arXiv subjects

Jie Chen

Publications and source records attributed to Jie Chen.

At least 163 records · Page 9Linked to original sources

arXiv2025

A Dual-Modulation Framework for RGB-T Crowd Counting via Spatially Modulated Attention and Adaptive Fusion

Accurate RGB-Thermal (RGB-T) crowd counting is crucial for public safety in challenging conditions. While recent Transformer-based methods excel at capturing global context, their inherent lack of spatial inductive bias causes attention to spread to irrelevant background regions, compromising crowd localization precision. Furthermore, effectively bridging the gap between these distinct modalities remains a major hurdle. To tackle this, we propose the Dual Modulation Framework, comprising two modules: Spatially Modulated Attention (SMA), which improves crowd localization by using a learnable Spatial Decay Mask to penalize attention between distant tokens and prevent focus from spreading to the background; and Adaptive Fusion Modulation (AFM), which implements a dynamic gating mechanism to prioritize the most reliable modality for adaptive cross-modal fusion. Extensive experiments on RGB-T crowd counting datasets demonstrate the superior performance of our method compared to previous works. Code available at https://github.com/Cht2924/RGBT-Crowd-Counting.

cs.CV↗

arXiv2025

Standardizing Generative Face Video Compression using Supplemental Enhancement Information

This paper proposes a Generative Face Video Compression (GFVC) approach using Supplemental Enhancement Information (SEI), where a series of compact spatial and temporal representations of a face video signal (e.g., 2D/3D keypoints, facial semantics and compact features) can be coded using SEI messages and inserted into the coded video bitstream. At the time of writing, the proposed GFVC approach using SEI messages has been included into a draft amendment of the Versatile Supplemental Enhancement Information (VSEI) standard by the Joint Video Experts Team (JVET) of ISO/IEC JTC 1/SC 29 and ITU-T SG21, which will be standardized as a new version of ITU-T H.274 | ISO/IEC 23002-7. To the best of the authors' knowledge, the JVET work on the proposed SEI-based GFVC approach is the first standardization activity for generative video compression. The proposed SEI approach has not only advanced the reconstruction quality of early-day Model-Based Coding (MBC) via the state-of-the-art generative technique, but also established a new SEI definition for future GFVC applications and deployment. Experimental results illustrate that the proposed SEI-based GFVC approach can achieve remarkable rate-distortion performance compared with the latest Versatile Video Coding (VVC) standard, whilst also potentially enabling a wide variety of functionalities including user-specified animation/filtering and metaverse-related applications.

cs.CV↗

arXiv2025

Stochastic Schrödinger-Korteweg de Vries systems driven by multiplicative noises

In this paper, we consider the well-posedness of stochastic S-KdV driven by multiplicative noises in $H_x^1\times H_x^1$. To get the local well-posedness, we first develop the bilinear and trilinear Bourgain norm estimates of the nonlinear terms with $b\in\left(0,1/2\right)$. Then, to overcome regularity problems, we introduce a series of approximation equations with localized nonlinear terms, which are also cutted-off in both the physical and the frequency space. By limitations, these approximation equations will help us get a priori estimate in the Bourgain space and finish the proof of the global well-posedness of the initial system.

math.PR↗

arXiv2025

Hybrid Two-Stage Reconstruction of Multiscale Subsurface Flow with Physics-informed Residual Connected Neural Operator

The novel neural networks show great potential in solving partial differential equations. For single-phase flow problems in subsurface porous media with high-contrast coefficients, the key is to develop neural operators with accurate reconstruction capability and strict adherence to physical laws. In this study, we proposed a hybrid two-stage framework that uses multiscale basis functions and physics-guided deep learning to solve the Darcy flow problem in high-contrast fractured porous media. In the first stage, a data-driven model is used to reconstruct the multiscale basis function based on the permeability field to achieve effective dimensionality reduction while preserving the necessary multiscale features. In the second stage, the physics-informed neural network, together with Transformer-based global information extractor is used to reconstruct the pressure field by integrating the physical constraints derived from the Darcy equation, ensuring consistency with the physical laws of the real world. The model was evaluated on datasets with different combinations of permeability and basis functions and performed well in terms of reconstruction accuracy. Specifically, the framework achieves R2 values above 0.9 in terms of basis function fitting and pressure reconstruction, and the residual indicator is on the order of $1\times 10^{-4}$. These results validate the ability of the proposed framework to achieve accurate reconstruction while maintaining physical consistency.

cs.LG↗

arXiv2025

DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning

This letter introduces DiffAero, a lightweight, GPU-accelerated, and fully differentiable simulation framework designed for efficient quadrotor control policy learning. DiffAero supports both environment-level and agent-level parallelism and integrates multiple dynamics models, customizable sensor stacks (IMU, depth camera, and LiDAR), and diverse flight tasks within a unified, GPU-native training interface. By fully parallelizing both physics and rendering on the GPU, DiffAero eliminates CPU-GPU data transfer bottlenecks and delivers orders-of-magnitude improvements in simulation throughput. In contrast to existing simulators, DiffAero not only provides high-performance simulation but also serves as a research platform for exploring differentiable and hybrid learning algorithms. Extensive benchmarks and real-world flight experiments demonstrate that DiffAero and hybrid learning algorithms combined can learn robust flight policies in hours on consumer-grade hardware. The code is available at https://github.com/flyingbitac/diffaero.

cs.RO↗

arXiv2025

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework

Large reasoning models (LRMs) have exhibited strong performance on complex reasoning tasks, with further gains achievable through increased computational budgets at inference. However, current test-time scaling methods predominantly rely on redundant sampling, ignoring the historical experience utilization, thereby limiting computational efficiency. To overcome this limitation, we propose Sticker-TTS, a novel test-time scaling framework that coordinates three collaborative LRMs to iteratively explore and refine solutions guided by historical attempts. At the core of our framework are distilled key conditions-termed stickers-which drive the extraction, refinement, and reuse of critical information across multiple rounds of reasoning. To further enhance the efficiency and performance of our framework, we introduce a two-stage optimization strategy that combines imitation learning with self-improvement, enabling progressive refinement. Extensive evaluations on three challenging mathematical reasoning benchmarks, including AIME-24, AIME-25, and OlymMATH, demonstrate that Sticker-TTS consistently surpasses strong baselines, including self-consistency and advanced reinforcement learning approaches, under comparable inference budgets. These results highlight the effectiveness of sticker-guided historical experience utilization. Our code and data are available at https://github.com/RUCAIBox/Sticker-TTS.

cs.AI↗

arXiv2025

Data-driven solar forecasting enables near-optimal economic decisions

Solar energy adoption is critical to achieving net-zero emissions. However, it remains difficult for many industrial and commercial actors to decide on whether they should adopt distributed solar-battery systems, which is largely due to the unavailability of fast, low-cost, and high-resolution irradiance forecasts. Here, we present SunCastNet, a lightweight data-driven forecasting system that provides 0.05$^\circ$, 10-minute resolution predictions of surface solar radiation downwards (SSRD) up to 7 days ahead. SunCastNet, coupled with reinforcement learning (RL) for battery scheduling, reduces operational regret by 76--93\% compared to robust decision making (RDM). In 25-year investment backtests, it enables up to five of ten high-emitting industrial sectors per region to cross the commercial viability threshold of 12\% Internal Rate of Return (IRR). These results show that high-resolution, long-horizon solar forecasts can directly translate into measurable economic gains, supporting near-optimal energy operations and accelerating renewable deployment.

physics.geo-ph↗

arXiv2025

Robust Offline Imitation Learning Through State-level Trajectory Stitching

Imitation learning (IL) has proven effective for enabling robots to acquire visuomotor skills through expert demonstrations. However, traditional IL methods are limited by their reliance on high-quality, often scarce, expert data, and suffer from covariate shift. To address these challenges, recent advances in offline IL have incorporated suboptimal, unlabeled datasets into the training. In this paper, we propose a novel approach to enhance policy learning from mixed-quality offline datasets by leveraging task-relevant trajectory fragments and rich environmental dynamics. Specifically, we introduce a state-based search framework that stitches state-action pairs from imperfect demonstrations, generating more diverse and informative training trajectories. Experimental results on standard IL benchmarks and real-world robotic tasks showcase that our proposed method significantly improves both generalization and performance.

cs.RO↗

arXiv2025

Investigation of $Λ_{b}\to Λ_{c} \ell^-\overlineν_\ell$ Decays in Perturbative QCD Approach

We investigate the semileptonic decays $Λ_{b} \to Λ_{c} \ell^- \barν_\ell$ (with $\ell = e, μ, τ$) within the framework of perturbative QCD (pQCD). The six independent $Λ_b \to Λ_c$ transition form factors are first calculated in the low-$q^2$ region using the $k_T$ factorization approach. These are then extrapolated to the full physical $q^2$ range via the model-independent $z$-expansion, incorporating recent lattice QCD results at high $q^2$. Based on the obtained form factors, we compute the branching fractions of $Λ_b \to Λ_c \ell^- \barν_\ell$ decays. Our prediction for the lepton flavor universality ratio, $\mathcal{R}_{Λ_c} = 0.29^{+0.12}_{-0.11}$, is slightly larger than the latest experimental measurement. In addition, we analyze several angular observables, including forward-backward asymmetries, lepton-side convexity parameters, and polarization asymmetries. These results offer valuable theoretical input for current and future experimental investigations of semileptonic heavy-to-heavy baryon transitions.

hep-ph↗

arXiv2025

SPGrasp: Spatiotemporal Prompt-driven Grasp Synthesis in Dynamic Scenes

Real-time interactive grasp synthesis for dynamic objects remains challenging as existing methods fail to achieve low-latency inference while maintaining promptability. To bridge this gap, we propose SPGrasp (spatiotemporal prompt-driven dynamic grasp synthesis), a novel framework extending segment anything model v2 (SAMv2) for video stream grasp estimation. Our core innovation integrates user prompts with spatiotemporal context, enabling real-time interaction with end-to-end latency as low as 59 ms while ensuring temporal consistency for dynamic objects. In benchmark evaluations, SPGrasp achieves instance-level grasp accuracies of 90.6% on OCID and 93.8% on Jacquard. On the challenging GraspNet-1Billion dataset under continuous tracking, SPGrasp achieves 92.0% accuracy with 73.1 ms per-frame latency, representing a 58.5% reduction compared to the prior state-of-the-art promptable method RoG-SAM while maintaining competitive accuracy. Real-world experiments involving 13 moving objects demonstrate a 94.8% success rate in interactive grasping scenarios. These results confirm SPGrasp effectively resolves the latency-interactivity trade-off in dynamic grasp synthesis.

cs.RO↗

arXiv2025

UniAPO: Unified Multimodal Automated Prompt Optimization

Prompting is fundamental to unlocking the full potential of large language models. To automate and enhance this process, automatic prompt optimization (APO) has been developed, demonstrating effectiveness primarily in text-only input scenarios. However, extending existing APO methods to multimodal tasks, such as video-language generation introduces two core challenges: (i) visual token inflation, where long visual token sequences restrict context capacity and result in insufficient feedback signals; (ii) a lack of process-level supervision, as existing methods focus on outcome-level supervision and overlook intermediate supervision, limiting prompt optimization. We present UniAPO: Unified Multimodal Automated Prompt Optimization, the first framework tailored for multimodal APO. UniAPO adopts an EM-inspired optimization process that decouples feedback modeling and prompt refinement, making the optimization more stable and goal-driven. To further address the aforementioned challenges, we introduce a short-long term memory mechanism: historical feedback mitigates context limitations, while historical prompts provide directional guidance for effective prompt optimization. UniAPO achieves consistent gains across text, image, and video benchmarks, establishing a unified framework for efficient and transferable prompt optimization.

cs.CV↗

arXiv2025

Strichartz type estimates of the Airy equation

In this article, we show the necessary and sufficient conditions for the inequality $\|u\|_{L_t^qL_x^r}\lesssim \|u\|_{X^{s,b}}$, where $$\|u\|_{X^{s,b}}:=\|\hat{u}(τ,ξ)\langle ξ\rangle^s\langle τ-ξ^3\rangle^b \|_{L_{τ,ξ}^2}. $$ Here, we provide a complete classification of the indices relationships for which this inequality holds true. Such estimates will be very useful in solving the well-posedness for low regularity well-posedness of the Korteweg--de Vries equations and stochastic Korteweg--de Vries equations.

math.AP↗

arXiv2025

Universal Entanglement Pattern Formation via a Quantum Quench

We identify a universal short-time structure in symmetry-resolved entanglement dynamics -- the entanglement channel wave (ECW) -- arising from the decomposition of entanglement into conserved-quantum-number sectors that host robust, channel-specific patterns. Focusing on domain-wall melting, we conduct a systematic investigation across three paradigmatic classes of many-body systems: U(1) fermions, U(1) bosons, and SU(2) spinful fermions. For each class, we explore four distinct regimes defined by the presence or absence of interactions and disorder, employing both the Krylov-subspace iterative method and the correlation matrix approach. The ECW emerges universally across all cases, establishing its independence from particle statistics, interaction strength and disorder. In free fermions, the ECW formalism further enables analytical determination of the correlation matrix spectrum. The subsequent melting of the ECW exhibits symmetry- and statistics-dependent signatures, revealing finer structures in the growth of symmetry-resolved entanglement.

cond-mat.str-el↗

arXiv2025

On the Variability Features of Active Galactic Nuclei in Little Red Dots

The high-redshift ($z>4$) compact sources with ``V-shaped" spectral energy distributions (SEDs), known as Little Red Dots (LRDs), are discovered by the James Webb Space Telescope and provide valuable clues to the physics of active galactic nuclei (AGNs) in the early universe. The nature of LRDs is controversial. Recently, several studies have investigated LRDs through variability, a characteristic feature of AGNs. These studies explore LRD variability by extrapolating empirical relationships from local quasars. Here, we adopt the Corona-heated Accretion-disk Reprocessing (CHAR) model, which is motivated by accretion physics and applicable to reproduce AGN conventional variability, to study the variability of $22$ LRDs in \citet{Tee2025}. Our results indicate that the observed variability in LRDs is dominated by measurement uncertainties. Within the CHAR model, the lack of variability in LRDs can be explained by two scenarios: either AGNs contribute $\lesssim30\%$ of the observed luminosities, or they are intrinsically luminous AGNs. We use simulations to demonstrate the observational requirements to effectively investigate LRDs via variability: first, a sample of about $200$ LRDs; second, each LRD has two observations separated by at least two years in the observed frame; third, the photometric uncertainty is $\leq 0.07$ mag. If the LRDs still lack variability under these conditions, the time-domain study would provide independent evidence that the accretion mode of LRDs differs significantly from low-redshift quasars.

astro-ph.GA↗

arXiv2025

OneLoc: Geo-Aware Generative Recommender Systems for Local Life Service

Local life service is a vital scenario in Kuaishou App, where video recommendation is intrinsically linked with store's location information. Thus, recommendation in our scenario is challenging because we should take into account user's interest and real-time location at the same time. In the face of such complex scenarios, end-to-end generative recommendation has emerged as a new paradigm, such as OneRec in the short video scenario, OneSug in the search scenario, and EGA in the advertising scenario. However, in local life service, an end-to-end generative recommendation model has not yet been developed as there are some key challenges to be solved. The first challenge is how to make full use of geographic information. The second challenge is how to balance multiple objectives, including user interests, the distance between user and stores, and some other business objectives. To address the challenges, we propose OneLoc. Specifically, we leverage geographic information from different perspectives: (1) geo-aware semantic ID incorporates both video and geographic information for tokenization, (2) geo-aware self-attention in the encoder leverages both video location similarity and user's real-time location, and (3) neighbor-aware prompt captures rich context information surrounding users for generation. To balance multiple objectives, we use reinforcement learning and propose two reward functions, i.e., geographic reward and GMV reward. With the above design, OneLoc achieves outstanding offline and online performance. In fact, OneLoc has been deployed in local life service of Kuaishou App. It serves 400 million active users daily, achieving 21.016% and 17.891% improvements in terms of gross merchandise value (GMV) and orders numbers.

cs.IR↗

arXiv2025

From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditional RL approaches, RLVR leverages rule-based feedback to guide LLMs in generating and refining complex reasoning chains -- a process critically dependent on effective exploration strategies. While prior work has demonstrated RLVR's empirical success, the fundamental mechanisms governing LLMs' exploration behaviors remain underexplored. This technical report presents a systematic investigation of exploration capacities in RLVR, covering four main aspects: (1) exploration space shaping, where we develop quantitative metrics to characterize LLMs' capability boundaries; (2) entropy-performance exchange, analyzed across training stages, individual instances, and token-level patterns; and (3) RL performance optimization, examining methods to effectively translate exploration gains into measurable improvements. By unifying previously identified insights with new empirical evidence, this work aims to provide a foundational framework for advancing RLVR systems.

cs.CL↗

arXiv2025

EF-VI: Enhancing End-Frame Injection for Video Inbetweening

Video inbetweening aims to synthesize intermediate video sequences conditioned on the given start and end frames. Current state-of-the-art methods primarily extend large-scale pre-trained Image-to-Video Diffusion Models (I2V-DMs) by incorporating the end-frame condition via direct fine-tuning or temporally bidirectional sampling. However, the former results in a weak end-frame constraint, while the latter inevitably disrupts the input representation of video frames, leading to suboptimal performance. To improve the end-frame constraint while avoiding disruption of the input representation, we propose a novel video inbetweening framework specific to recent and more powerful transformer-based I2V-DMs, termed EF-VI. It efficiently strengthens the end-frame constraint by utilizing an enhanced injection. This is based on our proposed well-designed lightweight module, termed EF-Net, which encodes only the end frame and expands it into temporally adaptive frame-wise features injected into the I2V-DM. Extensive experiments demonstrate the superiority of our EF-VI compared with other baselines.

cs.CV↗

arXiv2025

Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection

Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes. However, existing methods suffer from inefficient feature leverage and high computational costs due to redundant feature processing and rigid query allocation. To address these challenges, we propose Dome-DETR, a novel framework with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection. To reduce feature redundancies, we introduce a lightweight Density-Focal Extractor (DeFE) to produce clustered compact foreground masks. Leveraging these masks, we incorporate Masked Window Attention Sparsification (MWAS) to focus computational resources on the most informative regions via sparse attention. Besides, we propose Progressive Adaptive Query Initialization (PAQI), which adaptively modulates query density across spatial areas for better query allocation. Extensive experiments demonstrate that Dome-DETR achieves state-of-the-art performance (+3.3 AP on AI-TOD-V2 and +2.5 AP on VisDrone) while maintaining low computational complexity and a compact model size. Code is available at https://github.com/RicePasteM/Dome-DETR.

cs.CV↗