arXiv subjects

Yifan Feng

Publications and source records attributed to Yifan Feng.

At least 19 recordsLinked to original sources

arXiv2026

Spatial Token Interleaving and Two-Pass BP Decoding for Semantic Image Transmission

Semantic error control coding (SECC) can correct the residual errors of a standard channel code with a foundation model that supplies a prior on the source content, but existing SECC schemes are designed for text. In this paper, we develop SECC for image transmission with spatial token interleaving and a two-pass belief propagation (BP) schedule. At the transmitter, a vector-quantized (VQ) tokenizer converts an image into tokens, which are transmitted in multiple low-density parity-check (LDPC) code blocks of fifth-generation New Radio (5G NR). In raster order, a block that BP fails to decode corrupts consecutive token rows, so the interleaver reorders the tokens such that adjacent tokens are carried by different blocks, without additional transmitted bits. At the receiver, after the first BP pass, token recovery fuses the token probabilities given by BP with the predictions of the autoregressive model Emu3-Gen, and the second BP pass decodes each block again with the fused distributions as priors on the information bits. On Kodak24 at 0.5 channel uses per pixel and a signal-to-noise ratio (SNR) of 0.15 dB, the second pass removes 92% of the token errors left by token recovery, and interleaving reduces the final token error rate by 88%. At medium to high SNR, the proposed receiver exceeds deep joint source--channel coding baselines with the same channel uses by at least 1.2 dB in peak signal-to-noise ratio.

cs.IT↗

arXiv2026

Self-Supervised Passive WiFi CSI-Based Motion Tracking with Physics-Informed Deep SSM

Inferring target position from WiFi channel state information (CSI) is challenging due to the noisy and heterogeneous nature of CSI-derived observations. Measurements such as angle, delay, and Doppler provide only imperfect information about target position and velocity, particularly in dynamic multipath environments where observation reliability varies. Motivated by this challenge, this paper proposes a physics-informed Bayesian state space framework for passive CSI-based tracking. We introduce a context-conditioned deep state space model (DSSM) that captures temporal motion and environmental dynamics, while adaptively modeling time-varying observation uncertainties. By incorporating geometric constraints, this framework enables heterogeneous CSI measurement modalities to jointly regularize the consistency and confidence of the tracking process. Experimental results demonstrate that the proposed framework yields smoother trajectory estimates with reduced temporal fluctuations and outperforms existing methods in tracking accuracy.

eess.SP↗

arXiv2026

A Behavioral Model for Exploration vs. Exploitation: Theoretical Framework and Experimental Evidence

How do people navigate the exploration-exploitation (EE) trade-off when making repeated choices with unknown rewards? We study this question through the lens of multi-armed bandit problems and introduce a novel behavioral model, Quantal Choice with Adaptive Reduction of Exploration (QCARE). It generalizes Thompson Sampling, allowing for a principled way to quantify the EE trade-off and reflect human decision-making patterns. The model adaptively reduces exploration as information accumulates, with the reduction rate serving as a parameter to quantify the EE trade-off dynamics. We theoretically analyze how varying reduction rates influence decision quality, shedding light on the distinct effects of ``over-exploration'' and ``under-exploration.'' Empirically, we validate QCARE using behavioral data collected from human participants. QCARE not only captures critical behavioral patterns in the EE trade-off but also performs competitively with, and often outperforms, alternative models in out-of-sample prediction. Our analysis reveals a behavioral tendency toward over-exploration.

math.OC↗

arXiv2026

Hyper-Fold: Exploring the Expressive Limit of Sequence-Geometry Learning for Proteins via Hypergraph Modeling

Protein structure modeling rests on a single computational primitive: the interaction between what a residue is (sequence content) and where it sits (three-dimensional geometry). What is the expressive limit of this layer class? We show that the complete bilinear operator over content-geometry outer products--the sufficient statistic of all second-order interactions--is the expressive ceiling, while the additive message passing of mainstream geometric GNNs is provably blind to content-geometry binding. We then introduce Hyper-Fold, a rank-K separable convolutional backbone approaching this ceiling at message-passing cost: each radius neighborhood is organized into a sequence hyperedge and a contact hyperedge, modulated by an edge-conditioned matrix-valued operator factorized into K learned basis operators with geometry-generated coefficients. Across enzyme function prediction, fold classification, and ligand binding site detection, Hyper-Fold and its hierarchical variant Hyper-Fold-Deep achieve the best results among protein-specific structure encoders; Hyper-Fold-Pocket, an anchored set-prediction head, surpasses UniSite-3D on UniSite-DS and two zero-shot benchmarks with no sequence language model features, 68x fewer parameters, and 4.8x lower latency--suggesting that a sufficiently expressive 3D backbone recovers information that fusion architectures previously borrowed from evolution-scale pretraining.

cs.AI↗

arXiv2026

Learning to Select and Rank from Choice-Based Feedback: A Simple Nested Approach

We study a ranking and selection problem of learning from choice-based feedback with dynamic assortments. In this problem, a company sequentially displays a set of items to a population of customers and collects their choices as feedback. The only information available about the underlying choice model is that the choice probabilities are consistent with some unknown true strict ranking over the items. The objective is to identify, with the fewest samples, the most preferred item or the full ranking over the items at a high confidence level. We propose novel and simple algorithms for both learning goals through a nested approach. For best-item identification, we introduce Nested Elimination (NE), and for full-ranking identification, we introduce Nested Partition (NP). Both algorithms are fast to run and admit instance-specific, non-asymptotic sample-complexity guarantees. By comparing these guarantees with information-theoretic lower bounds, we establish that both algorithms are asymptotically worst-case optimal. Our analysis is based on an analytical framework that characterizes the system dynamics through analyzing a sequence of multi-dimensional random walks. We further extend the problem to incorporate capacity-constrained displays. Numerical experiments on synthetic and real data corroborate our theory.

cs.LG↗

arXiv2026

Make it SewSimple: Navigating UK Curriculum and Classroom Practice in Secondary Computing Education with E-textiles

This paper explores the potential of integrating e-textiles as part of the approach to delivering computing in UK secondary schools. As one of the few UK-based exploratory studies of teachers experiences, it investigates how e-textile platforms such as the SewSimple maker kit and the BBC micro:bit can be incorporated into Key Stage 3 computing education (ages 11-14), taking into account both English national curriculum requirements and the realities of classroom practice. Our research question is: How do teachers perceive the potential of including e-textiles as part of computing education in English secondary schools? In summary, our research contributes to secondary computing education in three ways. First, we examine teachers direct, cross-disciplinarity experiences in two participatory design workshops using a newly designed e-textile platform and extend the limited discussion on supporting the BBC micro:bit in e-textile education. Second, we specifically identify opportunities, barriers, and challenges across three dimensions: school planning, national curriculum guidance, and practical e-textile implementation. Third, we offer insights into best practices for supporting maker technology adoption and pedagogical practices within existing institutional structures to maximize students' benefits for secondary school computing education.

cs.CY↗

arXiv2026

Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation

Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex n-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains challenging due to the scenario gap: generic extractors struggle to generalize across diverse domains with specific jargon, while existing methods often fail to balance structural skeletons with fine-grained details. To bridge this gap, we propose Hyper-KGGen, a skill-driven framework that reformulates extraction as a dynamic skill-evolving process. First, Hyper-KGGen employs a coarse-to-fine mechanism to systematically decompose documents, ensuring full-dimensional coverage from binary links to complex hyperedges. Crucially, it incorporates an adaptive skill acquisition module that actively distills domain expertise into a Global Skill Library. This is achieved via a stability-based feedback loop, where extraction stability serves as a relative reward signal to induce high-quality skills from unstable traces and missed predictions. Additionally, we present HyperDocRED, a rigorously annotated benchmark for document-level knowledge hypergraph extraction. Experiments demonstrate that Hyper-KGGen significantly outperforms strong baselines, validating that evolved skills provide substantially richer guidance than static few-shot examples in multi-scenario settings.

cs.CL↗

arXiv2026

High-Fidelity 3D Geometric Reconstruction of Pelvic Organs from MRI: A Hybrid Deep Learning and Iterative Optimization Approach

Patient-specific 3D reconstruction of pelvic organ geometry from MRI is important for pelvic floor modeling and downstream patient-specific analysis. However, while previous studies have focused primarily on either image segmentation or downstream use of 3D models, the reconstruction of high-fidelity, high-quality geometries remains labor-intensive and poorly standardized. The study introduced a hybrid deformable shape modeling framework that integrates deep learning prediction with iterative optimization for the reconstruction of the bladder, uterus, and rectum. The framework consists of three core components: a geometry-aware multi-level deep learning architecture that preserves topological consistency of pelvic organs; a two-stage amortized optimization training strategy that balances global shape capture and local surface refinement; and a holistic synergy mechanism--where iterative optimization provides supervision for deep learning during the training phase, and during inference, deep learning rapidly predicts the global organ morphology, followed by iterative optimization to refine local surfaces and mesh quality. This framework demonstrated marked superiority in geometric fidelity than current mainstream deep learning-based organ reconstruction models. For individual anatomical structures, the reconstructed 3D geometries for the bladder, rectum, and uterus achieved significantly lower Chamfer Distance values and higher Dice Similarity Coefficient scores. In addition, while maintaining high computational efficiency, the proposed architecture yielded superior overall volumetric mesh quality. At the patient level, the framework achieved higher mean values for the 10 worst elements for both minSICN and minSIGE compared to traditional geometric post-processing algorithms.

cs.CV↗

arXiv2026

Beyond Pairwise: Empowering LLM Alignment With Ranked Choice Modeling

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from richer forms of human feedback, such as multiway comparisons and top-$k$ rankings. We introduce Ranked Choice Preference Optimization (RCPO), a unified framework that bridges preference optimization with (ranked) choice modeling via maximum likelihood estimation. RCPO supports both utility-based and rank-based models, subsumes several pairwise methods (such as DPO and SimPO) as special cases, and provides principled training objectives for richer feedback formats. We instantiate this framework with two representative models (Multinomial Logit and Mallows-RMJ). Experiments on Llama-3-8B-Instruct, Gemma-2-9B-it, and Mistral-7B-Instruct across in-distribution and out-of-distribution settings show that RCPO consistently outperforms competitive baselines. RCPO shows that directly leveraging ranked preference data, combined with the right choice models, yields more effective alignment. It offers an extensible foundation for incorporating (ranked) choice modeling into LLM training.

cs.LG↗

arXiv2025

Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enhances the response quality and domain-specific performance of large language models (LLMs) by incorporating external knowledge to combat hallucinations. In recent research, graph structures have been integrated into RAG to enhance the capture of semantic relations between entities. However, it primarily focuses on low-order pairwise entity relations, limiting the high-order associations among multiple entities. Hypergraph-enhanced approaches address this limitation by modeling multi-entity interactions via hyperedges, but they are typically constrained to inter-chunk entity-level representations, overlooking the global thematic organization and alignment across chunks. Drawing inspiration from the top-down cognitive process of human reasoning, we propose a theme-aligned dual-hypergraph RAG framework (Cog-RAG) that uses a theme hypergraph to capture inter-chunk thematic structure and an entity hypergraph to model high-order semantic relations. Furthermore, we design a cognitive-inspired two-stage retrieval strategy that first activates query-relevant thematic content from the theme hypergraph, and then guides fine-grained recall and diffusion in the entity hypergraph, achieving semantic alignment and consistent generation from global themes to local details. Our extensive experiments demonstrate that Cog-RAG significantly outperforms existing state-of-the-art baseline approaches.

cs.IR↗

arXiv2025

Hypergraph Foundation Model

Hypergraph neural networks (HGNNs) effectively model complex high-order relationships in domains like protein interactions and social networks by connecting multiple vertices through hyperedges, enhancing modeling capabilities, and reducing information loss. Developing foundation models for hypergraphs is challenging due to their distinct data, which includes both vertex features and intricate structural information. We present Hyper-FM, a Hypergraph Foundation Model for multi-domain knowledge extraction, featuring Hierarchical High-Order Neighbor Guided Vertex Knowledge Embedding for vertex feature representation and Hierarchical Multi-Hypergraph Guided Structural Knowledge Extraction for structural information. Additionally, we curate 11 text-attributed hypergraph datasets to advance research between HGNNs and LLMs. Experiments on these datasets show that Hyper-FM outperforms baseline methods by approximately 13.4%, validating our approach. Furthermore, we propose the first scaling law for hypergraph foundation models, demonstrating that increasing domain diversity significantly enhances performance, unlike merely augmenting vertex and hyperedge counts. This underscores the critical role of domain diversity in scaling hypergraph models.

cs.LG↗

arXiv2025

OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation

Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises. While large language models have made automated report generation technically feasible, systematic research in this specific area remains notably absent, particularly lacking formal task definitions and corresponding benchmarks. To bridge this gap, we define the Automated Online Public Opinion Report Generation (OPOR-GEN) task and construct OPOR-BENCH, an event-centric dataset covering 463 crisis events with their corresponding news articles, social media posts, and a reference summary. To evaluate report quality, we propose OPOR-EVAL, a novel agent-based framework that simulates human expert evaluation by analyzing generated reports in context. Experiments with frontier models demonstrate that our framework achieves high correlation with human judgments. Our comprehensive task definition, benchmark dataset, and evaluation framework provide a solid foundation for future research in this critical domain.

cs.CL↗

arXiv2025

Absorbing Markov Chain-Based Analysis of Age of Information in Discrete-Time Dual-Queue Systems

Status update systems require the timely collection of sensing information for which deploying multiple sensors/servers to obtain diversity gains is considered as a promising solution. In this work, we construct an absorbing Markov chain (AMC) to exactly model Age of Information (AoI) in a discretetime dual-queue (DTDQ) status update system with generate at will (GAW) status updates, discrete phase-type (DPH-type) distributed service times and transmission freezing. Specifically, transmission is frozen for a certain number of slots following the initiation of a transmission, after which one of the two servers is allowed to simultaneously sample the monitored physical process and transmit a status update packet, according to the availabilities and priorities of the two servers. Based on the discrete-time AMC, we provide the exact distributions of both AoI and peak AoI (PAoI), enabling the derivation of arbitrary order moments. In addition, we analytically study the role of freezing using several typical service time distributions, including geometric, uniform, and triangular distributions. The introduction of freezing for DTDQ systems is demonstrated to be significantly beneficial in reducing the mean AoI for various service time distributions. Additionally, we study the impact of the statistical parameters of the service times and heterogeneity between the two servers on the freezing gain, i.e., reduction in mean AoI attained with optimum freezing policies.

cs.IT↗

arXiv2025

Animate-X++: Universal Character Image Animation with Dynamic Backgrounds

Character image animation, which generates high-quality videos from a reference image and target pose sequence, has seen significant progress in recent years. However, most existing methods only apply to human figures, which usually do not generalize well on anthropomorphic characters commonly used in industries like gaming and entertainment. Furthermore, previous methods could only generate videos with static backgrounds, which limits the realism of the videos. For the first challenge, our in-depth analysis suggests to attribute this limitation to their insufficient modeling of motion, which is unable to comprehend the movement pattern of the driving video, thus imposing a pose sequence rigidly onto the target character. To this end, this paper proposes Animate-X++, a universal animation framework based on DiT for various character types, including anthropomorphic characters. To enhance motion representation, we introduce the Pose Indicator, which captures comprehensive motion pattern from the driving video through both implicit and explicit manner. The former leverages CLIP visual features of a driving video to extract its gist of motion, like the overall movement pattern and temporal relations among motions, while the latter strengthens the generalization of DiT by simulating possible inputs in advance that may arise during inference. For the second challenge, we introduce a multi-task training strategy that jointly trains the animation and TI2V tasks. Combined with the proposed partial parameter training, this approach achieves not only character animation but also text-driven background dynamics, making the videos more realistic. Moreover, we introduce a new Animated Anthropomorphic Benchmark (A2Bench) to evaluate the performance of Animate-X++ on universal and widely applicable animation images. Extensive experiments demonstrate the superiority and effectiveness of Animate-X++.

cs.CV↗

arXiv2025

Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation

Large language models (LLMs) have transformed various sectors, including education, finance, and medicine, by enhancing content generation and decision-making processes. However, their integration into the medical field is cautious due to hallucinations, instances where generated content deviates from factual accuracy, potentially leading to adverse outcomes. To address this, we introduce Hyper-RAG, a hypergraph-driven Retrieval-Augmented Generation method that comprehensively captures both pairwise and beyond-pairwise correlations in domain-specific knowledge, thereby mitigating hallucinations. Experiments on the NeurologyCrop dataset with six prominent LLMs demonstrated that Hyper-RAG improves accuracy by an average of 12.3% over direct LLM use and outperforms Graph RAG and Light RAG by 6.3% and 6.0%, respectively. Additionally, Hyper-RAG maintained stable performance with increasing query complexity, unlike existing methods which declined. Further validation across nine diverse datasets showed a 35.5% performance improvement over Light RAG using a selection-based assessment. The lightweight variant, Hyper-RAG-Lite, achieved twice the retrieval speed and a 3.3% performance boost compared with Light RAG. These results confirm Hyper-RAG's effectiveness in enhancing LLM reliability and reducing hallucinations, making it a robust solution for high-stakes applications like medical diagnostics.

cs.IR↗

arXiv2025

Optimal Partition for Multi-Type Queueing System

We study an optimal server partition and customer assignment problem for an uncapacitated FCFS queueing system with heterogeneous types of customers. Each type of customers is associated with a Poisson arrival, a certain service time distribution, and a unit waiting cost. The goal is to minimize the expected total waiting cost by partitioning the server into sub-queues, each with a smaller service capacity, and routing customer types probabilistically. First, we show that by properly partitioning the queue, it is possible to reduce the expected waiting costs by an arbitrarily large ratio. Then, we show that for any given server partition, the optimal customer assignment admits a certain geometric structure, enabling an efficient algorithm to find the optimal assignment. Such an optimal structure also applies when minimizing the expected sojourn time. Finally, we consider the joint partition-assignment optimization problem. The customer assignment under the optimal server partition admits a stronger structure. Specifically, if the first two moments of the service time distributions satisfy certain properties, it is optimal to deterministically assign customer types with consecutive service rates to the same sub-queue. This structure allows for more efficient algorithms. Overall, the common rule of thumb to partition customers into continuous segments ranked by service rates could be suboptimal, and our work is the first to comprehensively study the queue partition problem based on customer types.

math.OC↗

arXiv2024

FFA Sora, video generation as fundus fluorescein angiography simulator

Fundus fluorescein angiography (FFA) is critical for diagnosing retinal vascular diseases, but beginners often struggle with image interpretation. This study develops FFA Sora, a text-to-video model that converts FFA reports into dynamic videos via a Wavelet-Flow Variational Autoencoder (WF-VAE) and a diffusion transformer (DiT). Trained on an anonymized dataset, FFA Sora accurately simulates disease features from the input text, as confirmed by objective metrics: Frechet Video Distance (FVD) = 329.78, Learned Perceptual Image Patch Similarity (LPIPS) = 0.48, and Visual-question-answering Score (VQAScore) = 0.61. Specific evaluations showed acceptable alignment between the generated videos and textual prompts, with BERTScore of 0.35. Additionally, the model demonstrated strong privacy-preserving performance in retrieval evaluations, achieving an average Recall@K of 0.073. Human assessments indicated satisfactory visual quality, with an average score of 1.570(scale: 1 = best, 5 = worst). This model addresses privacy concerns associated with sharing large-scale FFA data and enhances medical education.

cs.CV↗

arXiv2024

Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation

We introduce Hyper-YOLO, a new object detection method that integrates hypergraph computations to capture the complex high-order correlations among visual features. Traditional YOLO models, while powerful, have limitations in their neck designs that restrict the integration of cross-level features and the exploitation of high-order feature interrelationships. To address these challenges, we propose the Hypergraph Computation Empowered Semantic Collecting and Scattering (HGC-SCS) framework, which transposes visual feature maps into a semantic space and constructs a hypergraph for high-order message propagation. This enables the model to acquire both semantic and structural information, advancing beyond conventional feature-focused learning. Hyper-YOLO incorporates the proposed Mixed Aggregation Network (MANet) in its backbone for enhanced feature extraction and introduces the Hypergraph-Based Cross-Level and Cross-Position Representation Network (HyperC2Net) in its neck. HyperC2Net operates across five scales and breaks free from traditional grid structures, allowing for sophisticated high-order interactions across levels and positions. This synergy of components positions Hyper-YOLO as a state-of-the-art architecture in various scale models, as evidenced by its superior performance on the COCO dataset. Specifically, Hyper-YOLO-N significantly outperforms the advanced YOLOv8-N and YOLOv9-T with 12\% $\text{AP}^{val}$ and 9\% $\text{AP}^{val}$ improvements. The source codes are at ttps://github.com/iMoonLab/Hyper-YOLO.

cs.CV↗