arXiv subjects

Shiyu Liu

Publications and source records attributed to Shiyu Liu.

At least 19 recordsLinked to original sources

arXiv2026

Tri-DehazeGS: Scene--Medium Decoupled Gaussian Splatting with Transmittance-Aware Optimization

Recovering clean 3D scenes from hazy multi-view images is challenging because haze attenuates scene radiance and introduces atmospheric scattering. Recent scattering-aware Gaussian Splatting methods introduce physical haze models into reconstruction, but they often apply degradation in image space or bind medium-related variables to Gaussian primitives, which can entangle clean scene radiance with atmospheric effects. Moreover, low-transmittance regions provide weakened supervision for Gaussian optimization, causing distant or dense-haze areas to be under-reconstructed. We argue that clean reconstruction under haze requires both scene--medium disentanglement and transmittance-aware optimization rebalancing. To this end, we propose Tri-DehazeGS, a scene--medium decoupled Gaussian Splatting framework. It represents the clean scene with Gaussian primitives, models the participating medium using an independent view-shared tri-plane field, and composes hazy observations through a physical scattering model. We further introduce Medium-Decoupled Transmittance Gradient Compensation (MD-TGC), which compensates haze-suppressed gradients after medium freezing without altering forward rendering. Experiments on real and synthetic haze benchmarks show that Tri-DehazeGS improves clean novel-view reconstruction. Code is available at https://github.com/aptx46/Tri-DehazeGS.

cs.CV↗

arXiv2026

iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often constrained by the continuous nature of their training data. We hypothesize that by injecting the rich and unconstrained content diversity from image data into this coherent temporal framework, we can generate image sets that feature both natural transitions and a far more expansive dynamic range. To this end, we introduce iMontage, a unified framework designed to repurpose a powerful video model into an all-in-one image generator. The framework consumes and produces variable-length image sets, unifying a wide array of image generation and editing tasks. To achieve this, we propose an elegant and minimally invasive adaptation strategy, complemented by a tailored data curation process and training paradigm. This approach allows the model to acquire broad image manipulation capabilities without corrupting its invaluable original motion priors. iMontage excels across several mainstream many-in-many-out tasks, not only maintaining strong cross-image contextual consistency but also generating scenes with extraordinary dynamics that surpass conventional scopes. Find our homepage at: https://kr1sjfu.github.io/iMontage-web/.

cs.CV↗

arXiv2026

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their own knowledge boundaries, blindly triggering searches when internal knowledge suffices and failing to terminate search even when adequate evidence has been collected. The lack of self-awareness leads to severe \textbf{over-search}, incurring substantial inference latency and prohibitive computational cost. To this end, we propose SAAS, a novel RL framework designed to cultivate dynamic self-awareness that precisely regulates search behavior without compromising accuracy. SAAS introduces three key components: (i) a search boundary modeling mechanism, which identifies the search boundary under the evolving policy by contrasting search-disabled and search-enabled rollouts; (ii) a boundary-aware reward module, which translates this boundary awareness into trajectory-level penalties, suppressing unnecessary and redundant searches; and (iii) a stage-wise optimization strategy, which leverages a sequential curriculum to prioritize reasoning over search regularization, thereby avoiding reward hacking. Extensive experiments demonstrate that SAAS substantially reduces over-search, while maintaining accuracy. Our code and implementation details are released at https://github.com/XMUDeepLIT/SAAS.

cs.AI↗

arXiv2026

CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning

Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large language models, but most methods still optimize reasoning trajectories over the static problem set, wasting rollout budget on solved or overly difficult problems. We propose \textbf{CLPO (Curriculum Learning meets Policy Optimization)}, a self-evolving curriculum framework that uses on-policy rollout accuracy to identify solved, medium-difficulty, and hard problems, then restructures selected tasks according to the model's current capability. Hard problems are simplified to become learnable, while medium-difficulty problems are diversified to provide useful training variation. This allows the learning curriculum to co-evolve with the policy rather than remaining fixed as the model's capability boundary shifts. Rather than treating these rewrites as static data augmentation, CLPO optimizes restructuring trajectories with credit assigned by the downstream accuracy gain of the rewritten problem, requiring no additional human annotations beyond the original verifiable answers. Experiments across mathematical reasoning and out-of-domain general reasoning benchmarks show that CLPO substantially outperforms GRPO and DAPO on Qwen3-8B by 10.21 and 7.75 average points, respectively. Ablation studies on math and code domains further show that both the restructuring mode and the rewriting loss contribute to the final gains, demonstrating that CLPO provides a scalable and robust pathway for eliciting stronger reasoning capabilities through a self-evolving curriculum.

cs.AI↗

arXiv2026

Observation and Control of the Magnetic Photogalvanic Effect from Strongly Bound Excitons

Photogalvanic effects arising from the quantum geometry of noncentrosymmetric materials are promising for next-generation light-harvesting devices that do not require a built-in electric field. Recent theories predict photogalvanic currents generated in magnetic systems with spin-dependent symmetry breaking as well as by bound exciton states, allowing for potential magnetic field control of the photoresponse and enhanced detection of deep sub-gap signals, respectively. We demonstrate the magnetic photogalvanic effect in a bilayer CrI3 tunnel junction with both magnetic field switching and electric field tuning of interlayer symmetry. By controlling for the polarization and energy of light illumination, we disentangle the shift and injection current contributions and find that the peak response occurs under resonant excitation of strongly bound excitons in CrI3. Our results can be captured within a many-body framework of the photogalvanic effect, while our devices function as tunable, multispectral helicity- and polarization-sensitive detectors that highlight the potential of 2D magnets for future optoelectronic applications.

cond-mat.mtrl-sci↗

arXiv2026

HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis

Audio-driven talking head generation faces a fundamental trade-off between personalization and generalization, limiting its practical application. Implicit models often achieve generalization at the cost of structural incoherence, resulting in unstable head motion and inaccurate lip synchronization. While explicit methods incorporate geometric and anatomical priors such as 3D Morphable Models (3DMMs), which parameterize facial geometry, or Action Units (AUs), which code facial muscle movements--they tend to produce overly neutral expressions or suffer from limited generalization. To resolve this conflict, we present HM-Talker, an audio-driven talking head framework that synergistically integrates explicit articulatory cues with implicit prosodic features to characterize identity-specific dynamics while enabling audio-driven generalization. Its distinctive features can be summarized as: i) the Cross-Modal Mapping Module (CMMM) that extracts a comprehensive vocabulary of motion cues from audio and video, and ii) the Hybrid Motion Modeling Module (HMMM) that employs a Stochastic Feature Pairing (SFP) strategy to dynamically merge paired implicit and explicit features for motion synthesis. This design facilitates an iterative optimization of the lower face motion, alternating between identity-specific and identity-agnostic (audio-only) objectives. Extensive experiments demonstrate that HM-Talker outperforms state-of-the-art methods in both visual realism and lip-sync accuracy across diverse settings.

cs.CV↗

arXiv2026

DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding

GUI agents powered by Multimodal Large Language Models (MLLMs) have demonstrated impressive capability in understanding and executing user instructions. However, accurately grounding instruction-relevant elements from high-resolution screenshots cluttered with irrelevant UI components remains challenging for existing approaches. Inspired by how humans dynamically adjust their perceptual scope to locate task-related regions on complex screens, we propose DRS-GUI, a training-free dynamic region search framework for GUI grounding that can be seamlessly integrated into existing MLLMs. DRS-GUI introduces a lightweight UI Perceptor that performs three human-like perceptual actions (Focus, Shift, and Scatter) to progressively explore the interface and generate region proposals. To dynamically schedule these actions, we further design an Action Planner based on Monte Carlo Tree Search (MCTS). A region quality reward is employed to evaluate and select the highly instruction-relevant region, efficiently pruning redundant UI elements. Experiments demonstrate that DRS-GUI yields a 14\% improvement on ScreenSpot-Pro for general and GUI-specific MLLMs (Qwen2.5-VL-7B and UGround-V1-7B), significantly enhancing grounding performance and generalization.

cs.AI↗

arXiv2026

NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results

This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to identify robust reconstruction pipelines that are robust under real-world adverse conditions, specifically extreme low-light and smoke-degraded environments, as captured by our RealX3D benchmark. A total of 279 participants registered for the competition, of whom 33 teams submitted valid results. We thoroughly evaluate the submitted approaches against state-of-the-art baselines, revealing significant progress in 3D reconstruction under adverse conditions. Our analysis highlights shared design principles among top-performing methods and provides insights into effective strategies for handling 3D scene degradation.

cs.CV↗

arXiv2026

BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search

RL-based agentic search enables LLMs to solve complex questions via dynamic planning and external search. While this approach significantly enhances accuracy with agent policies optimized via large-scale reinforcement learning, we identify a critical gap in reliability: these agents fail to recognize their reasoning boundaries and rarely admit ``I DON'T KNOW'' (IDK) even when evidence is insufficient or reasoning reaches its limit. The lack of reliability often leads to plausible but unreliable answers, introducing significant risks in many real-world scenarios. To this end, we propose Boundary-Aware Policy Optimization (BAPO), a novel RL framework designed to cultivate reliable boundary awareness without compromising accuracy. BAPO introduces two key components: (i) a group-based boundary-aware reward that encourages an IDK response only when the reasoning reaches its limit, and (ii) an adaptive reward modulator that strategically suspends this reward during early exploration, preventing the model from exploiting IDK as a shortcut. Extensive experiments on four benchmarks demonstrate that BAPO substantially enhances the overall reliability of agentic search.

cs.AI↗

arXiv2026

Countering the Over-Reliance Trap: Mitigating Object Hallucination for LVLMs via a Self-Validation Framework

Despite progress in Large Vision Language Models (LVLMs), object hallucination remains a critical issue in image captioning task, where models generate descriptions of non-existent objects, compromising their reliability. Previous work attributes this to LVLMs' over-reliance on language priors and attempts to mitigate it through logits calibration. However, they still lack a thorough analysis of the over-reliance. To gain a deeper understanding of over-reliance, we conduct a series of preliminary experiments, indicating that as the generation length increases, LVLMs' over-reliance on language priors leads to inflated probability of hallucinated object tokens, consequently exacerbating object hallucination. To circumvent this issue, we propose Language-Prior-Free Verification to enable LVLMs to faithfully verify the confidence of object existence. Based on this, we propose a novel training-free Self-Validation Framework to counter the over-reliance trap. It first validates objects' existence in sampled candidate captions and further mitigates object hallucination via caption selection or aggregation. Experiment results demonstrate that our framework mitigates object hallucination significantly in image captioning task (e.g., 65.6% improvement on CHAIRI metric with LLaVA-v1.5-7B), surpassing the previous SOTA methods. This result highlights a novel path towards mitigating hallucination by unlocking the inherent potential within LVLMs themselves.

cs.CV↗

arXiv2026

RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

Image restoration under real-world degradations is critical for downstream tasks such as autonomous driving and object detection. However, existing restoration models are often limited by the scale and distribution of their training data, resulting in poor generalization to real-world scenarios. Recently, large-scale image editing models have shown strong generalization ability in restoration tasks, especially for closed-source models like Nano Banana Pro, which can restore images while preserving consistency. Nevertheless, achieving such performance with those large universal models requires substantial data and computational costs. To address this issue, we construct a large-scale dataset covering nine common real-world degradation types and train a state-of-the-art open-source model to narrow the gap with closed-source alternatives. Furthermore, we introduce RealIR-Bench, which contains 464 real-world degraded images and tailored evaluation metrics focusing on degradation removal and consistency preservation. Extensive experiments demonstrate our model ranks first among open-source methods, achieving state-of-the-art performance.

cs.CV↗

arXiv2026

AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting

Accurate air quality forecasting is essential for public health and environmental sustainability, but remains challenging due to the complex pollutant dynamics. Existing deep learning methods often model pollutant dynamics as an instantaneous process, overlooking the intrinsic delays in pollutant propagation. Thus, we propose AirDDE, the first neural delay differential equation framework in this task that integrates delay modeling into a continuous-time pollutant evolution under physical guidance. Specifically, two novel components are introduced: (1) a memory-augmented attention module that retrieves globally and locally historical features, which can adaptively capture delay effects modulated by multifactor data; and (2) a physics-guided delay evolving function, grounded in the diffusion-advection equation, that models diffusion, delayed advection, and source/sink terms, which can capture delay-aware pollutant accumulation patterns with physical plausibility. Extensive experiments on three real-world datasets demonstrate that AirDDE achieves the state-of-the-art forecasting performance with an average MAE reduction of 8.79\% over the best baselines. The code is available at https://github.com/w2obin/airdde-aaai.

cs.LG↗

arXiv2026

SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC

Large Language Models (LLMs) have revolutionized numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains such as healthcare and finance remains constrained due to the scarcity of accessible training data caused by stringent privacy requirements. Secure Multi-party Computation (MPC)-based privacy-preserving machine learning provides theoretical guarantees for the privacy of model parameters and data. However, its application to LLMs has been predominantly limited to inference, as fine-tuning introduces significant efficiency challenges, particularly in backward propagation, optimizer, and self-attention operations. To address these challenges, we propose SecP-Tuning, the first MPC-based framework designed for efficient, privacy-preserving prompt tuning of LLMs. SecP-Tuning innovatively integrates Forward-only Tuning (FoT) through the ``data owner-server interaction" paradigm, effectively removing the need for privacy-preserving computations in backward propagation and optimization processes. Furthermore, it devises an efficient privacy-preserving Random Feature Attention (RFA), effectively mitigating the computational complexity of softmax-based self-attention and circumventing MPC-incompatible nonlinear operations. Experimental results demonstrate that, compared to full-Parameter Supervised Fine-Tuning (SFT) and gradient-based prompt tuning, SecP-Tuning achieves approximately 12x and 16x end-to-end acceleration, as well as 17x and 20x reductions in communication overhead, respectively. Moreover, it delivers performance comparable to gradient-based methods across multiple few-shot tasks.

cs.LG↗

arXiv2026

Depth-Enhanced YOLO-SAM2 Detection for Reliable Ballast Insufficiency Identification

This paper presents a depth-enhanced YOLO-SAM2 framework for detecting ballast insufficiency in railway tracks using RGB-D data. Although YOLOv8 provides reliable localization, the RGB-only model shows limited safety performance, achieving high precision (0.99) but low recall (0.49) due to insufficient ballast, as it tends to over-predict the sufficient class. To improve reliability, we incorporate depth-based geometric analysis enabled by a sleeper-aligned depth-correction pipeline that compensates for RealSense spatial distortion using polynomial modeling, RANSAC, and temporal smoothing. SAM2 segmentation further refines region-of-interest masks, enabling accurate extraction of sleeper and ballast profiles for geometric classification. Experiments on field-collected top-down RGB-D data show that depth-enhanced configurations substantially improve the detection of insufficient ballast. Depending on bounding-box sampling (AABB or RBB) and geometric criteria, recall increases from 0.49 to as high as 0.80, and F1-score improves from 0.66 to over 0.80. These results demonstrate that integrating depth correction with YOLO-SAM2 yields a more robust and reliable approach for automated railway ballast inspection, particularly in visually ambiguous or safety-critical scenarios.

cs.CV↗

arXiv2026

Long term convergence rate of Smoluchowski-Kramers approximation by Stein's method

We consider the following second-order stochastic differential equation on $\mathbb{R}^{2d}$: \begin{equation*} dX_t^m=Y_t^mdt, \quad mdY_t^m=b(X_t^m)dt+σ(X_t^m)dB_t-Y^m_tdt, \end{equation*} where $X^m_t$ and $Y^m_t$ represent the position and velocity of a particle at time $t$, $m>0$ denotes its mass, $b:\mathbb{R}^d \rightarrow \mathbb{R}^d$ is the drift field, $σ:\mathbb{R}^d \rightarrow \mathbb{R}^{d \times d}$ is the diffusion coefficient, and $\{B_t\}_{t \ge 0}$ is a $d$-dimensional standard Brownian motion. The Smoluchowski--Kramers approximation states that as $m \rightarrow 0$, this system converges to the limiting equation: \begin{equation*} dX_t=b(X_t)dt+σ(X_t)dB_t. \end{equation*} Utilizing Stein's method, we prove that the $1$-Wasserstein distance between the invariant distribution of $X_t^m$ and that of its small-mass limit $X_t$ is of order $O(\sqrt{m}|\ln m|).$ Particularly, in the one-dimensional case, the convergence rate can be improved to $O(\sqrt{m}).$

math.PR↗

arXiv2025

ReasonEdit: Towards Reasoning-Enhanced Image Editing Models

Recent advances in image editing models have shown remarkable progress. A common architectural design couples a multimodal large language model (MLLM) encoder with a diffusion decoder, as seen in systems such as Step1X-Edit and Qwen-Image-Edit, where the MLLM encodes both the reference image and the instruction but remains frozen during training. In this work, we demonstrate that unlocking the reasoning capabilities of MLLM can further push the boundaries of editing models. Specifically, we explore two reasoning mechanisms, thinking and reflection, which enhance instruction understanding and editing accuracy. Based on that, our proposed framework enables image editing in a thinking-editing-reflection loop: the thinking mechanism leverages the world knowledge of MLLM to interpret abstract instructions, while the reflection reviews editing results, automatically corrects unintended manipulations, and identifies the stopping round. Extensive experiments demonstrate that our reasoning approach achieves significant performance gains, with improvements of ImgEdit (+4.3%), GEdit (+4.7%), and Kris (+8.2%) when initializing our DiT from the Step1X-Edit (ReasonEdit-S), and also outperforms previous open-source methods on both GEdit and Kris when integrated with Qwen-Image-Edit (ReasonEdit-Q).

cs.CV↗

arXiv2025

Beyond Correlation: Causal Multi-View Unsupervised Feature Selection Learning

Multi-view unsupervised feature selection (MUFS) has recently received increasing attention for its promising ability in dimensionality reduction on multi-view unlabeled data. Existing MUFS methods typically select discriminative features by capturing correlations between features and clustering labels. However, an important yet underexplored question remains: \textit{Are such correlations sufficiently reliable to guide feature selection?} In this paper, we analyze MUFS from a causal perspective by introducing a novel structural causal model, which reveals that existing methods may select irrelevant features because they overlook spurious correlations caused by confounders. Building on this causal perspective, we propose a novel MUFS method called CAusal multi-view Unsupervised feature Selection leArning (CAUSA). Specifically, we first employ a generalized unsupervised spectral regression model that identifies informative features by capturing dependencies between features and consensus clustering labels. We then introduce a causal regularization module that can adaptively separate confounders from multi-view data and simultaneously learn view-shared sample weights to balance confounder distributions, thereby mitigating spurious correlations. Thereafter, integrating both into a unified learning framework enables CAUSA to select causally informative features. Comprehensive experiments demonstrate that CAUSA outperforms several state-of-the-art methods. To our knowledge, this is the first in-depth study of causal multi-view feature selection in the unsupervised setting.

cs.LG↗

arXiv2025

Motion Planning and Control of an Overactuated 4-Wheel Drive with Constrained Independent Steering

This paper addresses motion planning and con- trol of an overactuated 4-wheel drive train with independent steering (4WIS) where mechanical constraints prevent the wheels from executing full 360-degree rotations (swerve). The configuration space of such a robot is constrained and contains discontinuities that affect the smoothness of the robot motion. We introduce a mathematical formulation of the steering constraints and derive discontinuity planes that partition the velocity space into regions of smooth and efficient motion. We further design the motion planner for path tracking and ob- stacle avoidance that explicitly accounts for swerve constraints and the velocity transition smoothness. The motion controller uses local feedback to generate actuation from the desired velocity, while properly handling the discontinuity crossing by temporarily stopping the motion and repositioning the wheels. We implement the proposed motion planner as an extension to ROS Navigation package and evaluate the system in simulation and on a physical robot.

cs.RO↗