Searcharxiv⌕ Search

arXiv subjects

Yihao Wu

Publications and source records attributed to Yihao Wu.

At least 19 recordsLinked to original sources
arXiv2026

Discovering Explicit Magnetic Core Loss Equations via Learnable Symbolic Sparse Identification

Explicit magnetic core loss equations with simple expressions and physical interpretability are significant tools in the design of high-frequency power magnetics. Traditional fits to empirical data like the Steinmetz Equation (SE) often struggle with accuracy, whereas modern machine learning approaches improve precision but deviate from physics. To fill this gap, this paper proposes a Learnable Symbolic Sparse Identification (LSSI) framework for data-driven equation discovery. Specifically, LSSI reformulates magnetic core loss equations for sinusoidal drives as a symbolic regression problem derived directly from experimental data. Building upon the SE, an expanded library of candidate functions are introduced and a sparse identification framework is implemented to select the dominant ones. More importantly, crucial parameters like exponents and coefficients of candidate functions are treated as learnable ones, simultaneously achieving equation simplicity and high expressiveness of the underlying fractional power laws. Experimental results demonstrate that LSSI achieves superior accuracy with a state-of-the-art $\mathbf{R^2}$ of $\mathbf{0.9999}$ and a MAPE of $\mathbf{1.04\%}$ through a highly compact explicit equation containing only $\mathbf{4}$ active terms. Furthermore, it drastically reduces the parameter count from $\mathbf{4417}$ in neural network methods to $\mathbf{15}$, showcasing exceptional compactness and efficiency. The LSSI framework thus provides a physically transparent and highly accurate solution suitable for complex modern magnetic characterization and design.

eess.SY↗
arXiv2026

SCALPEL: Semantic Cross-modal Alignment via LLM-Powered Encoder Learning for Medical Vision-Language Representation

Vision-language pre-training (VLP) serves as a cornerstone for medical multimodal representation learning. However, existing medical VLP frameworks are often constrained by the limited context windows and shallow representational capacities of lightweight text encoders when processing lengthy, terminology-dense clinical reports. While integrating medical large language models (LLMs) offers unprecedented clinical reasoning capabilities, it introduces three major bottlenecks: (i) the anisotropic representational collapse of generative LLMs under standard contrastive objectives, (ii) the prohibitive memory overhead of joint end-to-end training with large batch sizes, and (iii) the medical hallucinations induced by vanilla contrastive losses that ignore fine-grained anatomical laterality and negation modifiers. To address these challenges, we propose \textbf{SCALPEL}, a \textbf{S}emantic \textbf{C}ross-modal \textbf{A}lignment framework via \textbf{L}LM-\textbf{P}owered \textbf{E}ncoder \textbf{L}earning. First, Clinical Report Contrastive fine-tuning converts a generative LLM into an isotropic encoder via domain-specific clinical text adaptation. Second, an asymmetric alignment strategy leverages offline feature caching to enable efficient training. Critically, we formulate an Anatomy-Negation Aware Objective that explicitly penalizes mismatched image-text pairs involving laterality confusion or false negations. Extensive experiments across MIMIC-CXR, CheXpert, and IU X-Ray benchmarks demonstrate that SCALPEL achieves state-of-the-art performance in cross-modal retrieval, zero-shot disease classification and medical visual question answering.

cs.CV↗
arXiv2026

Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen scenes. Although recent multimodal large models and world-model-based methods have improved navigation, they often preserve excessive task-irrelevant detail, weakening generalization and increasing computational burden. We propose BrainNav, a navigation framework grounded in the Principle of Minimal Sufficiency. BrainNav consists of three components: a Logical Anchor Model that implements instruction-aware selective perception to suppress environmental noise, a Minimalist Constraint Alignment module that serves as a compact cross-modal bottleneck, efficiently synchronizing discrete linguistic intent with continuous latent dynamics while filtering out redundant information, and a Compression World Model that predicts action-conditioned states within a condensed, low-rank latent space. These modules align semantic intent with spatial perception, enhancing the agent's robustness and efficiency in complex tasks. Experiments show that BrainNav improves over prior SOTA by 2.0 % / 1.0 in SR/SPL on R2R-CE val-unseen and 0.94 % / 0.78 on RxR-CE val-unseen. These results indicate that minimally sufficient world representations provide an effective foundation for robust VLN.

cs.CV↗
arXiv2026

Probing Lorentz-invariance-violation with quantum coherence of Unruh-DeWitt detector

Testing Lorentz invariance violation (LIV) is notoriously difficult, as its characteristic energy scale, $M_\star$, in modified dispersion relations typically lies beyond current experimental reach. To enable a low-energy probe, we investigate the quantum coherence of an inertial Unruh-DeWitt (UDW) detector interacting with a massless scalar field with a Lorentz-violating dispersion relation $\omega_{|\textbf{k}|}=|\textbf{k}|f(|\textbf{k}|/M_\star)$. Unlike the Lorentz-invariant case where quantum coherence is rapidity-independent, we find for the Lorentz-violating quantum field case the dynamics of detector's quantum coherence exhibits a strong dependence on its rapidity -- offering a potential low-energy signature of LIV. Applying this to the polymer-quantized scalar field theory inspired by loop quantum gravity, we show that the detector's quantum coherence exhibits a pronounced dependence on rapidity and undergoes a sharp transition near a critical rapidity $\beta_c \approx 1.3675$, a value within reach of existing facilities like the Relativistic Heavy Ion Collider. We also show how the detector's rapidity and its energy-level spacing enhance the response to the test of LIV. Our results establish quantum coherence as a sensitive and practical probe of LIV, providing a complementary avenue for testing quantum gravity-induced modifications to field theory.

hep-th↗
arXiv2026

FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization

Post-training Vision-Language-Action (VLA) models into policies that can be reliably deployed on real robots remains a major bottleneck. SFT and DAgger exploit failure signals only indirectly, and reward-based RL is bottlenecked by the difficulty of real-world reward design and of training reliable critics. We present FlowPRO, a reward-free offline reinforced fine-tuning framework for flow-matching VLAs. Algorithmically, we propose RPRO (Robotic Flow-matching Proximalized Preference Optimization), a preference-optimization objective tailored to the flow-matching action head of VLA models. RPRO pairs a contrastive optimizer with an explicit proximal regularizer that anchors the absolute magnitude of the implicit reward, thereby eliminating the reward-hacking failure mode of plain Flow-DPO. On the data side, a teleoperated intervention-and-rollback paradigm produces naturally paired positive and negative trajectories $(\tau^w, \tau^l)$ on a real robot from a single operator action; a Smooth Interpolation procedure, combined with batch mixing, then converts these sparse corrections into dense per-state supervision while preserving the base policy's capabilities. On four long-horizon bimanual tasks, FlowPRO attains the highest success rate, outperforming four representative baselines, and ablations confirm the contribution of each loss component.

cs.RO↗
arXiv2026

LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos

Recovering a dynamic 3D scene from a long monocular video is crucial for dense geometry, camera motion, and temporal correspondence to remain consistent in a shared coordinate system. Existing methods face two key challenges: (1) feed-forward reconstruction models provide accurate local predictions but are limited to short clips, and (2) long-range trackers preserve correspondences without producing dense sequence-level reconstruction. This paper presents LongDPM, a novel overlap-aware framework for scalable long-range monocular dynamic reconstruction. First, LongDPM processes long videos in overlapping chunks, keeping inference memory bounded by the chunk length. Second, it connects chunk-local coordinate systems through confidence-weighted registration with static-aware overlap abstraction. Third, it associates dynamic identities across chunk boundaries and fuses matched trajectories to recover coherent long-range 3D motion. Experimental results demonstrate that LongDPM achieves superior long-range reconstruction and tracking performance, reducing dense tracking EPE over V-DPM on PointOdyssey, Kubric-F, and Kubric-G, while obtaining the best TUM-dynamics ATE for camera pose estimation.

cs.CV↗
arXiv2026

Evaluating the Expressive Appropriateness of Speech in Rich Contexts

Evaluating expressive speech remains challenging, as existing methods mainly assess emotional intensity and overlook whether a speech sample is expressively appropriate for its contextual setting. This limitation hinders reliable evaluation of speech systems used in narrative-driven and interactive applications, such as audiobooks and conversational agents. We introduce CEAEval, a Context-rich framework for Evaluating Expressive Appropriateness in speech, which assesses whether a speech sample expressively aligns with the underlying communicative intent implied by its discourse-level narrative context. To support this task, we construct CEAEval-D, the first context-rich speech dataset with real human performances in Mandarin conversational speech, providing narrative descriptions together with fifteen dimensions of human annotations covering expressive attributes and expressive appropriateness. We further develop CEAEval-M, a model that integrates knowledge distillation, planner-based multi-model collaboration, adaptive audio attention bias, and reinforcement learning to perform context-rich expressive appropriateness evaluation. Experiments on a human-annotated test set demonstrate that CEAEval-M substantially outperforms existing speech evaluation and analysis systems.

eess.AS↗
arXiv2026

Choose What to Manipulate: Revealing Data Scaling Laws in Bounding-Box Guided Policies for Semantic Manipulation

Diffusion-based policies generalize poorly in semantic manipulation, a key obstacle to real-world deployment, because text-only instructions cannot reliably steer the policy toward the target object in cluttered, dynamic scenes. We instead use bounding-box instructions to specify the target directly, and study how performance scales with data. To this end, we build Label-UMI, a handheld segmentation device with an automated annotation pipeline for efficiently collecting semantically labeled demonstrations, and propose a semantic-motion-decoupled framework that couples object detection with a bounding-box-guided diffusion policy; a first-frame anchoring mechanism keeps execution robust to missed detections and noisy boxes. We find that generalization follows a bounded, saturating data-scaling law with diminishing returns, validated on four real-world tasks with 6,400 demonstrations, and distill an object-diversity-first collection strategy reaching 85\% success in cluttered scenes. All data and code will be released.

cs.RO↗
arXiv2026

CogRail: Benchmarking VLMs in Cognitive Intrusion Perception for Intelligent Railway Transportation Systems

Accurate and early perception of potential intrusion targets is essential for ensuring the safety of railway transportation systems. However, most existing systems focus narrowly on object classification within fixed visual scopes and apply rule-based heuristics to determine intrusion status, often overlooking targets that pose latent intrusion risks. Anticipating such risks requires the cognition of spatial context and temporal dynamics for the object of interest (OOI), which presents challenges for conventional visual models. To facilitate deep intrusion perception, we introduce a novel benchmark, CogRail, which integrates curated open-source datasets with cognitively driven question-answer annotations to support spatio-temporal reasoning and prediction. Building upon this benchmark, we conduct a systematic evaluation of state-of-the-art visual-language models (VLMs) using multimodal prompts to identify their strengths and limitations in this domain. Furthermore, we fine-tune VLMs for better performance and propose a joint fine-tuning framework that integrates three core tasks, position perception, movement prediction, and threat analysis, facilitating effective adaptation of general-purpose foundation models into specialized models tailored for cognitive intrusion perception. Extensive experiments reveal that current large-scale multimodal models struggle with the complex spatial-temporal reasoning required by the cognitive intrusion perception task, underscoring the limitations of existing foundation models in this safety-critical domain. In contrast, our proposed joint fine-tuning framework significantly enhances model performance by enabling targeted adaptation to domain-specific reasoning demands, highlighting the advantages of structured multi-task learning in improving both accuracy and interpretability. Code will be available at https://github.com/Hub-Tian/CogRail.

cs.CV↗
arXiv2025

Evaluating Bias in Spoken Dialogue LLMs for Real-World Decisions and Recommendations

While biases in large language models (LLMs), such as stereotypes and cultural tendencies in outputs, have been examined and identified, their presence and characteristics in spoken dialogue models (SDMs) with audio input and output remain largely unexplored. Paralinguistic features, such as age, gender, and accent, can affect model outputs; when compounded by multi-turn conversations, these effects may exacerbate biases, with potential implications for fairness in decision-making and recommendation tasks. In this paper, we systematically evaluate biases in speech LLMs and study the impact of multi-turn dialogues with repeated negative feedback. Bias is measured using Group Unfairness Score (GUS) for decisions and similarity-based normalized statistics rate (SNSR) for recommendations, across both open-source models like Qwen2.5-Omni and GLM-4-Voice, as well as closed-source APIs such as GPT-4o Audio and Gemini-2.5-Flash. Our analysis reveals that closed-source models generally exhibit lower bias, while open-source models are more sensitive to age and gender, and recommendation tasks tend to amplify cross-group disparities. We found that biased decisions may persist in multi-turn conversations. This work provides the first systematic study of biases in end-to-end spoken dialogue models, offering insights towards fair and reliable audio-based interactive systems. To facilitate further research, we release the FairDialogue dataset and evaluation code.

cs.CL↗
arXiv2025

Content Accuracy and Quality Aware Resource Allocation Based on LP-Guided DRL for ISAC-Driven AIGC Networks

Integrated sensing and communication (ISAC) can enhance artificial intelligence-generated content (AIGC) networks by providing efficient sensing and transmission. Existing AIGC services usually assume that the accuracy of the generated content can be ensured, given accurate input data and prompt, thus only the content generation quality (CGQ) is concerned. However, it is not applicable in ISAC-based AIGC networks, where content generation is based on inaccurate sensed data. Moreover, the AIGC model itself introduces generation errors, which depend on the number of generating steps (i.e., computing resources). To assess the quality of experience of ISAC-based AIGC services, we propose a content accuracy and quality aware service assessment metric (CAQA). Since allocating more resources to sensing and generating improves content accuracy but may reduce communication quality, and vice versa, this sensing-generating (computing)-communication three-dimensional resource tradeoff must be optimized to maximize the average CAQA (AvgCAQA) across all users with AIGC (CAQA-AIGC). This problem is NP-hard, with a large solution space that grows exponentially with the number of users. To solve the CAQA-AIGC problem with low complexity, a linear programming (LP) guided deep reinforcement learning (DRL) algorithm with an action filter (LPDRL-F) is proposed. Through the LP-guided approach and the action filter, LPDRL-F can transform the original three-dimensional solution space to two dimensions, reducing complexity while improving the learning performance of DRL. Simulations show that compared to existing DRL and generative diffusion model (GDM) algorithms without LP, LPDRL-F converges faster and finds better resource allocation solutions, improving AvgCAQA by more than 10%. With LPDRL-F, CAQA-AIGC can achieve an improvement in AvgCAQA of more than 50% compared to existing schemes focusing solely on CGQ.

cs.LG↗
arXiv2025

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through iterative error corrections and quality checks to ensure high quality. Unlike existing benchmarks that are limited to specific domains of sound, music, or speech, MMAR extends them to a broad spectrum of real-world audio scenarios, including mixed-modality combinations of sound, music, and speech. Each question in MMAR is hierarchically categorized across four reasoning layers: Signal, Perception, Semantic, and Cultural, with additional sub-categories within each layer to reflect task diversity and complexity. To further foster research in this area, we annotate every question with a Chain-of-Thought (CoT) rationale to promote future advancements in audio reasoning. Each item in the benchmark demands multi-step deep reasoning beyond surface-level understanding. Moreover, a part of the questions requires graduate-level perceptual and domain-specific knowledge, elevating the benchmark's difficulty and depth. We evaluate MMAR using a broad set of models, including Large Audio-Language Models (LALMs), Large Audio Reasoning Models (LARMs), Omni Language Models (OLMs), Large Language Models (LLMs), and Large Reasoning Models (LRMs), with audio caption inputs. The performance of these models on MMAR highlights the benchmark's challenging nature, and our analysis further reveals critical limitations of understanding and reasoning capabilities among current models. We hope MMAR will serve as a catalyst for future advances in this important but little-explored area.

cs.SD↗
arXiv2025

Metadata-private Messaging without Coordination

For those seeking end-to-end private communication free from pervasive metadata tracking and censorship, the Tor network has been the de-facto choice in practice, despite its susceptibility to traffic analysis attacks. Recently, numerous metadata-private messaging proposals have emerged with the aim to surpass Tor in the messaging context by obscuring the relationships between any two messaging buddies, even against global and active attackers. However, most of these systems face an undesirable usability constraint: they require a metadata-private "dialing" phase to establish mutual agreement and timing or round coordination before initiating any regular chats among users. This phase is not only resource-intensive but also inflexible, limiting users' ability to manage multiple concurrent conversations seamlessly. For stringent privacy requirement, the often-enforced traffic uniformity further exacerbated the limitations of this roadblock. In this paper, we introduce PingPong, a new end-to-end system for metadata-private messaging designed to overcome these limitations. Under the same traffic uniformity requirement, PingPong replaces the rigid "dial-before-converse" paradigm with a more flexible "notify-before-retrieval" workflow. This workflow incorporates a metadata-private notification subsystem, Ping, and a metadata-private message store, Pong. Both Ping and Pong leverage hardware-assisted secure enclaves for performance and operates through a series of customized oblivious algorithms, while meeting the uniformity requirements for metadata protection. By allowing users to switch between conversations on demand, PingPong achieves a level of usability akin to modern instant messaging systems, while also offering improved performance and bandwidth utilization for goodput. We have built a prototype of PingPong with 32 8-core servers equipped with enclaves to validate our claims.

cs.CR↗
arXiv2025

MetaWild: A Multimodal Dataset for Animal Re-Identification with Environmental Metadata

Identifying individual animals within large wildlife populations is essential for effective wildlife monitoring and conservation efforts. Recent advancements in computer vision have shown promise in animal re-identification (Animal ReID) by leveraging data from camera traps. However, existing Animal ReID datasets rely exclusively on visual data, overlooking environmental metadata that ecologists have identified as highly correlated with animal behavior and identity, such as temperature and circadian rhythms. Moreover, the emergence of multimodal models capable of jointly processing visual and textual data presents new opportunities for Animal ReID, but existing datasets fail to leverage these models' text-processing capabilities, limiting their full potential. Additionally, to facilitate the use of metadata in existing ReID methods, we propose the Meta-Feature Adapter (MFA), a lightweight module that can be incorporated into existing vision-language model (VLM)-based Animal ReID methods, allowing ReID models to leverage both environmental metadata and visual information to improve ReID performance. Experiments on MetaWild show that combining baseline ReID models with MFA to incorporate metadata consistently improves performance compared to using visual information alone, validating the effectiveness of incorporating metadata in re-identification. We hope that our proposed dataset can inspire further exploration of multimodal approaches for Animal ReID.

cs.CV↗
arXiv2024

An Individual Identity-Driven Framework for Animal Re-Identification

Reliable re-identification of individuals within large wildlife populations is crucial for biological studies, ecological research, and wildlife conservation. Classic computer vision techniques offer a promising direction for Animal Re-identification (Animal ReID), but their backbones' close-set nature limits their applicability and generalizability. Despite the demonstrated effectiveness of vision-language models like CLIP in re-identifying persons and vehicles, their application to Animal ReID remains limited due to unique challenges, such as the various visual representations of animals, including variations in poses and forms. To address these limitations, we leverage CLIP's cross-modal capabilities to introduce a two-stage framework, the \textbf{Indiv}idual \textbf{A}nimal \textbf{ID}entity-Driven (IndivAID) framework, specifically designed for Animal ReID. In the first stage, IndivAID trains a text description generator by extracting individual semantic information from each image, generating both image-specific and individual-specific textual descriptions that fully capture the diverse visual concepts of each individual across animal images. In the second stage, IndivAID refines its learning of visual concepts by dynamically incorporating individual-specific textual descriptions with an integrated attention module to further highlight discriminative features of individuals for Animal ReID. Evaluation against state-of-the-art methods across eight benchmark datasets and a real-world Stoat dataset demonstrates IndivAID's effectiveness and applicability. Code is available at \url{https://github.com/ywu840/IndivAID}.

cs.CV↗
arXiv2024

Geometric phase assisted detection of Lorentz-invariance violation from modified dispersion at high energies

Many theories of quantum gravity propose Lorentz-violating dispersion relations of the form $ω_{|\mathbf{k}|}=|\mathbf{k}|f(|\mathbf{k}|/M_\star)$, which approximately recover to the Lorentz invariance, $ω_{|\mathbf{k}|}\approx|\mathbf{k}|$, at the energy scales much below $M_\star$. However, usually such a scale is assumed to be near the Planck scale, thus the feature of the Lorentz-violating theory is weak and its experimental test becomes extremely challenging. Since the geometric phase (GP) is of accumulative and sensitive nature to weak effects, here we explore the GP acquired by an inertial atomic detector that is coupled to a quantum field with this kind of Lorentz-violating dispersion. We show that for the Lorentz-violating field theory case the GP depends on the velocity of the detector, which is quite different from the Lorentz symmetry case where the GP is independent of the detector's velocity. In particular, we show that the GP may present a drastic low-energy Lorentz violation for any $f$ that dips below unity somewhere. We apply our analysis to detecting the polymer quantization motivated by loop quantum gravity, and show the detector acquires an experimentally detectable GP with the assist of detector's velocity that below current ion collider rapidities. Furthermore, the accumulative nature of GP might facilitate the relevant detection significantly.

hep-th↗
arXiv2024

A Comprehensive Survey on EEG-Based Emotion Recognition: A Graph-Based Perspective

Compared to other modalities, electroencephalogram (EEG) based emotion recognition can intuitively respond to emotional patterns in the human brain and, therefore, has become one of the most focused tasks in affective computing. The nature of emotions is a physiological and psychological state change in response to brain region connectivity, making emotion recognition focus more on the dependency between brain regions instead of specific brain regions. A significant trend is the application of graphs to encapsulate such dependency as dynamic functional connections between nodes across temporal and spatial dimensions. Concurrently, the neuroscientific underpinnings behind this dependency endow the application of graphs in this field with a distinctive significance. However, there is neither a comprehensive review nor a tutorial for constructing emotion-relevant graphs in EEG-based emotion recognition. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of graph-related methods in this field from a methodological perspective. We propose a unified framework for graph applications in this field and categorize these methods on this basis. Finally, based on previous studies, we also present several open challenges and future directions in this field.

eess.SP↗