arXiv subjects

Yutong Zheng

Publications and source records attributed to Yutong Zheng.

17 recordsLinked to original sources

arXiv2026

UniVerse: Benchmarking and Enhancing LALMs on Culturally Inclusive Low-Resource Music Understanding

Recent advances in large audio-language models (LALMs) have significantly improved performance in tasks such as music captioning, genre classification, and sound event detection. However, limited attention has been paid to improving their adaptability across diverse musical traditions, particularly folk music rooted in distinct cultural contexts. Folk-music traditions are typically resource-scarce, unevenly represented across regions, and poorly documented. Even when such samples appear in large-scale pre-training, LALMs often fail to capture their structural and stylistic characteristics, partly due to the absence of dedicated evaluation protocols and training solutions. To address these limitations, we introduce UniVerse, a reproducible solution for low-resource music understanding. Specifically, we propose UniVerseBench, a benchmark of 5,042 Q&A pairs across more than 38 cultural and linguistic entities, constructed via an expert-guided yet highly automated pipeline. In parallel, we construct a fully automated, model-generated multi-turn dialogue training dataset UniVerseSet. By training LALMs on UniVerseSet, we systematically adapt and investigate representative multimodal imbalance learning strategies across both dense and Mixture-of-Experts (MoE) architectures. Experimental results indicate that fully automated data curation combined with imbalance-aware training yields non-trivial improvements, but models still struggle to capture fine-grained acoustic features, indicating a gap between surface-level alignment and deep musical comprehension.

cs.SD↗

arXiv2026

X-Foresight: A Joint Vision-Action Causal Forecasting Network via Predictive World Modeling

Physical world knowledge resides mainly in videos. Equipping Vision-Language-Action (VLA) models with such knowledge is fundamental for safe and generalizable planning. Predictive world modeling enables VLA to internalize physical dynamics and long-term causality by predicting future video from past observations. However, naive next-frame prediction faces two challenges: 1) unlike semantically distinct text tokens, video tokens are low-entropy and redundant, causing prediction to degenerate into trivial extrapolation. 2) world modeling poses a temporal dilemma: dense prediction captures instantaneous dynamics, but cannot efficiently model long-horizon causality. To learn world knowledge effectively, we introduce X-Foresight, a predictive world model integrated directly into the VLA architecture to jointly learn world modeling and real-time action control. At its core lies a long-horizon chunk-wise auto-regressive strategy that addresses both challenges: by predicting semantically distant chunks rather than adjacent frames, it escapes trivial extrapolation, while preserving dense intra-chunk frames for instantaneous dynamics and sparse inter-chunk transitions for long-term causality. A curriculum learning schedule progressively extends prediction horizons and stabilizes long-horizon training. To capture long-term causality effectively, we present temporal importance sampling, which concentrates supervision on safety-critical chunks identified by ego-motion and behavioral signals. We further delegate photorealistic synthesis to a diffusion-based multi-view renderer, improving photorealistic appearance. Comprehensive experiments demonstrate that X-Foresight significantly outperforms VLA baselines in planning performance while maintaining strong generative fidelity, establishing a robust paradigm for world-knowledge-driven autonomous systems.

cs.CV↗

arXiv2026

X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving

Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relying instead on reactive perception-action mapping. While integrating Predictive World Models (PWMs) addresses this gap, existing approaches either incur prohibitive cascaded latency or act as shallow terminal tasks that fail to deeply embed forward-looking reasoning. To endow VLA models with this reasoning capability, we propose X-Mind. Rather than treating PWMs as an external auxiliary module, this framework internalizes them as the Visual Chain-of-Thought (Visual CoT). By enforcing a world rollout prior to action, the model is constrained to imagine future evolution first, yielding a driving policy that is robustly grounded in environmental dynamics and aware of the future consequences its actions will unfold. The challenge here is efficiency, and we tackle it on two fronts. First, we introduce a compact representation of visual thinking: an abstract sketch that fuses a Bird's-Eye-View (BEV) layout with abstract driving priors (e.g., navigation intents and traffic rules). Rather than rolling out dense future frames, the model reasons over this sketch as a mental canvas; aided by a Deep Compression Autoencoder (DC-AE), a 12-frame future rollout is reduced to merely 96 tokens, alleviating the long-context computational bottleneck. Second, to accelerate generation further, we propose a recurrent block diffusion scheme that unrolls the denoising steps across the layers of the large drive model, folding iterative refinement into the backbone's one forward pass. Trained and validated on large-scale real-world data, X-Mind achieves competitive end-to-end driving performance, which makes it a highly practical, low-latency solution that successfully deploys large-scale cognitive reasoning directly onto resource-constrained vehicle platforms.

cs.CV↗

arXiv2026

Exact-Penalty Prox-Linear Methods for Bilevel Optimization with $\ell_1$ Lower-Level Gradient Penalty

Bilevel optimization is a fundamental framework for hierarchical decision-making, but its solution is challenging due to the implicit and typically set-valued nature of the lower-level optimality condition. In this paper, we study bilevel optimization problems through an exact-penalty reformulation based on the $\ell_1$-norm of the lower-level gradient. Under suitable regularity assumptions, we show that this penalty defines a distance-bound function and yields an exact penalty property for sufficiently large penalty parameters. To solve the resulting nonsmooth penalized problem, we propose an exact-penalty prox-linear (EPPL) method and establish a stationarity-oriented convergence guarantee. We further specialize the method to the simple bilevel setting, where the subproblem admits an explicit dual reformulation as a box-constrained quadratic program. This structure leads to a dual spectral projected gradient method with closed-form primal recovery, for which convergence of the inner dual iterates is proved. Numerical experiments on a minimum-norm least-squares bilevel model show that the proposed method is effective in reducing both the lower-level and upper-level gaps to high accuracy. Compared with several existing methods, the proposed approach attains the best final solution accuracy on the tested instance.

math.OC↗

arXiv2026

ScenePilot-4K: A Large-Scale First-Person Dataset and Benchmark for Vision-Language Models in Autonomous Driving

In this paper, we introduce ScenePilot-4K, a large-scale first-person dataset for safety-aware vision-language learning and evaluation in autonomous driving. Built from public online driving videos, ScenePilot-4K contains 3,847 hours of video and 27.7M front-view frames spanning 63 countries/regions and 1,210 cities. It jointly provides scene-level natural-language descriptions, risk assessment labels, key-participant annotations, ego trajectories, and camera parameters through a unified multi-stage annotation pipeline. Building on this dataset, we establish ScenePilot-Bench, a standardized benchmark that evaluates vision-language models along four complementary axes: scene understanding, spatial perception, motion planning, and GPT-based semantic alignment. The benchmark includes fine-grained metrics and geographic generalization settings that expose model robustness under cross-region and cross-traffic domain shifts. Baseline results on representative open-source and proprietary vision-language models show that current models remain competitive in high-level scene semantics but still exhibit substantial limitations in geometry-aware perception and planning-oriented reasoning. Beyond the released dataset itself, the proposed annotation pipeline serves as a reusable and extensible recipe for scalable dataset construction from public Internet driving videos. The codes and supplementary materials are available at: https://github.com/yjwangtj/ScenePilot-4K, with the dataset available at https://huggingface.co/datasets/larswangtj/ScenePilot-4K.

cs.CV↗

arXiv2026

Joint Training Scattering Matrix Learning and Channel Estimation for Beyond-Diagonal Reconfigurable Intelligent Surfaces

Beyond-diagonal reconfigurable intelligent surface (BD-RIS) generalizes the conventional diagonal RIS (D-RIS) by introducing tunable inter-element connections, offering enhanced wave manipulation capabilities. However, realizing the advantages of BD-RIS requires accurate channel state information (CSI), whose acquisition becomes significantly more challenging due to the increased number of channel coefficients, leading to prohibitively large pilot training overhead in BD-RIS-aided multi-user multiple-input multiple-output (MU-MIMO) systems. Existing studies reduce pilot overhead by exploiting the channel correlations induced by the Kronecker-product or multi-linear structure of BD-RIS-aided channels, which neglect the spatial correlation among antennas and the statistical correlation across RIS-user channels. In this paper, we propose a learning-based channel estimation framework, namely the joint training scattering matrix learning and channel estimation framework (JTSMLCEF), which jointly optimizes the BD-RIS training scattering matrix and estimates the cascaded channels in an end-to-end manner to achieve accurate channel estimation and reduce the pilot overhead. The proposed JTSMLCEF follows a two-phase channel estimation protocol to enable adaptive training scattering matrix optimization with a training scattering matrix optimizer (TSMO) and cascaded channel estimation with a dual-attention channel estimator (DACE). Specifically, the DACE is designed with intra-user and inter-user attention modules to capture the multi-dimensional correlations in multi-user cascaded channels. Simulation results demonstrate the superiority of JTSMLCEF. Compared with the current state-of-the-art method, it reduces the pilot overhead by $80\%$ while further reducing the normalized mean squared error (NMSE) by $82.6\%$ and $92.5\%$ in indoor and urban micro-cell (UMi) scenarios, respectively.

eess.SP↗

arXiv2026

Voices of Civilizations: A Multilingual QA Benchmark for Global Music Understanding

We introduce Voices of Civilizations, the first multilingual QA benchmark for evaluating audio LLMs' cultural comprehension on full-length music recordings. Covering 380 tracks across 38 languages, our automated pipeline yields 1,190 multiple-choice questions through four stages - each followed by manual verification: 1) compiling a representative music list; 2) generating cultural-background documents for each sample in the music list via LLMs; 3) extracting key attributes from those documents; and 4) constructing multiple-choice questions probing language, region associations, mood, and thematic content. We evaluate models under four conditions and report per-language accuracy. Our findings demonstrate that even state-of-the-art audio LLMs struggle to capture subtle cultural nuances without rich textual context and exhibit systematic biases in interpreting music from different cultural traditions. The dataset is publicly available on Hugging Face to foster culturally inclusive music understanding research.

cs.SD↗

arXiv2025

Bilevel Models for Adversarial Learning and A Case Study

Adversarial learning has been attracting more and more attention thanks to the fast development of machine learning and artificial intelligence. However, due to the complicated structure of most machine learning models, the mechanism of adversarial attacks is not well interpreted. How to measure the effect of attacks is still not quite clear. In this paper, we investigate the adversarial learning from the perturbation analysis point of view. We characterize the robustness of learning models through the calmness of the solution mapping. In the case of convex clustering models, we identify the conditions under which the clustering results remain the same under perturbations. When the noise level is large, it leads to an attack. Therefore, we propose two bilevel models for adversarial learning where the effect of adversarial learning is measured by some deviation function. Specifically, we systematically study the so-called $δ$-measure and show that under certain conditions, it can be used as a deviation function in adversarial learning for convex clustering models. Finally, we conduct numerical tests to verify the above theoretical results as well as the efficiency of the two proposed bilevel models.

cs.LG↗

arXiv2024

From an attention economy to an ecology of attending. A manifesto

As the signatories of this manifesto, we denounce the attention economy as inhumane and a threat to our sociopolitical and ecological well-being. We endorse policymakers' efforts to address the negative consequences of the attention economy's technology, but add that these approaches are often limited in their criticism of the systemic context of human attention. Starting from Buddhist philosophy, we advocate a broader approach: an ecology of attending, that centers on conceptualizing, designing, and using attention (1) in an embedded way and (2) focused on the alleviating of suffering. With 'embedded' we mean that attention is not a neutral, isolated mechanism but a meaning-engendering part of an 'ecology' of bodily, sociotechnical and moral frameworks. With 'focused on the alleviation of suffering' we explicitly move away from the (often implicit) conception of attention as a tool for gratifying desires.

cs.CY↗

arXiv2024

A Reference-Based 3D Semantic-Aware Framework for Accurate Local Facial Attribute Editing

Facial attribute editing plays a crucial role in synthesizing realistic faces with specific characteristics while maintaining realistic appearances. Despite advancements, challenges persist in achieving precise, 3D-aware attribute modifications, which are crucial for consistent and accurate representations of faces from different angles. Current methods struggle with semantic entanglement and lack effective guidance for incorporating attributes while maintaining image integrity. To address these issues, we introduce a novel framework that merges the strengths of latent-based and reference-based editing methods. Our approach employs a 3D GAN inversion technique to embed attributes from the reference image into a tri-plane space, ensuring 3D consistency and realistic viewing from multiple perspectives. We utilize blending techniques and predicted semantic masks to locate precise edit regions, merging them with the contextual guidance from the reference image. A coarse-to-fine inpainting strategy is then applied to preserve the integrity of untargeted areas, significantly enhancing realism. Our evaluations demonstrate superior performance across diverse editing tasks, validating our framework's effectiveness in realistic and applicable facial attribute editing.

cs.CV↗

arXiv2023

Detecting subtle macroscopic changes in a finite temperature classical scalar field with machine learning

The ability to detect macroscopic changes is important for probing the behaviors of experimental many-body systems from the classical to the quantum realm. Although abrupt changes near phase boundaries can easily be detected, subtle macroscopic changes are much more difficult to detect as the changes can be obscured by noise. In this study, as a toy model for detecting subtle macroscopic changes in many-body systems, we try to differentiate scalar field samples at varying temperatures. We compare different methods for making such differentiations, from physics method, statistics method, to AI method. Our finding suggests that the AI method outperforms both the statistical method and the physics method in its sensitivity. Our result provides a proof-of-concept that AI can potentially detect macroscopic changes in many-body systems that elude physical measures.

cond-mat.stat-mech↗

arXiv2022

Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling

In recent works, utilizing a deep network trained on meta-training set serves as a strong baseline in few-shot learning. In this paper, we move forward to refine novel-class features by finetuning a trained deep network. Finetuning is designed to focus on reducing biases in novel-class feature distributions, which we define as two aspects: class-agnostic and class-specific biases. Class-agnostic bias is defined as the distribution shifting introduced by domain difference, which we propose Distribution Calibration Module(DCM) to reduce. DCM owes good property of eliminating domain difference and fast feature adaptation during optimization. Class-specific bias is defined as the biased estimation using a few samples in novel classes, which we propose Selected Sampling(SS) to reduce. Without inferring the actual class distribution, SS is designed by running sampling using proposal distributions around support-set samples. By powering finetuning with DCM and SS, we achieve state-of-the-art results on Meta-Dataset with consistent performance boosts over ten datasets from different domains. We believe our simple yet effective method demonstrates its possibility to be applied on practical few-shot applications.

cs.CV↗

arXiv2021

Unsupervised Disentanglement of Linear-Encoded Facial Semantics

We propose a method to disentangle linear-encoded facial semantics from StyleGAN without external supervision. The method derives from linear regression and sparse representation learning concepts to make the disentangled latent representations easily interpreted as well. We start by coupling StyleGAN with a stabilized 3D deformable facial reconstruction method to decompose single-view GAN generations into multiple semantics. Latent representations are then extracted to capture interpretable facial semantics. In this work, we make it possible to get rid of labels for disentangling meaningful facial semantics. Also, we demonstrate that the guided extrapolation along the disentangled representations can help with data augmentation, which sheds light on handling unbalanced data. Finally, we provide an analysis of our learned localized facial representations and illustrate that the semantic information is encoded, which surprisingly complies with human intuition. The overall unsupervised design brings more flexibility to representation learning in the wild.

cs.CV↗

arXiv2019

Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement

Generic Image recognition is a fundamental and fairly important visual problem in computer vision. One of the major challenges of this task lies in the fact that single image usually has multiple objects inside while the labels are still one-hot, another one is noisy and sometimes missing labels when annotated by humans. In this paper, we focus on tackling these challenges accompanying with two different image recognition problems: multi-model ensemble and noisy data recognition with a unified framework. As is well-known, usually the best performing deep neural models are ensembles of multiple base-level networks, as it can mitigate the variation or noise containing in the dataset. Unfortunately, the space required to store these many networks, and the time required to execute them at runtime, prohibit their use in applications where test sets are large (e.g., ImageNet). In this paper, we present a method for compressing large, complex trained ensembles into a single network, where the knowledge from a variety of trained deep neural networks (DNNs) is distilled and transferred to a single DNN. In order to distill diverse knowledge from different trained (teacher) models, we propose to use adversarial-based learning strategy where we define a block-wise training loss to guide and optimize the predefined student network to recover the knowledge in teacher models, and to promote the discriminator network to distinguish teacher vs. student features simultaneously. Extensive experiments on CIFAR-10/100, SVHN, ImageNet and iMaterialist Challenge Dataset demonstrate the effectiveness of our MEAL method. On ImageNet, our ResNet-50 based MEAL achieves top-1/5 21.79%/5.99% val error, which outperforms the original model by 2.06%/1.14%. On iMaterialist Challenge Dataset, our MEAL obtains a remarkable improvement of top-3 1.15% (official evaluation metric) on a strong baseline model of ResNet-101.

cs.CV↗

arXiv2018

Ring loss: Convex Feature Normalization for Face Recognition

We motivate and present Ring loss, a simple and elegant feature normalization approach for deep networks designed to augment standard loss functions such as Softmax. We argue that deep feature normalization is an important aspect of supervised classification problems where we require the model to represent each class in a multi-class problem equally well. The direct approach to feature normalization through the hard normalization operation results in a non-convex formulation. Instead, Ring loss applies soft normalization, where it gradually learns to constrain the norm to the scaled unit circle while preserving convexity leading to more robust features. We apply Ring loss to large-scale face recognition problems and present results on LFW, the challenging protocols of IJB-A Janus, Janus CS3 (a superset of IJB-A Janus), Celebrity Frontal-Profile (CFP) and MegaFace with 1 million distractors. Ring loss outperforms strong baselines, matches state-of-the-art performance on IJB-A Janus and outperforms all other results on the challenging Janus CS3 thereby achieving state-of-the-art. We also outperform strong baselines in handling extremely low resolution face matching.

cs.CV↗

arXiv2017

Towards a Deep Learning Framework for Unconstrained Face Detection

Robust face detection is one of the most important pre-processing steps to support facial expression analysis, facial landmarking, face recognition, pose estimation, building of 3D facial models, etc. Although this topic has been intensely studied for decades, it is still challenging due to numerous variants of face images in real-world scenarios. In this paper, we present a novel approach named Multiple Scale Faster Region-based Convolutional Neural Network (MS-FRCNN) to robustly detect human facial regions from images collected under various challenging conditions, e.g. large occlusions, extremely low resolutions, facial expressions, strong illumination variations, etc. The proposed approach is benchmarked on two challenging face detection databases, i.e. the Wider Face database and the Face Detection Dataset and Benchmark (FDDB), and compared against recent other face detection methods, e.g. Two-stage CNN, Multi-scale Cascade CNN, Faceness, Aggregate Chanel Features, HeadHunter, Multi-view Face Detection, Cascade CNN, etc. The experimental results show that our proposed approach consistently achieves highly competitive results with the state-of-the-art performance against other recent face detection methods.

cs.CV↗

arXiv2016

CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection

Robust face detection in the wild is one of the ultimate components to support various facial related problems, i.e. unconstrained face recognition, facial periocular recognition, facial landmarking and pose estimation, facial expression recognition, 3D facial model construction, etc. Although the face detection problem has been intensely studied for decades with various commercial applications, it still meets problems in some real-world scenarios due to numerous challenges, e.g. heavy facial occlusions, extremely low resolutions, strong illumination, exceptionally pose variations, image or video compression artifacts, etc. In this paper, we present a face detection approach named Contextual Multi-Scale Region-based Convolution Neural Network (CMS-RCNN) to robustly solve the problems mentioned above. Similar to the region-based CNNs, our proposed network consists of the region proposal component and the region-of-interest (RoI) detection component. However, far apart of that network, there are two main contributions in our proposed network that play a significant role to achieve the state-of-the-art performance in face detection. Firstly, the multi-scale information is grouped both in region proposal and RoI detection to deal with tiny face regions. Secondly, our proposed network allows explicit body contextual reasoning in the network inspired from the intuition of human vision system. The proposed approach is benchmarked on two recent challenging face detection databases, i.e. the WIDER FACE Dataset which contains high degree of variability, as well as the Face Detection Dataset and Benchmark (FDDB). The experimental results show that our proposed approach trained on WIDER FACE Dataset outperforms strong baselines on WIDER FACE Dataset by a large margin, and consistently achieves competitive results on FDDB against the recent state-of-the-art face detection methods.

cs.CV↗