamic scene-related tasks (e.g., novel view synthesis, 4D generation, scene understanding) and scenarios (e.g., single object, indoor scenes, driving environments, synthetic and real data).

cs.CV↗

arXiv2025

Driving View Synthesis on Free-form Trajectories with Generative Prior

Driving view synthesis along free-form trajectories is essential for realistic driving simulations, enabling closed-loop evaluation of end-to-end driving policies. Existing methods excel at view interpolation along recorded paths but struggle to generalize to novel trajectories due to limited viewpoints in driving videos. To tackle this challenge, we propose DriveX, a novel free-form driving view synthesis framework, that progressively distills generative prior into the 3D Gaussian model during its optimization. Within this framework, we utilize a video diffusion model to refine the degraded novel trajectory renderings from the in-training Gaussian model, while the restored videos in turn serve as additional supervision for optimizing the 3D Gaussian. Concretely, we craft an inpainting-based video restoration task, which can disentangle the identification of degraded regions from the generative capability of the diffusion model and remove the need of simulating specific degraded pattern in the training of the diffusion model. To further enhance the consistency and fidelity of generated contents, the pseudo ground truth is progressively updated with gradually improved novel trajectory rendering, allowing both components to co-adapt and reinforce each other while minimizing the disruption on the optimization. By tightly integrating 3D scene representation with generative prior, DriveX achieves high-quality view synthesis beyond recorded trajectories in real time--unlocking new possibilities for flexible and realistic driving simulations on free-form trajectories.

cs.CV↗

arXiv2025

seg2med: a bridge from artificial anatomy to multimodal medical images

We present seg2med, a modular framework for anatomy-driven multimodal medical image synthesis. The system integrates three components to enable high-fidelity, cross-modality generation of CT and MR images based on structured anatomical priors. First, anatomical maps are independently derived from three sources: real patient data, XCAT digital phantoms, and synthetic anatomies created by combining organs from multiple patients. Second, we introduce PhysioSynth, a modality-specific simulator that converts anatomical masks into prior volumes using tissue-dependent parameters (e.g., HU, T1, T2, proton density) and modality-specific signal models. It supports simulation of CT and multiple MR sequences including GRE, SPACE, and VIBE. Third, the synthesized anatomical priors are used to train 2-channel conditional denoising diffusion models, which take the anatomical prior as structural condition alongside the noisy image, enabling generation of high-quality, structurally aligned images. The framework achieves SSIM of 0.94 for CT and 0.89 for MR compared to real data, and FSIM of 0.78 for simulated CT. The generative quality is further supported by a Frechet Inception Distance (FID) of 3.62 for CT synthesis. In modality conversion, seg2med achieves SSIM of 0.91 for MR to CT and 0.77 for CT to MR. Anatomical fidelity evaluation shows synthetic CT achieves mean Dice scores above 0.90 for 11 key abdominal organs, and above 0.80 for 34 of 59 total organs. These results underscore seg2med's utility in cross-modality synthesis, data augmentation, and anatomy-aware medical AI.

eess.IV↗

arXiv2025

LiDARDustX: A LiDAR Dataset for Dusty Unstructured Road Environments

Autonomous driving datasets are essential for validating the progress of intelligent vehicle algorithms, which include localization, perception, and prediction. However, existing datasets are predominantly focused on structured urban environments, which limits the exploration of unstructured and specialized scenarios, particularly those characterized by significant dust levels. This paper introduces the LiDARDustX dataset, which is specifically designed for perception tasks under high-dust conditions, such as those encountered in mining areas. The LiDARDustX dataset consists of 30,000 LiDAR frames captured by six different LiDAR sensors, each accompanied by 3D bounding box annotations and point cloud semantic segmentation. Notably, over 80% of the dataset comprises dust-affected scenes. By utilizing this dataset, we have established a benchmark for evaluating the performance of state-of-the-art 3D detection and segmentation algorithms. Additionally, we have analyzed the impact of dust on perception accuracy and delved into the causes of these effects. The data and further information can be accessed at: https://github.com/vincentweikey/LiDARDustX.

cs.CV↗

arXiv2025

UAV-Enabled Secure ISAC Against Dual Eavesdropping Threats: Joint Beamforming and Trajectory Design

In this work, we study an unmanned aerial vehicle (UAV)-enabled secure integrated sensing and communication (ISAC) system, where a UAV serves as an aerial base station (BS) to simultaneously perform communication with a user and detect a target on the ground, while a dual-functional eavesdropper attempts to intercept the signals for both sensing and communication. Facing the dual eavesdropping threats, we aim to enhance the average achievable secrecy rate for the communication user by jointly designing the UAV trajectory together with the transmit information and sensing beamforming, while satisfying the requirements on sensing performance and sensing security, as well as the UAV power and flight constraints. To address the non-convex nature of the optimization problem, we employ the alternating optimization (AO) strategy, jointly with the successive convex approximation (SCA) and semidefinite relaxation (SDR) methods. Numerical results validate the proposed approach, demonstrating its ability to achieve a high secrecy rate while meeting the required sensing and security constraints.

cs.IT↗

arXiv2025

Device-Algorithm Co-Design of Ferroelectric Compute-in-Memory In-Situ Annealer for Combinatorial Optimization Problems

Combinatorial optimization problems (COPs) are crucial in many applications but are computationally demanding. Traditional Ising annealers address COPs by directly converting them into Ising models (known as direct-E transformation) and solving them through iterative annealing. However, these approaches require vector-matrix-vector (VMV) multiplications with a complexity of $O(n^2)$ for Ising energy computation and complex exponential annealing factor calculations during annealing process, thus significantly increasing hardware costs. In this work, we propose a ferroelectric compute-in-memory (CiM) in-situ annealer to overcome aforementioned challenges. The proposed device-algorithm co-design framework consists of (i) a novel transformation method (first to our known) that converts COPs into an innovative incremental-E form, which reduces the complexity of VMV multiplication from $O(n^2)$ to $O(n)$, and approximates exponential annealing factor with a much simplified fractional form; (ii) a double gate ferroelectric FET (DG FeFET)-based CiM crossbar that efficiently computes the in-situ incremental-E form by leveraging the unique structure of DG FeFETs; (iii) %When feasible solutions are detected, a CiM annealer that approaches the solutions of COPs via iterative incremental-E computations within a tunable back gate-based in-situ annealing flow. Evaluation results show that our proposed CiM annealer significantly reduces hardware overhead, reducing energy consumption by 1503/1716$\times$ and time cost by 8.08/8.15$\times$ in solving 3000-node Max-Cut problems compared to two state-of-the-art annealers. It also exhibits high solving efficiency, achieving a remarkable average success rate of 98\%, whereas other annealers show only 50\% given the same iteration counts.

cs.ET↗

arXiv2025

Balanced Mixed-Type Tabular Data Synthesis with Diffusion Models

Diffusion models have emerged as a robust framework for various generative tasks, including tabular data synthesis. However, current tabular diffusion models tend to inherit bias in the training dataset and generate biased synthetic data, which may influence discriminatory actions. In this research, we introduce a novel tabular diffusion model that incorporates sensitive guidance to generate fair synthetic data with balanced joint distributions of the target label and sensitive attributes, such as sex and race. The empirical results demonstrate that our method effectively mitigates bias in training data while maintaining the quality of the generated samples. Furthermore, we provide evidence that our approach outperforms existing methods for synthesizing tabular data on fairness metrics such as demographic parity ratio and equalized odds ratio, achieving improvements of over $10\%$. Our implementation is available at https://github.com/comp-well-org/fair-tab-diffusion.

cs.LG↗

arXiv2025

DeepInteraction++: Multi-Modality Interaction for Autonomous Driving

Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and finally hampering the model performance. To address this limitation, in this work, we introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout, enabling their unique characteristics to be exploited during the whole perception pipeline. To demonstrate the effectiveness of the proposed strategy, we design DeepInteraction++, a multi-modal interaction framework characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Specifically, the encoder is implemented as a dual-stream Transformer with specialized attention operation for information exchange and integration between separate modality-specific representations. Our multi-modal representational learning incorporates both object-centric, precise sampling-based feature alignment and global dense information spreading, essential for the more challenging planning task. The decoder is designed to iteratively refine the predictions by alternately aggregating information from separate representations in a unified modality-agnostic manner, realizing multi-modal predictive interaction. Extensive experiments demonstrate the superior performance of the proposed framework on both 3D object detection and end-to-end autonomous driving tasks. Our code is available at https://github.com/fudan-zvg/DeepInteraction.

cs.CV↗

arXiv2025

"Stupid robot, I want to speak to a human!" User Frustration Detection in Task-Oriented Dialog Systems

Detecting user frustration in modern-day task-oriented dialog (TOD) systems is imperative for maintaining overall user satisfaction, engagement, and retention. However, most recent research is focused on sentiment and emotion detection in academic settings, thus failing to fully encapsulate implications of real-world user data. To mitigate this gap, in this work, we focus on user frustration in a deployed TOD system, assessing the feasibility of out-of-the-box solutions for user frustration detection. Specifically, we compare the performance of our deployed keyword-based approach, open-source approaches to sentiment analysis, dialog breakdown detection methods, and emerging in-context learning LLM-based detection. Our analysis highlights the limitations of open-source methods for real-world frustration detection, while demonstrating the superior performance of the LLM-based approach, achieving a 16\% relative improvement in F1 score on an internal benchmark. Finally, we analyze advantages and limitations of our methods and provide an insight into user frustration detection task for industry practitioners.

cs.CL↗

arXiv2024

Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy

Deep learning models in computer vision have achieved significant success but pose increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of comprehensive understanding of their energy efficiency during inference. In this study, we conduct a comprehensive analysis of the inference energy consumption of 1,200 ImageNet classification models - the largest evaluation of its kind to date. Our findings reveal a steep diminishing return in accuracy gains relative to the increase in energy usage, highlighting sustainability concerns in the pursuit of marginal improvements. We identify key factors contributing to energy consumption and demonstrate methods to improve energy efficiency. To promote more sustainable AI practices, we introduce an energy efficiency scoring system and develop an interactive web application that allows users to compare models based on accuracy and energy consumption. By providing extensive empirical data and practical tools, we aim to facilitate informed decision-making and encourage collaborative efforts in developing energy-efficient AI technologies.

cs.CV↗