arXiv subjects

Zhimeng Zhang

Publications and source records attributed to Zhimeng Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Juno Microwave Radiometer Observations Reveal A Warmer Polar Atmosphere on Jupiter

The intriguing circumpolar cyclone pattern at Jupiter's poles raises fundamental questions about how these systems are organized vertically and, further, how the planet's internal heat shapes and sustains them in the absence of solar insolation. We report recent close-in observations of Jupiter's north pole acquired by NASA's Juno Microwave Radiometer (MWR), which achieved comprehensive microwave mapping of the region at an unprecedentedly high resolution. Using six-channel measurements from eleven perijove passes (PJ51-PJ61) poleward of 75N, we derive polar-mean nadir brightness temperatures and limb-darkening spectra that together point to two equally plausible atmospheric scenarios: (1) a dry-adiabatic profile with slightly depleted ammonia gas at a few bars, or (2) a moist-adiabatic profile with uniform ammonia. Markov chain Monte Carlo retrievals yield a deep ammonia abundance of 354.8+12.0/-11.0 ppmv (3+/-0.1 x solar) and a water abundance of 1.8+1.5/-1.1 x 1000 ppmv (2.1+1.8/-1.3 x solar), resembling previous estimates at lower latitudes. Remarkably, the north pole is found to be 6-7 K warmer than the equator at the 1-bar level, although the inferred difference is close to the 1-sigma uncertainty level. If confirmed, this result would suggest an enhanced internal heat flux toward the poles, which is consistent with the more intense lightning activity observed at high latitudes.

astro-ph.EP↗

arXiv2026

From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning

Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for embodied, egocentric tasks. A major source of failure is their reliance on temporal priors learned from passive video data, which often leads to spatiotemporal hallucinations and poor generalization in dynamic environments. To address this, we present EgoTSR, a curriculum-based framework for learning task-oriented spatiotemporal reasoning. EgoTSR is built on the premise that embodied reasoning should evolve from explicit spatial understanding to internalized task-state assessment and finally to long-horizon planning. To support this paradigm, we construct EgoTSR-Data, a large-scale dataset comprising 46 million samples organized into three stages: Chain-of-Thought (CoT) supervision, weakly supervised tagging, and long-horizon sequences. Extensive experiments demonstrate that EgoTSR effectively eliminates chronological biases, achieving 92.4% accuracy on long-horizon logical reasoning tasks while maintaining high fine-grained perceptual precision, significantly outperforming existing open-source and closed-source state-of-the-art models.

cs.AI↗

arXiv2025

REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection

The rapid progress of visual generative models has made AI-generated images increasingly difficult to distinguish from authentic ones, posing growing risks to social trust and information integrity. This motivates detectors that are not only accurate but also forensically explainable. While recent multimodal approaches improve interpretability, many rely on post-hoc rationalizations or coarse visual cues, without constructing verifiable chains of evidence, thus often leading to poor generalization. We introduce REVEAL-Bench, a reasoning-enhanced multimodal benchmark for AI-generated image forensics, structured around explicit chains of forensic evidence derived from lightweight expert models and consolidated into step-by-step chain-of-evidence traces. Based on this benchmark, we propose REVEAL (\underline{R}easoning-\underline{e}nhanced Forensic E\underline{v}id\underline{e}nce \underline{A}na\underline{l}ysis), an explainable forensic framework trained with expert-grounded reinforcement learning. Our reward design jointly promotes detection accuracy, evidence-grounded reasoning stability, and explanation faithfulness. Extensive experiments demonstrate significantly improved cross-domain generalization and more faithful explanations to baseline detectors. All data and codes will be released.

cs.CV↗

arXiv2025

EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration

Large language models (LLMs) are increasingly leveraged as foundational backbones in the development of advanced recommender systems, offering enhanced capabilities through their extensive knowledge and reasoning. Existing llm-based recommender systems (RSs) often face challenges due to the significant differences between the linguistic semantics of pre-trained LLMs and the collaborative semantics essential for RSs. These systems use pre-trained linguistic semantics but learn collaborative semantics from scratch via the llm-Backbone. However, LLMs are not designed for recommendations, leading to inefficient collaborative learning, weak result correlations, and poor integration of traditional RS features. To address these challenges, we propose EAGER-LLM, a decoder-only llm-based generative recommendation framework that integrates endogenous and exogenous behavioral and semantic information in a non-intrusive manner. Specifically, we propose 1)dual-source knowledge-rich item indices that integrates indexing sequences for exogenous signals, enabling efficient link-wide processing; 2)non-invasive multiscale alignment reconstruction tasks guide the model toward a deeper understanding of both collaborative and semantic signals; 3)an annealing adapter designed to finely balance the model's recommendation performance with its comprehension capabilities. We demonstrate EAGER-LLM's effectiveness through rigorous testing on three public benchmarks.

cs.IR↗

arXiv2024

Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models

Large vision models have been found vulnerable to adversarial examples, emphasizing the need for enhancing their adversarial robustness. While adversarial training is an effective defense for deep convolutional models, it often faces scalability issues with large vision models due to high computational costs. Recent approaches propose robust fine-tuning methods, such as adversarial tuning of low-rank adaptation (LoRA) in large vision models, but they still struggle to match the accuracy of full parameter adversarial fine-tuning. The integration of various defense mechanisms offers a promising approach to enhancing the robustness of large vision models, yet this paradigm remains underexplored. To address this, we propose hyper adversarial tuning (HyperAT), which leverages shared defensive knowledge among different methods to improve model robustness efficiently and effectively simultaneously. Specifically, adversarial tuning of each defense method is formulated as a learning task, and a hypernetwork generates LoRA specific to this defense. Then, a random sampling and tuning strategy is proposed to extract and facilitate the defensive knowledge transfer between different defenses. Finally, diverse LoRAs are merged to enhance the adversarial robustness. Experiments on various datasets and model architectures demonstrate that HyperAT significantly enhances the adversarial robustness of pretrained large vision models without excessive computational overhead, establishing a new state-of-the-art benchmark.

cs.CV↗

arXiv2024

HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs

The emergence of diverse generative vision models has recently enabled the synthesis of visually realistic images, underscoring the critical need for effectively detecting these generated images from real photos. Despite advances in this field, existing detection approaches often struggle to accurately identify synthesized images generated by different generative models. In this work, we introduce a novel and generalizable detection framework termed HyperDet, which innovatively captures and integrates shared knowledge from a collection of functionally distinct and lightweight expert detectors. HyperDet leverages a large pretrained vision model to extract general detection features while simultaneously capturing and enhancing task-specific features. To achieve this, HyperDet first groups SRM filters into five distinct groups to efficiently capture varying levels of pixel artifacts based on their different functionality and complexity. Then, HyperDet utilizes a hypernetwork to generate LoRA model weights with distinct embedding parameters. Finally, we merge the LoRA networks to form an efficient model ensemble. Also, we propose a novel objective function that balances the pixel and semantic artifacts effectively. Extensive experiments on the UnivFD and Fake2M datasets demonstrate the effectiveness of our approach, achieving state-of-the-art performance. Moreover, our work paves a new way to establish generalizable domain-specific fake image detectors based on pretrained large vision models.

cs.CV↗

arXiv2024

Norface: Improving Facial Expression Analysis by Identity Normalization

Facial Expression Analysis remains a challenging task due to unexpected task-irrelevant noise, such as identity, head pose, and background. To address this issue, this paper proposes a novel framework, called Norface, that is unified for both Action Unit (AU) analysis and Facial Emotion Recognition (FER) tasks. Norface consists of a normalization network and a classification network. First, the carefully designed normalization network struggles to directly remove the above task-irrelevant noise, by maintaining facial expression consistency but normalizing all original images to a common identity with consistent pose, and background. Then, these additional normalized images are fed into the classification network. Due to consistent identity and other factors (e.g. head pose, background, etc.), the normalized images enable the classification network to extract useful expression information more effectively. Additionally, the classification network incorporates a Mixture of Experts to refine the latent representation, including handling the input of facial representations and the output of multiple (AU or emotion) labels. Extensive experiments validate the carefully designed framework with the insight of identity normalization. The proposed method outperforms existing SOTA methods in multiple facial expression analysis tasks, including AU detection, AU intensity estimation, and FER tasks, as well as their cross-dataset tasks. For the normalized datasets and code please visit {https://norface-fea.github.io/}.

cs.CV↗

arXiv2024

Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment

A song is a combination of singing voice and accompaniment. However, existing works focus on singing voice synthesis and music generation independently. Little attention was paid to explore song synthesis. In this work, we propose a novel task called text-to-song synthesis which incorporating both vocals and accompaniments generation. We develop Melodist, a two-stage text-to-song method that consists of singing voice synthesis (SVS) and vocal-to-accompaniment (V2A) synthesis. Melodist leverages tri-tower contrastive pretraining to learn more effective text representation for controllable V2A synthesis. A Chinese song dataset mined from a music website is built up to alleviate data scarcity for our research. The evaluation results on our dataset demonstrate that Melodist can synthesize songs with comparable quality and style consistency. Audio samples can be found in https://text2songMelodist.github.io/Sample/.

eess.AS↗

arXiv2023

The composition of Saturn's rings

The origin and evolution of Saturn's rings is critical to understanding the Saturnian system as a whole. Here, we discuss the physical and chemical composition of the rings, as a foundation for evolutionary models described in subsequent chapters. We review the physical characteristics of the main rings, and summarize current constraints on their chemical composition. Radial trends are observed in temperature and to a limited extent in particle size distribution, with the C ring exhibiting higher temperatures and a larger population of small particles. The C ring also shows evidence for the greatest abundance of silicate material, perhaps indicative of formation from a rocky body. The C ring and Cassini Division have lower optical depths than the A and B rings, which contributes to the higher abundance of the exogenous neutral absorber in these regions. Overall, the main ring composition is strongly dominated by water ice, with minor silicate, UV absorber, and neutral absorber components. Sampling of the innermost D ring during Cassini's Grand Finale provides a new set of in situ constraints on the ring composition, and we explore ongoing work to understand the linkages between the main rings and the D ring. The D ring material is organic- and silicate-rich and water-poor relative to the main rings, with a large population of small grains. This composition may be explained in part by volatile losses in the D ring, and current constraints suggest some degree of fractionation rather than sampling of the bulk D ring material.

astro-ph.EP↗

arXiv2023

Efficient production of nuclear isomer $^{93m}$Mo with laser-accelerated proton beam and an astrophysical implication on $^{92m}$Mo production

Nuclear isomers play a key role in the creation of the elements in the universe and have a number of fascinating potential applications related to the controlled release of nuclear energy on demand. Particularly, $^{93m}$Mo isomer is a good candidate for studying the depletion of nuclear isomer via nuclear excitation by electron capture. For such purposes, efficient approach for $^{93m}$Mo production needs to be explored. In the present work, we demonstrate experimentally an efficient production of $^{93m}$Mo through $^{93}$Nb(p, n) reaction induced by intense laser pulse. When a ps-duration, 100-J laser pulse is employed, the $^{93m}$Mo isomer at 2425 keV (21/2$^+$, $T_{1/2}$ = 6.85 h) are generated with a high yield of $1.8\times10^6$ particles/shot. The resulting peak efficiency is expected to be $10^{17}$ particles/s, which is at least five orders of magnitudes higher than using classical proton accelerator. The effects of production and destruction of $^{93m}$Mo on the controversial astrophysical p-isotope $^{92}$Mo are studied. It is found that the $^{93}$Nb(p, n)-$^{93m}$Mo reaction is an important production path for ^{93m}Mo seed nucleus, and the influence of ^{93m}Mo-^{92}Mo reaction flow on ^{92}Mo production cannot be ignored. In addition, we propose to directly measure the astrophysical rate of (p, n) reaction using laser-induced proton beam since the latter one fits the Maxwell-Boltzmann distribution well. We conclude that laser-induced proton beam opens a new path to produce nuclear isomers with high peak efficiency towards the understanding of p-nuclei nucleosythesis.

nucl-ex↗

arXiv2023

FlowFace++: Explicit Semantic Flow-supervised End-to-End Face Swapping

This work proposes a novel face-swapping framework FlowFace++, utilizing explicit semantic flow supervision and end-to-end architecture to facilitate shape-aware face-swapping. Specifically, our work pretrains a facial shape discriminator to supervise the face swapping network. The discriminator is shape-aware and relies on a semantic flow-guided operation to explicitly calculate the shape discrepancies between the target and source faces, thus optimizing the face swapping network to generate highly realistic results. The face swapping network is a stack of a pre-trained face-masked autoencoder (MAE), a cross-attention fusion module, and a convolutional decoder. The MAE provides a fine-grained facial image representation space, which is unified for the target and source faces and thus facilitates final realistic results. The cross-attention fusion module carries out the source-to-target face swapping in a fine-grained latent space while preserving other attributes of the target image (e.g. expression, head pose, hair, background, illumination, etc). Lastly, the convolutional decoder further synthesizes the swapping results according to the face-swapping latent embedding from the cross-attention fusion module. Extensive quantitative and qualitative experiments on in-the-wild faces demonstrate that our FlowFace++ outperforms the state-of-the-art significantly, particularly while the source face is obstructed by uneven lighting or angle offset.

cs.CV↗

arXiv2023

DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video

For few-shot learning, it is still a critical challenge to realize photo-realistic face visually dubbing on high-resolution videos. Previous works fail to generate high-fidelity dubbing results. To address the above problem, this paper proposes a Deformation Inpainting Network (DINet) for high-resolution face visually dubbing. Different from previous works relying on multiple up-sample layers to directly generate pixels from latent embeddings, DINet performs spatial deformation on feature maps of reference images to better preserve high-frequency textural details. Specifically, DINet consists of one deformation part and one inpainting part. In the first part, five reference facial images adaptively perform spatial deformation to create deformed feature maps encoding mouth shapes at each frame, in order to align with the input driving audio and also the head poses of the input source images. In the second part, to produce face visually dubbing, a feature decoder is responsible for adaptively incorporating mouth movements from the deformed feature maps and other attributes (i.e., head pose and upper facial expression) from the source feature maps together. Finally, DINet achieves face visually dubbing with rich textural details. We conduct qualitative and quantitative comparisons to validate our DINet on high-resolution videos. The experimental results show that our method outperforms state-of-the-art works.

cs.CV↗

arXiv2022

FlowFace: Semantic Flow-guided Shape-aware Face Swapping

In this work, we propose a semantic flow-guided two-stage framework for shape-aware face swapping, namely FlowFace. Unlike most previous methods that focus on transferring the source inner facial features but neglect facial contours, our FlowFace can transfer both of them to a target face, thus leading to more realistic face swapping. Concretely, our FlowFace consists of a face reshaping network and a face swapping network. The face reshaping network addresses the shape outline differences between the source and target faces. It first estimates a semantic flow (i.e., face shape differences) between the source and the target face, and then explicitly warps the target face shape with the estimated semantic flow. After reshaping, the face swapping network generates inner facial features that exhibit the identity of the source face. We employ a pre-trained face masked autoencoder (MAE) to extract facial features from both the source face and the target face. In contrast to previous methods that use identity embedding to preserve identity information, the features extracted by our encoder can better capture facial appearances and identity information. Then, we develop a cross-attention fusion module to adaptively fuse inner facial features from the source face with the target facial attributes, thus leading to better identity preservation. Extensive quantitative and qualitative experiments on in-the-wild faces demonstrate that our FlowFace outperforms the state-of-the-art significantly.

cs.CV↗

arXiv2022

Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching

In federated learning (FL), clients may have diverse objectives, and merging all clients' knowledge into one global model will cause negative transfer to local performance. Thus, clustered FL is proposed to group similar clients into clusters and maintain several global models. In the literature, centralized clustered FL algorithms require the assumption of the number of clusters and hence are not effective enough to explore the latent relationships among clients. In this paper, without assuming the number of clusters, we propose a peer-to-peer (P2P) FL algorithm named PANM. In PANM, clients communicate with peers to adaptively form an effective clustered topology. Specifically, we present two novel metrics for measuring client similarity and a two-stage neighbor matching algorithm based Monte Carlo method and Expectation Maximization under the Gaussian Mixture Model assumption. We have conducted theoretical analyses of PANM on the probability of neighbor estimation and the error gap to the clustered optimum. We have also implemented extensive experiments under both synthetic and real-world clustered heterogeneity. Theoretical analysis and empirical experiments show that the proposed algorithm is superior to the P2P FL counterparts, and it achieves better performance than the centralized cluster FL method. PANM is effective even under extremely low communication budgets.

cs.AI↗

arXiv2022

Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives

Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA).The major stumbling block to achieve this purpose is the semantic gap between language and video since they are at different levels of abstraction. Existing efforts mainly focus on designing sophisticated architectures while utilizing frame- or object-level visual representations. In this paper, we reconsider the multi-modal alignment problem in VideoQA from feature and sample perspectives to achieve better performance. From the view of feature,we break down the video into trajectories and first leverage trajectory feature in VideoQA to enhance the alignment between two modalities. Moreover, we adopt a heterogeneous graph architecture and design a hierarchical framework to align both trajectory-level and frame-level visual feature with language feature. In addition, we found that VideoQA models are largely dependent on language priors and always neglect visual-language interactions. Thus, two effective yet portable training augmentation strategies are designed to strengthen the cross-modal correspondence ability of our model from the view of sample. Extensive results show that our method outperforms all the state-of-the-art models on the challenging NExT-QA benchmark, which demonstrates the effectiveness of the proposed method.

cs.CV↗

arXiv2022

Rethinking the Reference-based Distinctive Image Captioning

Distinctive Image Captioning (DIC) -- generating distinctive captions that describe the unique details of a target image -- has received considerable attention over the last few years. A recent DIC work proposes to generate distinctive captions by comparing the target image with a set of semantic-similar reference images, i.e., reference-based DIC (Ref-DIC). It aims to make the generated captions can tell apart the target and reference images. Unfortunately, reference images used by existing Ref-DIC works are easy to distinguish: these reference images only resemble the target image at scene-level and have few common objects, such that a Ref-DIC model can trivially generate distinctive captions even without considering the reference images. To ensure Ref-DIC models really perceive the unique objects (or attributes) in target images, we first propose two new Ref-DIC benchmarks. Specifically, we design a two-stage matching mechanism, which strictly controls the similarity between the target and reference images at object-/attribute- level (vs. scene-level). Secondly, to generate distinctive captions, we develop a strong Transformer-based Ref-DIC baseline, dubbed as TransDIC. It not only extracts visual features from the target image, but also encodes the differences between objects in the target and reference images. Finally, for more trustworthy benchmarking, we propose a new evaluation metric named DisCIDEr for Ref-DIC, which evaluates both the accuracy and distinctiveness of the generated captions. Experimental results demonstrate that our TransDIC can generate distinctive captions. Besides, it outperforms several state-of-the-art models on the two new benchmarks over different metrics.

cs.CV↗

arXiv2022

The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Unbiased SGG has achieved significant progress over recent years. However, almost all existing SGG models have overlooked the ground-truth annotation qualities of prevailing SGG datasets, i.e., they always assume: 1) all the manually annotated positive samples are equally correct; 2) all the un-annotated negative samples are absolutely background. In this paper, we argue that both assumptions are inapplicable to SGG: there are numerous "noisy" groundtruth predicate labels that break these two assumptions, and these noisy samples actually harm the training of unbiased SGG models. To this end, we propose a novel model-agnostic NoIsy label CorrEction strategy for SGG: NICE. NICE can not only detect noisy samples but also reassign more high-quality predicate labels to them. After the NICE training, we can obtain a cleaner version of SGG dataset for model training. Specifically, NICE consists of three components: negative Noisy Sample Detection (Neg-NSD), positive NSD (Pos-NSD), and Noisy Sample Correction (NSC). Firstly, in Neg-NSD, we formulate this task as an out-of-distribution detection problem, and assign pseudo labels to all detected noisy negative samples. Then, in Pos-NSD, we use a clustering-based algorithm to divide all positive samples into multiple sets, and treat the samples in the noisiest set as noisy positive samples. Lastly, in NSC, we use a simple but effective weighted KNN to reassign new predicate labels to noisy positive samples. Extensive results on different backbones and tasks have attested to the effectiveness and generalization abilities of each component of NICE.

cs.CV↗

arXiv2022

Transformer-based Multimodal Information Fusion for Facial Expression Analysis

Human affective behavior analysis has received much attention in human-computer interaction (HCI). In this paper, we introduce our submission to the CVPR 2022 Competition on Affective Behavior Analysis in-the-wild (ABAW). To fully exploit affective knowledge from multiple views, we utilize the multimodal features of spoken words, speech prosody, and facial expression, which are extracted from the video clips in the Aff-Wild2 dataset. Based on these features, we propose a unified transformer-based multimodal framework for Action Unit detection and also expression recognition. Specifically, the static vision feature is first encoded from the current frame image. At the same time, we clip its adjacent frames by a sliding window and extract three kinds of multimodal features from the sequence of images, audio, and text. Then, we introduce a transformer-based fusion module that integrates the static vision features and the dynamic multimodal features. The cross-attention module in the fusion module makes the output integrated features focus on the crucial parts that facilitate the downstream detection tasks. We also leverage some data balancing techniques, data augmentation techniques, and postprocessing methods to further improve the model performance. In the official test of ABAW3 Competition, our model ranks first in the EXPR and AU tracks. The extensive quantitative evaluations, as well as ablation studies on the Aff-Wild2 dataset, prove the effectiveness of our proposed method.

cs.CV↗