arXiv subjects

Feng Wu

Publications and source records attributed to Feng Wu.

At least 73 records · Page 4Linked to original sources

arXiv2025

UniSOT: A Unified Framework for Multi-Modality Single Object Tracking

Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference modalities enable various human-machine interactions, and different video modalities are demanded in complex scenarios to enhance tracking robustness. Existing trackers are designed for single or several video modalities with single or several reference modalities, which leads to separate model designs and limits practical applications. Practically, a unified tracker is needed to handle various requirements. To the best of our knowledge, there is still no tracker that can perform tracking with these above reference modalities across these video modalities simultaneously. Thus, in this paper, we present a unified tracker, UniSOT, for different combinations of three reference modalities and four video modalities with uniform parameters. Extensive experimental results on 18 visual tracking, vision-language tracking and RGB+X tracking benchmarks demonstrate that UniSOT shows superior performance against modality-specific counterparts. Notably, UniSOT outperforms previous counterparts by over 3.0\% AUC on TNL2K across all three reference modalities and outperforms Un-Track by over 2.0\% main metric across all three RGB+X video modalities.

cs.CV↗

arXiv2025

Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process

Developing effective multimodal fusion approaches has become increasingly essential in many real-world scenarios, such as health care and finance. The key challenge is how to preserve the feature expressiveness in each modality while learning cross-modal interactions. Previous approaches primarily focus on the cross-modal alignment, while over-emphasis on the alignment of marginal distributions of modalities may impose excess regularization and obstruct meaningful representations within each modality. The Dirichlet process (DP) mixture model is a powerful Bayesian non-parametric method that can amplify the most prominent features by its richer-gets-richer property, which allocates increasing weights to them. Inspired by this unique characteristic of DP, we propose a new DP-driven multimodal learning framework that automatically achieves an optimal balance between prominent intra-modal representation learning and cross-modal alignment. Specifically, we assume that each modality follows a mixture of multivariate Gaussian distributions and further adopt DP to calculate the mixture weights for all the components. This paradigm allows DP to dynamically allocate the contributions of features and select the most prominent ones, leveraging its richer-gets-richer property, thus facilitating multimodal feature fusion. Extensive experiments on several multimodal datasets demonstrate the superior performance of our model over other competitors. Ablation analysis further validates the effectiveness of DP in aligning modality distributions and its robustness to changes in key hyperparameters. Code is anonymously available at https://github.com/HKU-MedAI/DPMM.git

cs.LG↗

arXiv2025

GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images

While recent multimodal large language models (MLLMs) have advanced automated ECG interpretation, they still face two key limitations: (1) insufficient multimodal synergy between time series signals and visual ECG representations, and (2) limited explainability in linking diagnoses to granular waveform evidence. We introduce GEM, the first MLLM unifying ECG time series, 12-lead ECG images and text for grounded and clinician-aligned ECG interpretation. GEM enables feature-grounded analysis, evidence-driven reasoning, and a clinician-like diagnostic process through three core innovations: a dual-encoder framework extracting complementary time series and image features, cross-modal alignment for effective multimodal understanding, and knowledge-guided instruction generation for generating high-granularity grounding data (ECG-Grounding) linking diagnoses to measurable parameters ($e.g.$, QRS/PR Intervals). Additionally, we propose the Grounded ECG Understanding task, a clinically motivated benchmark designed to comprehensively assess the MLLM's capability in grounded ECG understanding. Experimental results on both existing and our proposed benchmarks show GEM significantly improves predictive performance (CSN $7.4\% \uparrow$), explainability ($22.7\% \uparrow$), and grounding ($24.8\% \uparrow$), making it more suitable for real-world clinical applications. GitHub repository: https://github.com/lanxiang1017/GEM.git

cs.CL↗

arXiv2025

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

Image captioning is a fundamental task that bridges the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with Supervised Fine-Tuning (SFT), a paradigm that relies on expensive, non-scalable data annotated by humans or proprietary models. This approach often leads to models that memorize specific ground-truth answers, limiting their generality and ability to generate diverse, creative descriptions. To overcome the limitation of SFT, we propose applying the Reinforcement Learning with Verifiable Rewards (RLVR) paradigm to the open-ended task of image captioning. A primary challenge, however, is designing an objective reward function for the inherently subjective nature of what constitutes a "good" caption. We introduce Captioning Reinforcement Learning (CapRL), a novel training framework that redefines caption quality through its utility: a high-quality caption should enable a non-visual language model to accurately answer questions about the corresponding image. CapRL employs a decoupled two-stage pipeline where an LVLM generates a caption, and the objective reward is derived from the accuracy of a separate, vision-free LLM answering Multiple-Choice Questions based solely on that caption. As the first study to apply RLVR to the subjective image captioning task, we demonstrate that CapRL significantly enhances multiple settings. Pretraining on the CapRL-5M caption dataset annotated by CapRL-3B results in substantial gains across 12 benchmarks. Moreover, within the Prism Framework for caption quality evaluation, CapRL achieves performance comparable to Qwen2.5-VL-72B, while exceeding the baseline by an average margin of 8.4%. Code is available here: https://github.com/InternLM/CapRL.

cs.CV↗

arXiv2025

In-Loop Filtering Using Learned Look-Up Tables for Video Coding

In-loop filtering (ILF) is a key technology in video coding standards to reduce artifacts and enhance visual quality. Recently, neural network-based ILF schemes have achieved remarkable coding gains, emerging as a powerful candidate for next-generation video coding standards. However, the use of deep neural networks (DNN) brings significant computational and time complexity or high demands for dedicated hardware, making it challenging for general use. To address this limitation, we study a practical ILF solution by adopting look-up tables (LUTs). After training a DNN with a restricted reference range for ILF, all possible inputs are traversed, and the output values of the DNN are cached into LUTs. During the coding process, the filtering process is performed by simply retrieving the filtered pixel through locating the input pixels and interpolating between the cached values, instead of relying on heavy inference computations. In this paper, we propose a universal LUT-based ILF framework, termed LUT-ILF++. First, we introduce the cooperation of multiple kinds of filtering LUTs and propose a series of customized indexing mechanisms to enable better filtering reference perception with limited storage consumption. Second, we propose the cross-component indexing mechanism to enable the filtering of different color components jointly. Third, in order to make our solution practical for coding uses, we propose the LUT compaction scheme to enable the LUT pruning, achieving a lower storage cost of the entire solution. The proposed framework is implemented in the VVC reference software. Experimental results show that the proposed framework achieves on average 0.82%/2.97%/1.63% and 0.85%/4.11%/2.06% bitrate reduction for common test sequences, under the AI and RA configurations, respectively. Compared to DNN-based solutions, our proposed solution has much lower time complexity and storage cost.

eess.IV↗

arXiv2025

High-efficiency infrared upconversion imaging with nonlinear silicon metasurfaces empowered by quasi-bound states in the continuum

Infrared imaging is indispensable for its ability to penetrate obscurants and visualize thermal signatures, yet its practical use is hindered by the intrinsic limitations of conventional detectors. Nonlinear upconversion, which converts infrared light into the visible band, offers a promising pathway to address these challenges. Here, we demonstrate high-efficiency infrared upconversion imaging using nonlinear silicon metasurfaces. By strategically breaking in-plane symmetry, the metasurface supports a high-$Q$ quasi-bound states in the continuum resonance, leading to strongly enhanced third-harmonic generation (THG) with a conversion efficiency of $3\times10^{-5}$ at a pump intensity of 10 GW/cm$^{2}$. Through this THG process, the metasurface enables high-fidelity upconversion of arbitrary infrared images into the visible range, achieving a spatial resolution of $\sim 6$ $\upmu$m as verified using a resolution target and various customized patterns. This work establishes a robust platform for efficient nonlinear conversion and imaging, highlighting the potential of CMOS-compatible silicon metasurfaces for high-performance infrared sensing applications with reduced system complexity.

physics.optics↗

arXiv2025

Louvre: Relaxing Hardware Requirements of Quantum LDPC Codes by Routing with Expanded Quantum Instruction Set

Generalized bicycle codes (GB codes) represent a promising family of quantum low-density parity-check codes, characterized by high code rates and relatively local qubit connectivity. A subclass of the GB code called bivariate bicycle codes (BB codes) has garnered significant interest due to their compatibility with two-layer connectivity architectures on superconducting quantum processors. However, one key limitation of BB codes is their high qubit connectivity degree requirements (degree 6), which exacerbates the noise susceptibility of the system. Building on the recent progress in implementing multiple two-qubit gates on a single chip, this work introduces Louvre -- a routing-based framework designed to reduce qubit connectivity requirements in GB codes. Specifically, Louvre-7 achieves degree reduction while preserving the depth of the syndrome extraction circuit, whereas Louvre-8 further minimizes the connectivity by slightly increasing the circuit depth. When applied to BB codes, these two schemes could reduce the average degree to 4.5 and 4, respectively. Crucially, Louvre eliminates some of the long-range, error-prone connections, which is a distinct advantage over prior approaches. Numerical simulations demonstrate that Louvre-7 has an indistinguishable logical error rate as the standard syndrome extraction circuits of GB codes, while Louvre-8 only incurs a slight error rate penalty. Furthermore, by reordering some of the gates in the circuit, we can reduce the coupler length without degrading the performance. Though most of our analysis focuses on GB codes defined on periodic boundary conditions, we further discuss the adaptability of Louvre to open-boundary lattices and defect-containing grids, underscoring its broader applicability in practical quantum error correction architectures.

quant-ph↗

arXiv2025

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation

Neuron segmentation from electron microscopy (EM) volumes is crucial for understanding brain circuits, yet the complex neuronal structures in high-resolution EM images present significant challenges. EM data exhibits unique characteristics including high noise levels, anisotropic voxel dimensions, and ultra-long spatial dependencies that make traditional vision models inadequate. Inspired by autoregressive pretraining in language models, we propose TokenUnify, a hierarchical predictive coding framework that captures multi-scale dependencies through three complementary learning objectives. TokenUnify integrates random token prediction, next-token prediction, and next-all token prediction to create a comprehensive representational space with emergent properties. From an information-theoretic perspective, these three tasks are complementary and provide optimal coverage of visual data structure, with our approach reducing autoregressive error accumulation from O(K) to O(sqrt(K)) for sequences of length K. We also introduce a large-scale EM dataset with 1.2 billion annotated voxels, offering ideal long-sequence visual data with spatial continuity. Leveraging the Mamba architecture's linear-time sequence modeling capabilities, TokenUnify achieves a 44% performance improvement on downstream neuron segmentation and outperforms MAE by 25%. Our approach demonstrates superior scaling properties as model size increases, effectively bridging the gap between pretraining strategies for language and vision models.

cs.CV↗

arXiv2025

Scaling Learned Image Compression Models up to 1 Billion

Recent advances in large language models (LLMs) highlight a strong connection between intelligence and compression. Learned image compression, a fundamental task in modern data compression, has made significant progress in recent years. However, current models remain limited in scale, restricting their representation capacity, and how scaling model size influences compression performance remains unexplored. In this work, we present a pioneering study on scaling up learned image compression models and revealing the performance trends through scaling laws. Using the recent state-of-the-art HPCM model as baseline, we scale model parameters from 68.5 millions to 1 billion and fit power-law relations between test loss and key scaling variables, including model size and optimal training compute. The results reveal a scaling trend, enabling extrapolation to larger scale models. Experimental results demonstrate that the scaled-up HPCM-1B model achieves state-of-the-art rate-distortion performance. We hope this work inspires future exploration of large-scale compression models and deeper investigations into the connection between compression and intelligence.

cs.CV↗

arXiv2025

One Step Beyond: Feedthrough & Placement-Aware Rectilinear Floorplanner

Floorplanning determines the shapes and locations of modules on a chip canvas and plays a critical role in optimizing the chip's Power, Performance, and Area (PPA) metrics. However, existing floorplanning approaches often fail to integrate with subsequent physical design stages, leading to suboptimal in-module component placement and excessive inter-module feedthrough. To tackle this challenge, we propose Flora, a three-stage feedthrough and placement aware rectilinear floorplanner. In the first stage, Flora employs wiremask and position mask techniques to achieve coarse-grained optimization of HPWL and feedthrough. In the second stage, under the constraint of a fixed outline, Flora achieves a zero-whitespace layout by locally resizing module shapes, thereby performing fine-grained optimization of feedthrough and improving component placement. In the third stage, Flora utilizes a fast tree search-based method to efficiently place components-including macros and standard cells-within each module, subsequently adjusting module boundaries based on the placement results to enable cross-stage optimization. Experimental results show that Flora outperforms recent state-of-the-art floorplanning approaches, achieving an average reduction of 6% in HPWL, 5.16% in FTpin, 29.15% in FTmod, and a 14% improvement in component placement performance.

cs.RO↗

arXiv2025

Piano: A Multi-Constraint Pin Assignment-Aware Floorplanner

Floorplanning is a critical step in VLSI physical design, increasingly complicated by modern constraints such as fixed-outline requirements, whitespace removal, and the presence of pre-placed modules. In addition, the assignment of pins on module boundaries significantly impacts the performance of subsequent stages, including detailed placement and routing. However, traditional floorplanners often overlook pin assignment with modern constraints during the floorplanning stage. In this work, we introduce Piano, a floorplanning framework that simultaneously optimizes module placement and pin assignment under multiple constraints. Specifically, we construct a graph based on the geometric relationships among modules and their netlist connections, then iteratively search for shortest paths to determine pin assignments. This graph-based method also enables accurate evaluation of feedthrough and unplaced pins, thereby guiding overall layout quality. To further improve the design, we adopt a whitespace removal strategy and employ three local optimizers to enhance layout metrics under multi-constraint scenarios. Experimental results on widely used benchmark circuits demonstrate that Piano achieves an average 6.81% reduction in HPWL, a 13.39% decrease in feedthrough wirelength, a 16.36% reduction in the number of feedthrough modules, and a 21.21% drop in unplaced pins, while maintaining zero whitespace.

cs.AR↗

arXiv2025

Partition Map-Based Fast Block Partitioning for VVC Inter Coding

Among the new techniques of Versatile Video Coding (VVC), the quadtree with nested multi-type tree (QT+MTT) block structure yields significant coding gains by providing more flexible block partitioning patterns. However, the recursive partition search in the VVC encoder increases the encoder complexity substantially. To address this issue, we propose a partition map-based algorithm to pursue fast block partitioning in inter coding. Based on our previous work on partition map-based methods for intra coding, we analyze the characteristics of VVC inter coding, and thus improve the partition map by incorporating an MTT mask for early termination. Next, we develop a neural network that uses both spatial and temporal features to predict the partition map. It consists of several special designs including stacked top-down and bottom-up processing, quantization parameter modulation layers, and partitioning-adaptive warping. Furthermore, we present a dual-threshold decision scheme to achieve a fine-grained trade-off between complexity reduction and rate-distortion (RD) performance loss. The experimental results demonstrate that the proposed method achieves an average 51.30% encoding time saving with a 2.12% Bjontegaard Delta Bit Rate (BDBR) under the random access configuration.

eess.IV↗

arXiv2025

Alleviating User-Sensitive bias with Fair Generative Sequential Recommendation Model

Recommendation fairness has recently attracted much attention. In the real world, recommendation systems are driven by user behavior, and since users with the same sensitive feature (e.g., gender and age) tend to have the same patterns, recommendation models can easily capture the strong correlation preference of sensitive features and thus cause recommendation unfairness. Diffusion model (DM) as a new generative model paradigm has achieved great success in recommendation systems. DM's ability to model uncertainty and represent diversity, and its modeling mechanism has a high degree of adaptability with the real-world recommendation process with bias. Therefore, we use DM to effectively model the fairness of recommendation and enhance the diversity. This paper proposes a FairGENerative sequential Recommendation model based on DM, FairGENRec. In the training phase, we inject random noise into the original distribution under the guidance of the sensitive feature recognition model, and a sequential denoise model is designed for the reverse reconstruction of items. Simultaneously, recommendation fairness modeling is completed by injecting multi-interests representational information that eliminates the bias of sensitive user features into the generated results. In the inference phase, the model obtains the noise in the form of noise addition by using the history interactions which is followed by reverse iteration to reconstruct the target item representation. Finally, our extensive experiments on three datasets demonstrate the dual enhancement effect of FairGENRec on accuracy and fairness, while the statistical analysis of the cases visualizes the degree of improvement on the fairness of the recommendation.

cs.IR↗

arXiv2025

Quasi-Bound States in the Continuum-Induced Second Harmonic Generation Enhancement in High-$Q$ Triple Dielectric Nanoresonators

High-$Q$ optical nanocavities are fundamental to modern optics and photonics, enabling enhanced light-matter interactions. Previous studies have demonstrated that high-$Q$ supercavity modes can be constructed within a single dielectric resonator by leveraging quasi-bound states in the continuum. However, their $Q$-factors are limited to few tens or hundreds when such a resonator is subwavelength scale. Here, we propose a general recipe for achieving high-$Q$ resonances with $Q>10,000$ in triple subwavelength dielectric resonators. This is realized through destructive interference between two resonant modes, optimized by structural tuning. Multipole analysis confirms that destructive interference across radiation channels suppresses loss, forming the ultrahigh-$Q$ states. These resonances can be efficiently excited by azimuthally polarized light due to improved mode overlap. As a key application, we demonstrate efficient second harmonic generation under this excitation, achieving a conversion efficiency of $6.6\%$ at an incident intensity of 0.78 GW/cm$^2$. Our results may find exciting applications in developing ultracompact photonic devices with superior performance.

physics.optics↗

arXiv2025

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

This paper presents ScaleCap, an inference-time scalable image captioning strategy that generates comprehensive and detailed image captions. The key challenges of high-quality image captioning lie in the inherent biases of LVLMs: multimodal bias resulting in imbalanced descriptive granularity, offering detailed accounts of some elements while merely skimming over others; linguistic bias leading to hallucinated descriptions of non-existent objects. To address these issues, we propose a scalable debiased captioning strategy, which continuously enriches and calibrates the caption with increased inference budget. Specifically, we propose two novel components: heuristic question answering and contrastive sentence rating. The former generates content-specific questions based on the image and answers them to progressively inject relevant information into the caption. The latter employs sentence-level offline contrastive decoding to effectively identify and eliminate hallucinations caused by linguistic biases. With increased inference cost, more heuristic questions are raised by ScaleCap to progressively capture additional visual details, generating captions that are more accurate, balanced, and informative. Extensive modality alignment experiments demonstrate the effectiveness of ScaleCap. Annotating 450K images with ScaleCap and using them for LVLM pretraining leads to consistent performance gains across 11 widely used benchmarks. Furthermore, ScaleCap showcases superb richness and fidelity of generated captions with two additional tasks: replacing images with captions in VQA task, and reconstructing images from captions to assess semantic coverage. Code is available at https://github.com/Cooperx521/ScaleCap.

cs.CV↗

arXiv2025

Coherent Goos-H$\ddot{a}$nchen shifts of meta-grating with radiation asymmetry

The coherent Goos-H$\ddot{a}$nchen shifts of meta-grating are proposed, which is the Goos-H$\ddot{a}$nchen shifts of the two outgoing beams under the simultaneous incidence of two coherent optical beams from opposite sides of the grating with the same lateral wave number. As both of the frequency and lateral wave number are resonant with a topological state of the meta-grating, such as unidirectionally guided resonance or circular polarized states, the energy flux and Goos-H$\ddot{a}$nchen shifts of the two outgoing beams are coherently controlled by the relative phase difference between the two incident beams. By applying stationary-phase method, it is found that the enhancement of coherent Goos-H$\ddot{a}$nchen shifts by the unidirectionally guided resonance and circular polarized states is accompanied by constant and peak transmittance, respectively. Analysis with temporal coupled mode theory shows that the different features are due to difference mechanism of interference between direction scattering and resonant radiation. The coherent Goos-H$\ddot{a}$nchen shifts with incident Gaussian beams are sensitive to the relative phase between the two beams, which can be applied in refractive index sensor.

physics.optics↗

arXiv2025

Booster Gym: An End-to-End Reinforcement Learning Framework for Humanoid Robot Locomotion

Recent advancements in reinforcement learning (RL) have led to significant progress in humanoid robot locomotion, simplifying the design and training of motion policies in simulation. However, the numerous implementation details make transferring these policies to real-world robots a challenging task. To address this, we have developed a comprehensive code framework that covers the entire process from training to deployment, incorporating common RL training methods, domain randomization, reward function design, and solutions for handling parallel structures. This library is made available as a community resource, with detailed descriptions of its design and experimental results. We validate the framework on the Booster T1 robot, demonstrating that the trained policies seamlessly transfer to the physical platform, enabling capabilities such as omnidirectional walking, disturbance resistance, and terrain adaptability. We hope this work provides a convenient tool for the robotics community, accelerating the development of humanoid robots. The code can be found in https://github.com/BoosterRobotics/booster_gym.

cs.RO↗

arXiv2025

Cross-architecture universal feature coding via distribution alignment

Feature coding has become increasingly important in scenarios where semantic representations rather than raw pixels are transmitted and stored. However, most existing methods are architecture-specific, targeting either CNNs or Transformers. This design limits their applicability in real-world scenarios where features from both architectures coexist. To address this gap, we introduce a new research problem: cross-architecture universal feature coding (CAUFC), which seeks to build a unified codec that can effectively compress features from heterogeneous architectures. To tackle this challenge, we propose a two-step distribution alignment method. First, we design the format alignment method that unifies CNN and Transformer features into a consistent 2D token format. Second, we propose the feature value alignment method that harmonizes statistical distributions via truncation and normalization. As a first attempt to study CAUFC, we evaluate our method on the image classification task. Experimental results demonstrate that our method achieves superior rate-accuracy trade-offs compared to the architecture-specific baseline. This work marks an initial step toward universal feature compression across heterogeneous model architectures.

cs.CV↗