Search arXiv⌕ Search

arXiv subjects

Kang Yang

Publications and source records attributed to Kang Yang.

At least 19 recordsLinked to original sources
arXiv2026

Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation

Recent audio-video generators increasingly support joint conditioning on text, images, audio, and video. These capabilities also enable attacks that exploit cross-modal interactions or obscure harmful intent to bypass safeguards and induce harmful audio-video outputs. However, existing generation-safety benchmarks have not kept pace with these advances, providing limited coverage of multimodal input combinations and obscured attack intents. To address these gaps, we introduce Multi2AV-Safety, the first full-coverage red-team benchmark for multimodal-to-audio-video generation, comprising 11,024 attack instances across all 11 non-singleton T/I/A/V conditioning configurations, 4 attack-intent categories, and 5 harm categories. Our evaluation of recent state-of-the-art models, including four multimodal-conditioned audio-video generators and eight safety guards, reveals substantial vulnerabilities in both generation and safeguarding, with multimodal compositional risk and obscured attack-intent risk emerging as two complementary challenges. Guided by these findings, we introduce PerceptGuard, an omni-modal guard integrating compositional-risk and attack-intent supervision through structured risk perception learning. By jointly training rationale generation and safety classification, it learns shared risk representations that enable a safety head to make efficient predictions at inference without rationale decoding, while retaining the ability to generate explanations on demand. Across 34 safety benchmarks, PerceptGuard combines SOTA multimodal safety detection with highly competitive unimodal performance, strengthening input-side safeguards against multimodal attacks on omni models. In particular, it improves safeguarding against the above risks, achieving an overall recall of 86.06\% on Multi2AV-Safety and outperforming GuardReasoner-Omni by 14.56\%.

cs.AI↗
arXiv2026

LR-V2X: Loss-Resilient Collaborative Perception under Low-Bandwidth Communication

Given the inherent unpredictability of packet loss in vehicular wireless communications, V2X collaborative perception can yield practical benefits only if agents can achieve reliable collaboration under lossy and low-bandwidth communication conditions. Existing dense BEV feature fusion methods depend on redundant BEV feature exchange, which is infeasible in low-bandwidth scenarios, while compact-communication methods aggressively compress messages but can hardly recover the missing feature content after packet loss. In this paper, we present LR-V2X, a loss-resilient, latent-space reconstruction framework that converts corrupted received latents (even under severe 90% packet loss) into a spatial prior and then reconstructs the missing BEV information from this informative prior and using ego context as condition. Notably, the model can be trained under complete communication conditions and can be directly applied to lossy conditions at test time, eliminating the need for training under numerous lossy conditions. Experiments on DAIR-V2X and V2XREAL show that LR-V2X delivers the strongest robustness under severe packet loss and preserves reliable collaboration as communication quality degrades. And it reduces communication overhead by $64\times$ compared to dense BEV feature fusion baselines. Code will be released at https://github.com/sidiangongyuan/LR-V2X.

cs.CV↗
arXiv2026

Spontaneous Chern-Euler Duality Transitions

Topological phase transitions are typically characterized by abrupt changes in a quantized invariant. Here we report a contrasting paradigm in spontaneous parity-time symmetry-breaking transitions induced by non-Hermiticity. The topological invariant remains conserved, but its nature transitions between the Chern number, characteristic of chiral transport in complex bands, and the Euler number, which characterizes the number of nodal points in pairs of real bands. This conserved morphing of topological properties applies to all pairs of bands whose spectral gaps to other bands remain open during the transition. It features qualitative changes in the non-Abelian geometric phases, which quantize in different forms across the transition. Our findings establish a generic topological duality principle governing transitions across symmetry classes and reveal unique connections among topology, symmetry, and non-Abelian gauge structure in non-unitary processes.

cond-mat.mes-hall↗
arXiv2026

Understanding Gaps in LLM Pipelines Towards Scalable Fuzzing Harness Generation: An Empirical Study and Enhancement

Large language model (LLM)-based techniques have achieved notable progress in fuzz harness generation. However, applying them to arbitrary functions \textit{at scale} remains difficult---generated harnesses often fail to compile or, worse, compile but remain logically ineffective. What factors drive success and what limitations hinder current methods remain unclear. To answer these questions, we conduct an empirical study on state-of-the-art LLM-based harness generation frameworks across 29 OSS-Fuzz projects. Our study establishes two pillars of success: contextual information to guide generation and pre-structured pipelines that ensure workflow stability. However, significant gaps remain: (1) existing context retrieval methods lack the robustness to reliably obtain necessary information across diverse projects; (2) current validation mechanisms fail to detect logically ineffective harnesses, such as those containing fabricated definitions; and (3) compilation workflows are brittle, unable to distinguish harness-level errors from build-configuration issues. We demonstrate the utility of these findings by enhancing existing techniques with a hybrid tool pool for robust context retrieval, an enhanced validation pipeline, and a compilation-error triage strategy. Evaluated on 243 OSS-Fuzz projects (65 C and 178 C++), the enhanced approach improves the three-shot success rate by approximately 20\% over state-of-the-art techniques, reaching 87\% for C and 81\% for C++. Our one-hour fuzzing results show that more than 75\% of the generated harnesses increase target-function coverage, surpassing baselines by over 10\%. In addition, the enhanced approach identified 15 new vulnerabilities across 11 real-world projects.

cs.CR↗
arXiv2026

Dynamical Parameters: An Interpretability Framework for Time-Series Foundation Models

This work studies a central gap in interpreting time-series foundation models (TSFMs): a dynamical property may be accessible in a hidden state even when the forecast fails to respond correctly as that property changes. We formalize these properties as Dynamical Parameters, including trend slope, oscillation frequency, and autoregressive dependence. We compare their representation accessibility, measured by recovery from hidden states, with their forecast response, measured by agreement with the expected forecast change. Across nine frozen TSFMs and thirteen laws, 42 of 63 model-parameter cells achieve accessibility above 0.95, whereas their median reference-aligned response relative to the conditional reference is only 0.46. To explain this gap, causal geometry compares the hidden-state change required to produce the reference response with the change induced by the parameter intervention. Directly modifying the hidden state recovers the reference response, but the parameter intervention often moves the state in a different direction. These results show that accessible parameter information need not be expressed in forecasts when input changes miss the required hidden-state direction.

cs.AI↗
arXiv2026

CoRF: Cross-Scene RF Synthesis by Learning Propagation and Preserving Array Physics

Existing radio-frequency (RF) neural fields fit each scene separately, making new-scene deployment measurement- and optimization-intensive. This work studies amortized cross-scene spatial spectrum synthesis, where a shared model learns propagation across scenes and instantiates an unseen scene from sparse target-scene measurements without scene-specific training. To achieve this, CoRF separates learned scene-dependent propagation from the known receiver-array observation model. An unordered set of spectrum-only references conditions a canonical anchor field, producing arrival directions and query-dependent component powers for each query. Analytic array physics maps these components to the receiver covariance and then to the spatial spectrum. This factorization keeps the pretrained propagation model frozen, enabling synthesis at arbitrary query locations after a single reference-conditioning pass. A necessary local reference-capacity bound and an error decomposition further characterize the formulation. Across 35 simulated scenes spanning seven categories, CoRF outperforms the strongest baseline by 7.09 dB PSNR on unseen variants of represented scene categories and by 6.97 dB on entirely unseen scene categories.

cs.NI↗
arXiv2026

CoVLM-Bench: A Real-World Benchmark for Cooperative Driving Question Answering and Planning

Vision-language models (VLMs) have made substantial progress in autonomous driving, but their success has primarily been studied in ego-centric scenes. Infrastructure-side observations provide views beyond the ego vehicle's field of view, yet conventional cooperative-driving systems typically transform them into geometric representations for downstream perception and planning. Directly incorporating these views into VLMs offers an opportunity to improve cooperative scene understanding and trajectory planning. However, question answering and trajectory planning have not been jointly evaluated on the same real-world vehicle-infrastructure scenes. We present CoVLM-Bench, a benchmark for cooperative driving question answering (CDQA) and cooperative planning (CP) on vehicle-infrastructure paired scenes. CoVLM-Bench provides scene-grounded CDQA annotations, three-part rationales as auxiliary supervision, and future trajectory targets derived from recorded ego motion. It contains 2,196 paired frames with 35,136 CDQA annotations, while CP predicts six waypoints over a three-second horizon. The annotations combine model-assisted drafting, record-based computation, and human verification. Built upon CoVLM-Bench, we introduce CoVLM-Drive, a unified VLM baseline that directly uses paired views for both CDQA and CP. Experiments show that CDQA adaptation improves answer accuracy and that CoVLM-Drive reaches a lower FDE than the compared V2X planners; QA initialization and rationale supervision each reduce planning error. Together, CoVLM-Bench and CoVLM-Drive support the training and comparison of VLMs for cooperative scene understanding and planning.

cs.CV↗
arXiv2026

Beyond Direct Sensing: Harnessing Indirect Observations from Third-Party Sensors in Vehicle Tracking

Vehicle tracking is fundamental to applications ranging from urban mobility and public safety to security and defense. Conventional tracking relies on direct access to sensors that provide strong observations such as vehicle identity and location. In practice, however, factors such as ownership, privacy, cost, and operational constraints may limit directly accessible sensors, leaving sparse observations and long tracking gaps. Meanwhile, many additional third-party sensing assets may be present across the environment but remain inaccessible at the raw-data level, preventing their direct integration into the tracking system. In this work, we investigate whether weak, indirect observations with uncertain spatial and temporal cues can complement sparse direct sensing for vehicle tracking. Specifically, we propose GrayTrack, which fuses weak anonymous events with sparse direct observations using a road-constrained particle filter. We build a CARLA-Mininet-WiFi pipeline to evaluate the system under controlled conditions, generating direct observations from accessible cameras and indirect observations from third-party cameras. Our learning-based detector achieves an F1 score of 0.989 for anonymous vehicle passages. Further, incorporating indirect third-party observations reduces trajectory RMSE by 60.1% and catastrophic track loss from 35.8% to 0.3%. These results demonstrate that GrayTrack can effectively exploit weak indirect observations to extend tracking capabilities.

eess.SP↗
arXiv2026

FuseFi: Combining Irregularly Sampled CSI from Diverse Communication Packets and Frequency Bands for Wi-Fi Sensing

Existing Wi-Fi sensing systems rely on injecting high-rate probing packets to extract channel state information (CSI), leading to communication degradation and limited deployment flexibility. Although Integrated Sensing and Communication (ISAC) is a promising direction, existing solutions still rely on auxiliary packet injection because they exploit only uniform CSI from a single frame type, discarding approximately 70% of naturally available packets. We present FuseFi, a novel Wi-Fi-based ISAC framework that directly exploits irregularly sampled CSI from diverse communication packets across multiple frequency bands, eliminating intrusive packet injection and introducing no sensing-specific communication overhead. FuseFi integrates a CSI sanitization pipeline to harmonize heterogeneous packets and remove burst-induced redundancy, together with a time-aware attention model that learns directly from non-uniform CSI sequences without resampling. We further introduce CommCSI-HAR, a new dataset with irregularly sampled CSI from real-world dual-band communication traffic. Extensive evaluations on this dataset and, separately, on four public sensing tasks across three benchmark datasets show that FuseFi achieves state-of-the-art accuracy with a compact model size, while fully preserving communication throughput.

eess.SP↗
arXiv2026

Scaling Online Complex Event Detection with Synthetic Supervision and Mamba-Based Neural Algorithmic Reasoning

Modern machine learning models excel at detecting individual actions, sounds, or scene attributes from short, localized observations. However, many real-world tasks, such as in smart cities and healthcare, require reasoning over high-level complex events (CEs): spatiotemporal, rule-governed patterns of short-term atomic events (AEs). Complex event detection (CED) is challenging due to long temporal dependencies, generalization beyond the training horizon, sparse CE-level supervision without temporally aligned fine-grained AE labels, and cognitively demanding annotation, as CE labels often depend on ordering, duration, negation, and completion-time semantics. These challenges are further amplified in an online setting that requires causal, streaming inference with limited computation. We identify the primary bottleneck in online CED as learning robust CE rules, and propose a Neural Algorithmic Reasoning framework that decouples rule learning from low-level sensor semantics by (i) generating large-scale synthetic AE-level concept traces to pretrain a Mamba-based CE-rule reasoner, and (ii) introducing an adapter that learns to map raw sensor inputs into the reasoner's latent space using limited, labeled sensor data. We introduce a controlled simulator-generated online multilabel CED testbed built from real-world multimodal sensor clips and rule-generated CE labels, with stress-test settings that vary sensor noise, distribution shift, and the window size used to segment streaming sensor sequences. Experiments on this controlled benchmark show that NAROCE is competitive with the strongest baselines and often outperforms them under these stress tests and longer-horizon generalization, while using 5x fewer labeled sensor sequences and 10-20x fewer FLOPs than all non-Mamba baselines. Code and dataset available at https://github.com/nesl/naroce_dailyoce.

cs.LG↗
arXiv2026

BOLT: Online Lightweight Adaptation for Preparation-Free Heterogeneous Cooperative Perception

Most existing heterogeneous cooperative perception methods depend on prior preparation like offline joint training or tailored collaborator-model adaptation. Such preprocessing is, however, generally impractical in real scenarios, as agents are usually independently trained by different developers and meet occasionally online. This work investigates \emph{preparation-free heterogeneous cooperative perception}, where agents use independently trained single-agent detectors without any pre-deployment coordination. We find direct cross-agent fusion under this setting greatly underperforms ego-only perception. We present BOLT, a lightweight plug-and-play module that adapts neighboring features online via ego-as-teacher distillation, requiring only ego predictions without ground-truth labels. BOLT leverages high-confidence ego perception features to guide cross-agent feature-domain alignment, while enabling neighbors to contribute features in the ego's low-confidence regions. With only 0.9M trainable parameters, BOLT improves AP@50 by up to 32.3 points over vanilla unadapted fusion in the preparation-free setting. It consistently outperforms ego-only results on DAIR-V2X and OPV2V, across different encoder pairs and fusion strategies. Code: https://github.com/sidiangongyuan/BOLT.

cs.CV↗
arXiv2026

SA-RSQ: A Versatile Sparse Representation Framework for Multi-modal Recommender Systems

Deploying high-dimensional multimodal features in industrial recommender systems incurs substantial storage and latency overhead. Hard quantization is compact but introduces boundary distortion, whereas dense soft quantization couples representation quality to the limited storage budget. We propose Sparse Activation-based Residual Soft Quantization (SA-RSQ), which uses Top-K sparse routing and softmax weights to store compact (Index, Probability) tuples. The stored tuples decouple per-item storage from codebook dimensionality; for a fixed selected support, gradients propagate through the routing weights and weighted reconstruction without relying on a straight-through estimator. Experiments on a proprietary food-delivery advertising dataset show favorable reconstruction-performance and CTR trade-offs across storage budgets of 8-48 bytes per item. A preliminary Next-Distribution Prediction study and a one-week online A/B test further demonstrate the practical potential of SA-RSQ, with relative lifts of +2.51% in CTR and +3.66% in CPM.

cs.AI↗
arXiv2026

Second-Chern Bounds in Non-Abelian Quantum Geometry

We study the quantum geometry of doubly degenerate energy levels in a four-dimensional parameter space. We find that the scalar quantum metric $g$ and the Berry curvature $F$ obey $(\operatorname{tr} g)^2/16\geq\sqrt{\det g}\geq |2\Tr(F\wedge F)-\Tr F\wedge \Tr F|/24$. The first inequality characterizes the anisotropy in the metric. The second determinant inequality measures the self-duality of the traceless $SU(2)$ part of the curvature under Hodge star operation and the algebraic closedness of the inter-level polarization amplitudes under $SU(2)$ rotations in the doubly degenerate levels. The saturation of the determinant bound imposes a quaternionic Cauchy-Riemann equation, analogous to the complex analyticity imposed by ideal-band conditions in two-dimensional Chern insulators. As examples, four-band Dirac Hamiltonians automatically saturate the determinant bound and possess a topological zero in $\operatorname{tr}(F\wedge F)$. We compare the differences between Kramers degeneracy and ordinary $U(2)$ degeneracy. In addition to the non-Abelian geometric bound, the latter also obeys an independent first-Chern bound.

cond-mat.mes-hall↗
arXiv2026

Robustness of real-space topology in moiré systems

The appearance of fractional Chern insulators in moiré systems can be rationalized by the presence of a fictitious magnetic field associated with the spatial texture of layer-resolved electronic wavefunctions. Here, we present a systematic study of real-space topology and the associated fictitious magnetic fields in moiré systems. We first show that at the level of individual Bloch wavefunctions, the real-space Chern number, akin to a Pontryagin index, is a fragile marker. It generically vanishes except for specific limits where the Bloch functions exhibit fine-tuned zeroes within the unit cell, such as the chiral limit of twisted bilayer graphene (TBG) or the adiabatic regime of twisted homobilayer transition metal dichalcogenides (TMD). We then show that these limitations do not apply to textures associated with ensembles of Bloch wavefunctions, such as entire bands or the ensemble of states at a given energy. The Chern number of these textures defines a robust topological index protected by a spectral gap. We find that symmetries constrain it to be nonzero for both twisted TMDs and TBG across all twist angles and levels of corrugation, implying experimental signatures in scanning tunneling microscopy measurements. By projection to the band ensemble texture, a single-component Hamiltonian under fictitious magnetic field emerges in a broad regime, enabling a direct comparison of multicomponent bands to Landau-level wavefunctions. We also study real-space topology within the topological heavy fermion model of TBG, finding that the real-space topological features are supported only by the light c-electrons.

cond-mat.mes-hall↗
arXiv2026

A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics

Grain growth is governed by the reduction in grain boundary energy and exhibits well-established statistical scaling laws. Developing data-driven surrogates that preserve these physical invariants while remaining computationally scalable remains challenging, especially in 3D. We present 3D-PRIMME (Physics-Regulated Interpretable Machine Learning for Microstructure Evolution) for learning three-dimensional grain growth dynamics. The model is trained using only two consecutive time steps yet accurately reproduces the linear coarsening law and preserves topological statistics over extended time scales. Despite being trained on a $100^3$ grid points with 512 grains, the learned evolution operator is applied to domains up to $1024^3$ grid points with 550000 grains without retraining, maintaining consistent kinetics and grain topology across orders-of-magnitude increases in system size. These results demonstrate that 3D-PRIMME learns a scale-independent and temporally stable local evolution rule, enabling efficient and robust large-scale surrogate prediction of 3D microstructure evolution.

cs.LG↗
arXiv2026

UECP: Uncertainty-Enhanced Collaborative Perception

Collaborative perception serves as a pivotal solution to enhance the perception capability of individual agents in autonomous driving, where a core challenge lies in seeking reliable evidence to quantify and weight the contribution of each participating agent. Existing methods typically rely on a confidence map, which is co-trained with the detection head, but it is inherently correlated with the detection results and thus fails to provide unbiased physical evidence. Furthermore, how to deeply integrate evidence into the cooperative fusion process remains an open question. To address these issues, this paper first proposes an uncertainty map, a physically grounded and unambiguous metric for evaluating perception quality. This map is directly supervised by real-time sensor signals, i.e., LiDAR point density, ensuring decoupling from detection noise and thereby providing physical scenario-aware evidence for weighting agent contribution. Based on this map, we develop the Uncertainty-Enhanced Collaborative Perception (UECP) framework, centered on the Uncertainty-Aware Pyramid Fusion (UAPF) module. UAPF uses a coarse-to-fine strategy, with two key components: Uncertainty-Weighted Downsampling (UWD) for high-fidelity feature preservation, and Uncertainty-Guided Residual Fusion (UGRF) to reinforce ego features, suppressing noise and ensuring robust fusion. Extensive experiments on real-world datasets show UECP outperforms state-of-the-art methods in effectiveness and robustness by embedding the uncertainty map into fusion. Code will be publicly available.

cs.CV↗
arXiv2026

TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering

Large language models (LLMs) and time-series language models (TSLMs) are increasingly applied to time-series question answering (TSQA). Unlike text-only QA, TSQA requires models to ground answers in temporal signals whose patterns may occur at different scales, specific time locations, or across separated intervals. However, existing benchmarks are typically organized by task types or high-level reasoning categories, making it difficult to diagnose the underlying signal-level capabilities driving model performance. We introduce TS-Skill, a controlled benchmark for evaluating three composable analytical skills in TSQA: temporal scale selection (SK1), temporal localization (SK2), and cross-interval integration (SK3). TS-Skill provides timestamp-aware questions, broad domain coverage, and human-validated QA quality. To construct the benchmark at scale, we develop SKEvol, a skill-guided agentic framework that combines domain-aware time-series seed generation, skill-controlled question generation, metadata- and code-assisted answer construction, multi-phase signal-grounded verification, and human-in-the-loop curation. Experiments on ten state-of-the-art LLMs and TSLMs reveal substantial and uneven capability gaps across SK1-SK3. In particular, SK3 remains consistently challenging for non-agent models, whereas tool-augmented agents show a selective advantage on standalone SK3. These findings demonstrate that skill-level evaluation can uncover temporal reasoning failures that are obscured by aggregate TSQA scores.

cs.CL↗
arXiv2026

RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis

Radio-frequency (RF) data synthesis predicts the received signal given transmitter and receiver positions, and is essential for wireless applications. Recent 3D Gaussian Splatting (3DGS)-based methods achieve efficient synthesis at any transmitter but only for a fixed receiver. Therefore, supporting $N$ receivers in one scene requires $N$ independent models and precludes prediction at unseen receivers. We present RxGS, which achieves receiver-generalizable synthesis within a single unified model. Our key insight is that scene geometry is receiver-independent while directional radiance is not: a first stage learns shared 3D Gaussian geometry, and a second stage freezes it and learns directional radiance conditioned on receiver position. A global conditioning branch captures shared receiver-dependent effects across the scene, while a local branch models per-scatterer variations from the receiver's geometry and occlusion. A multi-receiver CUDA rasterizer further batches rendering across all $N$ receivers. Evaluated across various RF datasets, RxGS matches or improves over per-receiver baselines with a single shared model and generalizes to receivers unseen during training within the scene, cutting training cost by up to $45\times$, inference cost by $7.6\times$, and storage by $N\times$.

cs.NI↗