Hanlin Wu

Hanlin Wu, Ning Ni, Libao Zhang

Deep learning-based algorithms have greatly improved the performance of remote sensing image (RSI) super-resolution (SR). However, increasing network depth and parameters cause a huge burden of computing and storage. Directly reducing the depth or width of existing models results in a large performance drop. We observe that the SR difficulty of different regions in an RSI varies greatly, and existing methods use the same deep network to process all regions in an image, resulting in a waste of computing resources. In addition, existing SR methods generally predefine integer scale factors and cannot perform stepless SR, i.e., a single model can deal with any potential scale factor. Retraining the model on each scale factor wastes considerable computing resources and model storage space. To address the above problems, we propose a saliency-aware dynamic routing network (SalDRN) for lightweight and stepless SR of RSIs. First, we introduce visual saliency as an indicator of region-level SR difficulty and integrate a lightweight saliency detector into the SalDRN to capture pixel-level visual characteristics. Then, we devise a saliency-aware dynamic routing strategy that employs path selection switches to adaptively select feature extraction paths of appropriate depth according to the SR difficulty of sub-image patches. Finally, we propose a novel lightweight stepless upsampling module whose core is an implicit feature function for realizing mapping from low-resolution feature space to high-resolution feature space. Comprehensive experiments verify that the SalDRN can achieve a good trade-off between performance and complexity. The code is available at \url{https://github.com/hanlinwu/SalDRN}.

Pei Deng, Wenqian Zhou, Hanlin Wu

Remote sensing (RS) change analysis is vital for monitoring Earth's dynamic processes by detecting alterations in images over time. Traditional change detection excels at identifying pixel-level changes but lacks the ability to contextualize these alterations. While recent advancements in change captioning offer natural language descriptions of changes, they do not support interactive, user-specific queries. To address these limitations, we introduce ChangeChat, the first bitemporal vision-language model (VLM) designed specifically for RS change analysis. ChangeChat utilizes multimodal instruction tuning, allowing it to handle complex queries such as change captioning, category-specific quantification, and change localization. To enhance the model's performance, we developed the ChangeChat-87k dataset, which was generated using a combination of rule-based methods and GPT-assisted techniques. Experiments show that ChangeChat offers a comprehensive, interactive solution for RS change analysis, achieving performance comparable to or even better than state-of-the-art (SOTA) methods on specific tasks, and significantly surpassing the latest general-domain model, GPT-4. Code and pre-trained weights are available at https://github.com/hanlinwu/ChangeChat.

Hanlin Wu, Ning Ni, Shan Wang et al.

Remote sensing images (RSIs) in real scenes may be disturbed by multiple factors such as optical blur, undersampling, and additional noise, resulting in complex and diverse degradation models. At present, the mainstream SR algorithms only consider a single and fixed degradation (such as bicubic interpolation) and cannot flexibly handle complex degradations in real scenes. Therefore, designing a super-resolution (SR) model that can cope with various degradations is gradually attracting the attention of researchers. Some studies first estimate the degradation kernels and then perform degradation-adaptive SR but face the problems of estimation error amplification and insufficient high-frequency details in the results. Although blind SR algorithms based on generative adversarial networks (GAN) have greatly improved visual quality, they still suffer from pseudo-texture, mode collapse, and poor training stability. In this article, we propose a novel blind SR framework based on the stochastic normalizing flow (BlindSRSNF) to address the above problems. BlindSRSNF learns the conditional probability distribution over the high-resolution image space given a low-resolution (LR) image by explicitly optimizing the variational bound on the likelihood. BlindSRSNF is easy to train and can generate photo-realistic SR results that outperform GAN-based models. Besides, we introduce a degradation representation strategy based on contrastive learning to avoid the error amplification problem caused by the explicit degradation estimation. Comprehensive experiments show that the proposed algorithm can obtain SR results with excellent visual perception quality on both simulated LR and real-world RSIs.

Ruiqi Wang, Qi Yu, Jie Ma et al.

High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of map super-resolution, which enhances coarse low-resolution (LR) land-cover products into HR maps at the resolution of the input imagery. Existing weakly supervised methods can leverage LR labels, but they typically use them to retrain dense predictors with substantial computational cost. We propose MapSR, a prompt-driven framework that decouples supervision from model training. MapSR uses LR labels once to extract class prompts from frozen vision foundation model features through a lightweight linear probe, after which HR mapping proceeds via training-free metric inference and graph-based prediction refinement. Specifically, class prompts are estimated by aggregating high-confidence HR features identified by the linear probe, and HR predictions are obtained by cosine-similarity matching followed by graph-based propagation for spatial refinement. Experiments on the Chesapeake Bay dataset show that MapSR achieves 59.64% mIoU without any HR labels, remaining competitive with the strongest weakly supervised baseline and surpassing a fully supervised baseline. Notably, MapSR reduces trainable parameters by four orders of magnitude and shortens training time from hours to minutes, enabling scalable HR mapping under limited annotation and compute budgets. The code is available at https://github.com/rikirikirikiriki/MapSR.

Jiangwei Mo, Xi Lu, Hanlin Wu

High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints and costs. In recent years, generative super-resolution (SR) methods, particularly diffusion models, have made significant progress. However, they typically require slow iterative inference with 40--1000 steps and exhibit limited flexibility in continuous-scale SR settings. To address these issues, we propose FlowGS, a generative reconstruction framework for arbitrary-scale SR of RSIs. FlowGS models the high-frequency detail representations between high- and low-resolution images and learns a continuous probability flow from noise to detail priors via flow matching (FM) constrained by shortcut consistency, thereby reducing generative complexity and improving inference efficiency. Additionally, we employ 2D Gaussian splatting to construct a continuous feature field, thereby enabling flexible reconstruction at arbitrary query locations. Experimental results show that FlowGS delivers competitive perceptual quality compared with existing methods in both continuous-scale and fixed-scale SR settings, with substantially improved inference efficiency.

Hanlin Wu, Zhenguang G. Cai

Spoken language is often, if not always, understood in a context formed by the identity of the speaker. For example, we can easily make sense of an utterance such as "I'm going to have a manicure this weekend" or "The first time I got pregnant I had a hard time" when spoken by a woman, but it would be harder to understand when it is spoken by a man. Previous ERP studies have shown mixed results regarding the neurophysiological responses to such speaker-content mismatches, with some reporting an N400 effect and others a P600 effect. In an EEG experiment involving 64 participants, we used social and biological mismatches as test cases to demonstrate how these distinct ERP patterns reflect different aspects of rational inference. We showed that when the mismatch involves social stereotypes (e.g., men getting a manicure), listeners can arrive at a "literal" interpretation by integrating the content with their social knowledge, though this integration requires additional effort due to stereotype violations-resulting in an N400 effect. In contrast, when the mismatch involves biological knowledge (e.g., men getting pregnant), a "literal" interpretation becomes highly implausible or impossible, leading listeners to treat the input as potentially containing errors and engage in correction processes-resulting in a P600 effect. Supporting this rational inference framework, we found that the social N400 effect decreased as a function of the listener's personality trait of openness (as more open-minded individuals maintain more flexible social expectations), while the biological P600 effect remained robust (as biological constraints are recognized regardless of individual personalities). Our findings help to reconcile empirical inconsistencies and reveal how rational inference shapes speaker-contextualized language comprehension.

Hanlin Wu, Yuxuan Song, Jingjing Gong et al.

Generative modeling of crystal data distribution is an important yet challenging task due to the unique periodic physical symmetry of crystals. Diffusion-based methods have shown early promise in modeling crystal distribution. More recently, Bayesian Flow Networks were introduced to aggregate noisy latent variables, resulting in a variance-reduced parameter space that has been shown to be advantageous for modeling Euclidean data distributions with structural constraints (Song et al., 2023). Inspired by this, we seek to unlock its potential for modeling variables located in non-Euclidean manifolds e.g. those within crystal structures, by overcoming challenging theoretical issues. We introduce CrysBFN, a novel crystal generation method by proposing a periodic Bayesian flow, which essentially differs from the original Gaussian-based BFN by exhibiting non-monotonic entropy dynamics. To successfully realize the concept of periodic Bayesian flow, CrysBFN integrates a new entropy conditioning mechanism and empirically demonstrates its significance compared to time-conditioning. Extensive experiments over both crystal ab initio generation and crystal structure prediction tasks demonstrate the superiority of CrysBFN, which consistently achieves new state-of-the-art on all benchmarks. Surprisingly, we found that CrysBFN enjoys a significant improvement in sampling efficiency, e.g., ~100x speedup 10 v.s. 2000 steps network forwards) compared with previous diffusion-based methods on MP-20 dataset. Code is available at https://github.com/wu-han-lin/CrysBFN.

Hanlin Wu, Pengfei Lin, Ehsan Javanmardi et al.

As autonomous driving moves toward full scene understanding, 3D semantic occupancy prediction has emerged as a crucial perception task, offering voxel-level semantics beyond traditional detection and segmentation paradigms. However, such a refined representation for scene understanding incurs prohibitive computation and memory overhead, posing a major barrier to practical real-time deployment. To address this, we propose SUG-Occ, an explicit Semantics and Uncertainty Guided Sparse Learning Enabled 3D Occupancy Prediction Framework, which exploits the inherent sparsity of 3D scenes to reduce redundant computation while maintaining geometric and semantic completeness. Specifically, we first utilize semantic and uncertainty priors to suppress projections from free space during view transformation while employing an explicit unsigned distance encoding to enhance geometric consistency, producing a structurally consistent sparse 3D representation. Secondly, we design an cascade sparse completion module via hyper cross sparse convolution and generative upsampling to enable efficiently coarse-to-fine reasoning. Finally, we devise an object contextual representation (OCR) based mask decoder that aggregates global semantic context from sparse features and refines voxel-wise predictions via lightweight query-context interactions, avoiding expensive attention operations over volumetric features. Extensive experiments on SemanticKITTI benchmark demonstrate that the proposed approach outperforms the baselines, achieving a 7.34/% improvement in accuracy and a 57.8\% gain in efficiency.

Pei Deng, Wenqian Zhou, Hanlin Wu

Accurate interpretation of land-cover changes in multi-temporal satellite imagery is critical for real-world scenarios. However, existing methods typically provide only one-shot change masks or static captions, limiting their ability to support interactive, query-driven analysis. In this work, we introduce remote sensing image change analysis (RSICA) as a new paradigm that combines the strengths of change detection and visual question answering to enable multi-turn, instruction-guided exploration of changes in bi-temporal remote sensing images. To support this task, we construct ChangeChat-105k, a large-scale instruction-following dataset, generated through a hybrid rule-based and GPT-assisted process, covering six interaction types: change captioning, classification, quantification, localization, open-ended question answering, and multi-turn dialogues. Building on this dataset, we propose DeltaVLM, an end-to-end architecture tailored for interactive RSICA. DeltaVLM features three innovations: (1) a fine-tuned bi-temporal vision encoder to capture temporal differences; (2) a visual difference perception module with a cross-semantic relation measuring (CSRM) mechanism to interpret changes; and (3) an instruction-guided Q-former to effectively extract query-relevant difference information from visual changes, aligning them with textual instructions. We train DeltaVLM on ChangeChat-105k using a frozen large language model, adapting only the vision and alignment modules to optimize efficiency. Extensive experiments and ablation studies demonstrate that DeltaVLM achieves state-of-the-art performance on both single-turn captioning and multi-turn interactive change analysis, outperforming existing multimodal large language models and remote sensing vision-language models. Code, dataset and pre-trained weights are available at https://github.com/hanlinwu/DeltaVLM.

Hanlin Wu, Zhenguang G. Cai

The identity of a speaker significantly influences spoken language comprehension by affecting both perception and expectation. This review explores speaker effects, focusing on how speaker information impacts language processing. We propose an integrative model featuring the interplay between bottom-up perception-based processes driven by acoustic details and top-down expectation-based processes driven by a speaker model. The acoustic details influence lower-level perception, while the speaker model modulates both lower-level and higher-level processes such as meaning interpretation and pragmatic inferences. We define speaker-idiosyncrasy and speaker-demographics effects and demonstrate how bottom-up and top-down processes interact at various levels in different scenarios. This framework contributes to psycholinguistic theory by offering a comprehensive account of how speaker information interacts with linguistic content to shape message construction. We suggest that speaker effects can serve as indices of a language learner's proficiency and an individual's characteristics of social cognition. We encourage future research to extend these findings to AI speakers, probing the universality of speaker effects across humans and artificial agents.

Xiaohui Sun, Hanlin Wu

Face restoration has advanced significantly with generative models like diffusion models and flow matching (FM), which learn continuous-time mappings between distributions. However, existing FM-based approaches often start from Gaussian noise, ignoring the inherent dependency between low-quality (LQ) and high-quality (HQ) data, resulting in path crossovers, curved trajectories, and multi-step sampling requirements. To address these issues, we propose Shortcut-enhanced Coupling flow for Face Restoration (SCFlowFR). First, it establishes a \textit{data-dependent coupling} that explicitly models the LQ--HQ dependency, minimizing path crossovers and promoting near-linear transport. Second, we employ conditional mean estimation to obtain a coarse prediction that refines the source anchor to tighten coupling and conditions the velocity field to stabilize large-step updates. Third, a shortcut constraint supervises average velocities over arbitrary time intervals, enabling accurate one-step inference. Experiments demonstrate that SCFlowFR achieves state-of-the-art one-step face restoration quality with inference speed comparable to traditional non-diffusion methods.

Hanlin Wu, Jiangwei Mo, Xiaohui Sun et al.

Recent advancements in diffusion models have significantly improved performance in super-resolution (SR) tasks. However, previous research often overlooks the fundamental differences between SR and general image generation. General image generation involves creating images from scratch, while SR focuses specifically on enhancing existing low-resolution (LR) images by adding typically missing high-frequency details. This oversight not only increases the training difficulty but also limits their inference efficiency. Furthermore, previous diffusion-based SR methods are typically trained and inferred at fixed integer scale factors, lacking flexibility to meet the needs of up-sampling with non-integer scale factors. To address these issues, this paper proposes an efficient and elastic diffusion-based SR model (E$^2$DiffSR), specially designed for continuous-scale SR in remote sensing imagery. E$^2$DiffSR employs a two-stage latent diffusion paradigm. During the first stage, an autoencoder is trained to capture the differential priors between high-resolution (HR) and LR images. The encoder intentionally ignores the existing LR content to alleviate the encoding burden, while the decoder introduces an SR branch equipped with a continuous scale upsampling module to accomplish the reconstruction under the guidance of the differential prior. In the second stage, a conditional diffusion model is learned within the latent space to predict the true differential prior encoding. Experimental results demonstrate that E$^2$DiffSR achieves superior objective metrics and visual quality compared to the state-of-the-art SR methods. Additionally, it reduces the inference time of diffusion-based SR methods to a level comparable to that of non-diffusion methods.

Hanlin Wu, Pengfei Lin, Ehsan Javanmardi et al.

3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, the perception capability of a single vehicle is inherently constrained by occlusion, restricted sensor range, and narrow viewpoints. To address these limitations, collaborative perception enables the exchange of complementary information, thereby enhancing the completeness and accuracy. In the absence of a dedicated dataset for collaborative 3D semantic occupancy prediction, we augment an existing collaborative perception dataset by replaying it in CARLA with a high-resolution semantic voxel sensor to provide dense and comprehensive occupancy annotations. In addition, we establish benchmarks with varying prediction ranges designed to systematically assess the impact of spatial extent on collaborative prediction. We further develop a baseline model that performs inter-agent feature fusion via spatial alignment and attention aggregation. Experimental results demonstrate that our baseline model consistently outperforms single-agent models, with increasing gains observed as the prediction range expands.

Hanlin Wu, Xufeng Duan, Zhenguang Cai

Voice-based AI development faces unique challenges in processing both linguistic and paralinguistic information. This study compares how large audio-language models (LALMs) and humans integrate speaker characteristics during speech comprehension, asking whether LALMs process speaker-contextualized language in ways that parallel human cognitive mechanisms. We compared two LALMs' (Qwen2-Audio and Ultravox 0.5) processing patterns with human EEG responses. Using surprisal and entropy metrics from the models, we analyzed their sensitivity to speaker-content incongruency across social stereotype violations (e.g., a man claiming to regularly get manicures) and biological knowledge violations (e.g., a man claiming to be pregnant). Results revealed that Qwen2-Audio exhibited increased surprisal for speaker-incongruent content and its surprisal values significantly predicted human N400 responses, while Ultravox 0.5 showed limited sensitivity to speaker characteristics. Importantly, neither model replicated the human-like processing distinction between social violations (eliciting N400 effects) and biological violations (eliciting P600 effects). These findings reveal both the potential and limitations of current LALMs in processing speaker-contextualized language, and suggest differences in social-linguistic processing mechanisms between humans and LALMs.

Hanlin Wu, Xiaohui Rao, Zhenguang G Cai

Listeners adapt language comprehension based on their mental representations of speakers, but how these representations are updated remains unclear. We investigated whether listeners probabilistically adapt comprehension based on the frequency of speakers making stereotype-incongruent statements. In two EEG experiments, participants heard speakers make stereotype-congruent or incongruent statements, with incongruency base rate manipulated. In Experiment 1, stereotype-incongruent statements decreased high-beta (21-30 Hz) and theta (4-6 Hz) oscillatory power in the low base rate condition but increased it in the high base rate condition. The theta effect varied with listeners' openness trait: less open-minded participants tended to show theta increases to stereotype incongruencies, while more open-minded participants tended to show theta decreases. In Experiment 2, we dissociated incongruency base rate from the target speaker by manipulating it using a non-target speaker and found that only the high-beta effect persisted. Our findings reveal two potential mechanisms: a speaker-general mechanism (indicated by high-beta oscillations) that adjusts overall expectations about hearing statements that violate social stereotypes, and a speaker-specific mechanism (indicated by theta oscillations) that updates a more detailed mental model specifically about an individual speaker. These findings provide evidence for how language processing interacts with social cognition.

Xiaohui Rao, Hanlin Wu, Zhenguang G. Cai

As AI companions become capable of human-like communication, including telling jokes, understanding how people cognitively and emotionally respond to AI humor becomes increasingly important. This study used electroencephalography (EEG) to compare how people process humor from AI versus human sources. Behavioral analysis revealed that participants rated AI and human humor as comparably funny. However, neurophysiological data showed that AI humor elicited a smaller N400 effect, suggesting reduced cognitive effort during the processing of incongruity. This was accompanied by a larger Late Positive Potential (LPP), indicating a greater degree of surprise and emotional response. This enhanced LPP likely stems from the violation of low initial expectations regarding AI's comedic capabilities. Furthermore, a key temporal dynamic emerged: human humor showed habituation effects, marked by an increasing N400 and a decreasing LPP over time. In contrast, AI humor demonstrated increasing processing efficiency and emotional reward, with a decreasing N400 and an increasing LPP. This trajectory reveals how the brain can dynamically update its predictive model of AI capabilities. This process of cumulative reinforcement challenges "algorithm aversion" in humor, as it demonstrates how cognitive adaptation to AI's language patterns can lead to an intensified emotional reward. Additionally, participants' social attitudes toward AI modulated these neural responses, with higher perceived AI trustworthiness correlating with enhanced emotional engagement. These findings indicate that the brain responds to AI humor with surprisingly positive and intense reactions, highlighting humor's potential for fostering genuine engagement in human-AI social interaction.

Xiaohui Rao, Hanlin Wu, Zhenguang G. Cai

As Large Language Models (LLMs) are increasingly deployed as social agents and trained to produce humor and irony, a question emerges: when encountering witty AI remarks, do people interpret these as intentional communication or mere computational output? This study investigates whether people adopt the intentional stance, attributing mental states to explain behavior,toward AI during irony comprehension. Irony provides an ideal paradigm because it requires distinguishing intentional contradictions from unintended errors through effortful semantic reanalysis. We compared behavioral and neural responses to ironic statements from AI versus human sources using established ERP components: P200 reflecting early incongruity detection and P600 indexing cognitive efforts in reinterpreting incongruity as deliberate irony. Results demonstrate that people do not fully adopt the intentional stance toward AI-generated irony. Behaviorally, participants attributed incongruity to deliberate communication for both sources, though significantly less for AI than human, showing greater tendency to interpret AI incongruities as computational errors. Neural data revealed attenuated P200 and P600 effects for AI-generated irony, suggesting reduced effortful detection and reanalysis consistent with diminished attribution of communicative intent. Notably, people who perceived AI as more sincere showed larger P200 and P600 effects for AI-generated irony, suggesting that intentional stance adoption is calibrated by specific mental models of artificial agents. These findings reveal that source attribution shapes neural processing of social-communicative phenomena. Despite current LLMs' linguistic sophistication, achieving genuine social agency requires more than linguistic competence, it necessitates a shift in how humans perceive and attribute intentionality to artificial agents.

Xiaohui Sun, Jiangwei Mo, Hanlin Wu et al.

Recent advancements in diffusion models (DMs) have greatly advanced remote sensing image super-resolution (RSISR). However, their iterative sampling processes often result in slow inference speeds, limiting their application in real-time tasks. To address this challenge, we propose the latent consistency model for super-resolution (LCMSR), a novel single-step diffusion approach designed to enhance both efficiency and visual quality in RSISR tasks. Our proposal is structured into two distinct stages. In the first stage, we pretrain a residual autoencoder to encode the differential information between high-resolution (HR) and low-resolution (LR) images, transitioning the diffusion process into a latent space to reduce computational costs. The second stage focuses on consistency diffusion learning, which aims to learn the distribution of residual encodings in the latent space, conditioned on LR images. The consistency constraint enforces that predictions at any two timesteps along the reverse diffusion trajectory remain consistent, enabling direct mapping from noise to data. As a result, the proposed LCMSR reduces the iterative steps of traditional diffusion models from 50-1000 or more to just a single step, significantly improving efficiency. Experimental results demonstrate that LCMSR effectively balances efficiency and performance, achieving inference times comparable to non-diffusion models while maintaining high-quality output.

Hanlin Wu, Ning Ni, Libao Zhang

Single-image super-resolution (SR) with fixed and discrete scale factors has achieved great progress due to the development of deep learning technology. However, the continuous-scale SR, which aims to use a single model to process arbitrary (integer or non-integer) scale factors, is still a challenging task. The existing SR models generally adopt static convolution to extract features, and thus unable to effectively perceive the change of scale factor, resulting in limited generalization performance on multi-scale SR tasks. Moreover, the existing continuous-scale upsampling modules do not make full use of multi-scale features and face problems such as checkerboard artifacts in the SR results and high computational complexity. To address the above problems, we propose a scale-aware dynamic network (SADN) for continuous-scale SR. First, we propose a scale-aware dynamic convolutional (SAD-Conv) layer for the feature learning of multiple SR tasks with various scales. The SAD-Conv layer can adaptively adjust the attention weights of multiple convolution kernels based on the scale factor, which enhances the expressive power of the model with a negligible extra computational cost. Second, we devise a continuous-scale upsampling module (CSUM) with the multi-bilinear local implicit function (MBLIF) for any-scale upsampling. The CSUM constructs multiple feature spaces with gradually increasing scales to approximate the continuous feature representation of an image, and then the MBLIF makes full use of multi-scale features to map arbitrary coordinates to RGB values in high-resolution space. We evaluate our SADN using various benchmarks. The experimental results show that the CSUM can replace the previous fixed-scale upsampling layers and obtain a continuous-scale SR network while maintaining performance. Our SADN uses much fewer parameters and outperforms the state-of-the-art SR methods.