arXiv subjects

Jiayu Yang

Publications and source records attributed to Jiayu Yang.

At least 19 recordsLinked to original sources

arXiv2026

ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation

Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose \ourname, a Gaussian splatting based framework for volumetric video reconstruction. Our key insight is that explicitly tracking long term complex motion with individual Gaussian primitives is inherently unstable. Instead, we organize Gaussians around time conditioned anchors that localize their spatial and temporal support, thereby reducing long range motion complexity. We further introduce a temporal windowing strategy to activate only anchors relevant to the queried time, which improves scalability and temporal coherence. In addition, to ensure spatial and temporal stability, we design a compact set of multi level anchor features that encode global features, local spatial features, and local temporal features, jointly constraining Gaussian generation. Extensive experiments demonstrate that \ourname \ consistently outperforms prior methods on long sequence volumetric videos with complex motions. Project page: https://github.com/WuJH2001/ATGS.

cs.CV↗

arXiv2026

A high-performance quantum pulse gate in thin-film lithium niobate

In this work, we demonstrate a quantum pulse gate (QPG) in thin-film lithium niobate. QPGs enable the selective manipulation and detection of temporal modes of quantum light and form the basis of numerous applications in photonic quantum technologies. To date, their widespread adaption is held back by two main limitations: restricted wavelength and polarization combinations of the involved fields and low normalized conversion efficiencies. We overcome these limitations through developing a QPG in thin-film lithium niobate. We design a waveguide geometry that provides the required dispersion properties for a highly efficient type-0 sum-frequency generation.We verify our design through mapping of the phase matching intensity, and demonstrate high-quality QPG operation by measuring a temporal-mode selectivity of (96.8$\pm$1.7)% on par with existing QPGs. Thanks to the strong confinement in thin-film lithium niobate, we succeed in demonstrating an internal conversion efficiency of (89.6$\pm$0.1)% for a pump power of only 20mW in front of our sample. This yields a lower-bound estimate for the normalized conversion efficiency of (1810$\pm$10)$\mathrm{W}^{-1}\mathrm{cm}^{-2}$, three orders of magnitude higher than in previous QPGs. Our results establish thin-film lithium niobate as ideal platform for high-performance QPGs and are a major step towards practical QPGs for photonic quantum technologies.

quant-ph↗

arXiv2026

Ultrafast programmable Bragg reflection in photonic integrated circuits

Distributed Bragg reflectors (DBRs) are foundational building blocks of classical and quantum photonic technologies. However, their optical responses are typically fixed upon fabrication, limiting circuit robustness, reconfigurability, and functionality in applications from high-speed communications to quantum computing. Here, we demonstrate photonic chip-based programmable DBRs at telecommunications wavelengths, which are formed by electro-optically inducing refractive index contrast between periodic ferroelectric domains in thin-film lithium niobate waveguides. We achieve voltage-controlled Bragg reflection from zero to near-unity, and gigahertz-speed reflectivity modulation. Our results bring DBRs into the ultrafast programmable regime, opening new opportunities in topological photonics, cavity quantum electrodynamics, integrated lasers, and optical interconnects. The interplay between nanoscale ferroelectric domain engineering and strong electro-optic nonlinearity establishes a new design strategy for nanophotonic devices, otherwise inaccessible in bulk media.

physics.optics↗

arXiv2026

PAMAE: Phase-Aware-MoE Action Experts Towards Reliable Flow-Matching Vision-Language-Action Policies

Reliable action generation for multi-stage robotic manipulation remains challenging for Vision-Language-Action (VLA) models. While existing flow-matching VLA policies offer strong multimodal grounding and generalization, they typically employ a single shared action expert, limiting their ability to capture phase-specific control patterns across distinct execution stages. We propose a plug-and-play Phase-Aware Mixture-of-Experts Action Module (PAMAE), as a step towards more reliable phase-consistent action generation. PAMAE replaces the original flow-matching action expert with a sparse expert mixture while preserving the pretrained VLA backbone. PAMAE introduces a phase-aware router that leverages execution-phase cues to allocate action generation across experts, supported by a lightweight phase prediction head and a routing alignment objective. To stabilize specialization, we adopt a two-stage training scheme that first warms up the expert module under the standard flow-matching loss and then optimizes phase-consistent routing under auxiliary supervision. On multi-stage manipulation simulation tasks, PAMAE improves task success by up to \textbf{9.2\%} over strong VLA baselines. Further ablations show that both phase-supervised routing and staged optimization are essential for the observed gains. Our results highlight phase-consistent expert allocation as an effective mechanism for improving the reliability and action quality of flow-matching VLA policies.

cs.RO↗

arXiv2026

PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policies

Long-horizon robotic manipulation is highly sensitive to physically infeasible transitions, contact-induced disturbances, and the lack of effective self-correction during execution. Although Vision-Language-Action (VLA) models provide strong task grounding through multimodal learning, they typically generate actions in a feed-forward manner without explicitly checking physical feasibility or diagnosing execution errors online. We present PhysReflect-VLA, a plug-and-play execution-time reliability framework that augments VLA policies with physical feasibility evaluation and structured self-reflection in a closed-loop control pipeline. A Feasibility Operator evaluates whether candidate actions induce dynamically consistent state transitions; an Action Explanation Operator verifies transition coherence; and an LLM-based Reflection Module analyzes state discrepancies to generate corrective guidance for subsequent actions. A two-stage training procedure stabilizes feasibility modeling and integrates reflection into the control loop. Experiments on multi-stage, contact-rich real-world manipulation tasks show consistent improvements in stage-wise stability and overall task success compared with representative VLA baselines with an average gain of 5.4\%. Ablation results further indicate that feasibility checking and reflection-based correction both contribute to improved execution robustness. These results highlight the importance of embedding physical consistency checks and online self-reflection for reliable long-horizon robotic manipulation.

cs.RO↗

arXiv2026

Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

Latent chain-of-thought compresses reasoning by replacing visible reasoning traces with continuous hidden-state recurrence, but existing formulations are difficult to optimize with standard on-policy reinforcement learning (RL) and hard to interpret causally. Our key insight is that a single pair of explicit boundary tokens can address both issues at once: discrete entry and exit anchors make the latent block compatible with standard on-policy RL, and the same anchors offer a natural foothold for mechanistic analysis. Motivated by this, we propose SWITCH, a switchable latent reasoning framework. The model emits to enter latent mode and to exit. Because the boundaries are ordinary discrete tokens, the GRPO policy ratio is well-defined at every decision point. The same anchors also expose the latent steps to direct probing and causal intervention. We train the model with a visible-to-latent curriculum and a Switch-GRPO objective that propagates gradients through recurrent latent computation. SWITCH consistently outperforms prior hidden-state-recurrence latent reasoning approaches at similar scale. Mechanistic analysis through the boundary tokens further reveals three findings: (i) is a sharply localised, learned switching policy rather than a stylistic artefact; (ii) the latent step it opens performs problem-specific, causally important computation rather than acting as an inert placeholder; and (iii) that computation is concentrated at a single hidden-state transition on entry. Together, these results show that hidden-state-recurrence latent reasoning is both RL-trainable and open to direct mechanistic analysis, including of how on-policy RL itself improves the model from the inside.

cs.LG↗

arXiv2026

ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction

Dynamic 3D scene reconstruction is essential for immersive media such as VR, MR, and XR, yet remains challenging for long multi-view sequences with large-scale motion. Existing dynamic Gaussian approaches are either Frame-Stream, offering scalability but poor temporal stability, or Clip, achieving local consistency at the cost of high memory and limited sequence length. We propose ClipGStream, a hybrid reconstruction framework that performs stream optimization at the clip level rather than the frame level. The sequence is divided into short clips, where dynamic motion is modeled using clip-independent spatio-temporal fields and residual anchor compensation to capture local variations efficiently, while inter-clip inherited anchors and decoders maintain structural consistency across clips. This Clip-Stream design enables scalable, flicker-free reconstruction of long dynamic videos with high temporal coherence and reduced memory overhead. Extensive experiments demonstrate that ClipGStream achieves state-of-the-art reconstruction quality and efficiency. The project page is available at: https://liangjie1999.github.io/ClipGStreamWeb/

cs.CV↗

arXiv2026

Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors

We present a novel method for generating geometrically realistic and consistent orbital videos from a single image of an object. Existing video generation works mostly rely on pixel-wise attention to enforce view consistency across frames. However, such mechanism does not impose sufficient constraints for long-range extrapolation, e.g. rear-view synthesis, in which pixel correspondences to the input image are limited. Consequently, these works often fail to produce results with a plausible and coherent structure. To tackle this issue, we propose to leverage rich shape priors from a 3D foundational generative model as an auxiliary constraint, motivated by its capability of modeling realistic object shape distributions learned from large 3D asset corpora. Specifically, we prompt the video generation with two scales of latent features encoded by the 3D foundation model: (i) a denoised global latent vector as an overall structural guidance, and (ii) a set of latent images projected from volumetric features to provide view-dependent and fine-grained geometry details. In contrast to commonly used 2.5D representations such as depth or normal maps, these compact features can model complete object shapes, and help to improve inference efficiency by avoiding explicit mesh extraction. To achieve effective shape conditioning, we introduce a multi-scale 3D adapter to inject feature tokens to the base video model via cross-attention, which retains its capabilities from general video pretraining and enables a simple and model-agonistic fine-tuning process. Extensive experiments on multiple benchmarks show that our method achieves superior visual quality, shape realism and multi-view consistency compared to state-of-the-art methods, and robustly generalizes to complex camera trajectories and in-the-wild images.

cs.CV↗

arXiv2026

LungCURE: Benchmarking Multimodal Real-World Clinical Reasoning for Precision Lung Cancer Diagnosis and Treatment

Lung cancer clinical decision support demands precise reasoning across complex, multi-stage oncological workflows. Existing multimodal large language models (MLLMs) fail to handle guideline-constrained staging and treatment reasoning. We formalize three oncological precision treatment (OPT) tasks for lung cancer, spanning TNM staging, treatment recommendation, and end-to-end clinical decision support. We introduce LungCURE, the first standardized multimodal benchmark built from 1,000 real-world, clinician-labeled cases across more than 10 hospitals. We further propose LCAgent, a multi-agent framework that ensures guideline-compliant lung cancer clinical decision-making by suppressing cascading reasoning errors across the clinical pathway. Experiments reveal large differences across various large language models (LLMs) in their capabilities for complex medical reasoning, when given precise treatment requirements. We further verify that LCAgent, as a simple yet effective plugin, enhances the reasoning performance of LLMs in real-world medical scenarios.

cs.MM↗

arXiv2026

ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

Large Language Models (LLMs) require efficient knowledge editing (KE) to update factual information, yet existing methods exhibit significant performance decay in multi-hop factual recall. This failure is particularly acute when edits involve intermediate implicit subjects within reasoning chains. Through causal analysis, we reveal that this limitation stems from an oversight of how chained knowledge is dynamically represented and utilized at the neuron level. We discover that during multi hop reasoning, implicit subjects function as query neurons, which sequentially activate corresponding value neurons across transformer layers to accumulate information toward the final answer, a dynamic prior KE work has overlooked. Guided by this insight, we propose ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall, a framework that leverages neuron-level attribution to identify and edit these critical query-value (Q-V) pathways. ACE provides a mechanistically grounded solution for multi-hop KE, empirically outperforming state-of-the-art methods by 9.44% on GPT-J and 37.46% on Qwen3-8B. Our analysis further reveals more fine-grained activation patterns in Qwen3 and demonstrates that the semantic interpretability of value neurons is orchestrated by query-driven accumulation. These findings establish a new pathway for advancing KE capabilities based on the principled understanding of internal reasoning mechanisms.

cs.CL↗

arXiv2026

Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps

We propose Light-Geometry Interaction (LGI) maps, a novel representation that encodes light-aware occlusion from monocular depth. Unlike ray tracing, which requires full 3D reconstruction, LGI captures essential light-shadow interactions reliably and accurately, computed from off-the-shelf 2.5D depth map predictions. LGI explicitly ties illumination direction to geometry, providing a physics-inspired prior that constrains generative models. Without such prior, these models often produce floating shadows, inconsistent illumination, and implausible shadow geometry. Building on this representation, we propose a unified pipeline for joint shadow generation and relighting - unlike prior methods that treat them as disjoint tasks - capturing the intrinsic coupling of illumination and shadowing essential for modeling indirect effects. By embedding LGI into a bridge-matching generative backbone, we reduce ambiguity and enforce physically consistent light-shadow reasoning. To enable effective training, we curated the first large-scale benchmark dataset for joint shadow and relighting, covering reflections, transparency, and complex interreflections. Experiments show significant gains in realism and consistency across synthetic and real images. LGI thus bridges geometry-inspired rendering with generative modeling, enabling efficient, physically consistent shadow generation and relighting.

cs.CV↗

arXiv2026

MLICv2: Enhanced Multi-Reference Entropy Modeling for Learned Image Compression

Recent advances in learned image compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series-LICs equipped with multi-reference entropy models-have substantially surpassed conventional image codecs such as Versatile Video Coding (VVC) Intra. However, existing MLIC variants suffer from several limitations: performance degradation at high bitrates due to insufficient transform capacity, suboptimal entropy modeling that fails to capture global correlations in initial slices, and lack of adaptive channel importance modeling. In this paper, we propose MLICv2 and MLICv2+, enhanced successors that systematically address these limitations through improved transform design, dvanced entropy modeling, and exploration of the potential of instance-specific optimization. For transform enhancement, we introduce a lightweight token mixing block inspired by the MetaFormer architecture, which effectively mitigates high-bitrate performance degradation while maintaining computational efficiency. For entropy modeling improvements, we propose hyperprior-guided global correlation prediction to extract global context even in the initial slice of latent representation, complemented by a channel reweighting module that dynamically emphasizes informative channels. We further explore enhanced positional embedding and guided selective compression strategies for superior context modeling. Additionally, we apply the Stochastic Gumbel Annealing (SGA) to demonstrate the potential for further performance improvements through input-specific optimization. Extensive experiments demonstrate that MLICv2 and MLICv2+ achieve state-of-the-art results, reducing Bjøntegaard-Delta Rate by 16.54%, 21.61%, 16.05% and 20.46%, 24.35%, 19.14% on Kodak, Tecnick, and CLIC Pro Val datasets, respectively, compared to VTM-17.0 Intra.

eess.IV↗

arXiv2026

Generalized model of anisotropic thermo-optic response on thin-film lithium niobate platform

Thermo-optic (TO) control is crucial for thin-film lithium niobate (TFLN) photonic integrated circuits (PICs), offering a simple and practical method for low-frequency and DC tuning while remaining compatible with high-frequency electro-optic (EO) modulation. In x-cut TFLN, the TO response is inherently anisotropic, depending on both waveguide propagation angle and polarization due to the mode-specific overlap of the electric field with the ordinary and extraordinary refractive index axes of the crystal. Despite its significance, a systematic and quantitative analysis of this anisotropy has remained elusive. Here, we present the first generalized analytical model that describes the anisotropic TO response as a function of polarization and arbitrary waveguide orientation, and rigorously validate it through numerical simulations and experiments. This study provides foundational insight into anisotropic thermal tuning and enables new opportunities for engineering energy-efficient and scalable photonic design in next-generation TFLN PICs.

physics.optics↗

arXiv2025

Universal dynamics and microwave control of programmable cavity electro-optic frequency combs

Electro-optic (EO) frequency combs are foundational for metrology and spectroscopy. Specifically, microresonator-based cavity EO combs are distinguished by efficient sideband generation, precisely controlled by microwave signals, enabling high-performance integrated frequency references and pulse sources. However, the apparent simplicity of these devices, often described by the EO modulation-induced coupling of nearest-neighbor cavity modes, has limited investigations of their fundamental physics, thereby restricting their full potential. Here, we uncover the universal dynamics and complete frequency lattice connectivity underpinning cavity EO microcombs, as well as characterize the full space of nonlinear optical states, controlled by modulation depth and optical detuning, using the thin-film lithium niobate photonic platform. Leveraging this understanding, we design complex long-range couplings between cavity modes to realize programmable spectro-temporal shaping of the generated combs and pulses. We achieve three technological advances, including repetition-rate flexibility, substantial comb bandwidth extension beyond traditional scaling laws, and resonantly-enhanced flat-top spectrum. Our results provide physical insights for synchronously driven cavity-based EO systems, broadly defined, paving the way for electrically controlled and electrically enhanced comb generators for next-generation photonic applications.

physics.optics↗

arXiv2025

Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content

3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, a key requirement for immersive applications. However, the extension of 3DGS to dynamic scenes remains limitations on the substantial data volume of dense Gaussians and the prolonged training time required for each frame. This paper presents \M, a scalable Gaussian Splatting framework designed for efficient training in streaming tasks. Specifically, Gaussian spheres are hierarchically organized by scale within an anchor-based structure. Coarser-level Gaussians represent the low-resolution structure of the scene, while finer-level Gaussians, responsible for detailed high-fidelity rendering, are selectively activated by the coarser-level Gaussians. To further reduce computational overhead, we introduce a hybrid deformation and spawning strategy that models motion of inter-frame through Gaussian deformation and triggers Gaussian spawning to characterize wide-range motion. Additionally, a bidirectional adaptive masking mechanism enhances training efficiency by removing static regions and prioritizing informative viewpoints. Extensive experiments demonstrate that \M~ achieves superior visual quality while significantly reducing training time compared to state-of-the-art methods.

cs.CV↗

arXiv2025

UTA-Sign: Unsupervised Thermal Video Augmentation via Event-Assisted Traffic Signage Sketching

The thermal camera excels at perceiving outdoor environments under low-light conditions, making it ideal for applications such as nighttime autonomous driving and unmanned navigation. However, thermal cameras encounter challenges when capturing signage from objects made of similar materials, which can pose safety risks for accurately understanding semantics in autonomous driving systems. In contrast, the neuromorphic vision camera, also known as an event camera, detects changes in light intensity asynchronously and has proven effective in high-speed, low-light traffic environments. Recognizing the complementary characteristics of these two modalities, this paper proposes UTA-Sign, an unsupervised thermal-event video augmentation for traffic signage in low-illumination environments, targeting elements such as license plates and roadblock indicators. To address the signage blind spots of thermal imaging and the non-uniform sampling of event cameras, we developed a dual-boosting mechanism that fuses thermal frames and event signals for consistent signage representation over time. The proposed method utilizes thermal frames to provide accurate motion cues as temporal references for aligning the uneven event signals. At the same time, event signals contribute subtle signage content to the raw thermal frames, enhancing the overall understanding of the environment. The proposed method is validated on datasets collected from real-world scenarios, demonstrating superior quality in traffic signage sketching and improved detection accuracy at the perceptual level.

cs.CV↗

arXiv2025

CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models

Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (XAI). Among these efforts, Concept Bottleneck Models (CBMs) have emerged as a key approach to improve interpretability by leveraging high-level semantic information. However, CBMs, like other machine learning models, are susceptible to security threats, particularly backdoor attacks, which can covertly manipulate model behaviors. Understanding that the community has not yet studied the concept level backdoor attack of CBM, because of "Better the devil you know than the devil you don't know.", we introduce CAT (Concept-level Backdoor ATtacks), a methodology that leverages the conceptual representations within CBMs to embed triggers during training, enabling controlled manipulation of model predictions at inference time. An enhanced attack pattern, CAT+, incorporates a correlation function to systematically select the most effective and stealthy concept triggers, thereby optimizing the attack's impact. Our comprehensive evaluation framework assesses both the attack success rate and stealthiness, demonstrating that CAT and CAT+ maintain high performance on clean data while achieving significant targeted effects on backdoored datasets. This work underscores the potential security risks associated with CBMs and provides a robust testing methodology for future security assessments.

cs.CV↗

arXiv2025

Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models

Concept Bottleneck Models (CBMs) enhance the interpretability of AI systems, particularly by bridging visual input with human-understandable concepts, effectively acting as a form of multimodal interpretability model. However, existing CBMs typically assume static datasets, which fundamentally limits their adaptability to real-world, continuously evolving multimodal data streams. To address this, we define a novel continual learning task for CBMs: simultaneously handling concept-incremental and class-incremental learning. This task requires models to continuously acquire new concepts (often representing cross-modal attributes) and classes while robustly preserving previously learned knowledge. To tackle this challenging problem, we propose CONceptual Continual Incremental Learning (CONCIL), a novel framework that fundamentally re-imagines concept and decision layer updates as linear regression problems. This reformulation eliminates the need for gradient-based optimization, thereby effectively preventing catastrophic forgetting. Crucially, CONCIL relies solely on recursive matrix operations, rendering it highly computationally efficient and well-suited for real-time and large-scale multimodal data applications. Experimental results compellingly demonstrate that CONCIL achieves "absolute knowledge memory" and significantly surpasses the performance of traditional CBM methods in both concept- and class-incremental settings, thus establishing a new paradigm for continual learning in CBMs, particularly valuable for dynamic multimodal understanding.

cs.LG↗