arXiv subjects

Junbo Wang

Publications and source records attributed to Junbo Wang.

At least 19 recordsLinked to original sources

arXiv2026

Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning

Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, leading to a cross-modal gap between the training (text-only) and the inference (video-only). Previous works attempt to bridge the gap through simple linear transformations. However, the inherent gap between text and video makes cross-modal representation space alignment insufficient, resulting in inaccurate sentences. To address this issue, we propose a novel zero-shot video captioning framework (WSV) consisting of two training stages, which first generates corresponding synthetic video latent representations via a pretrained text-to-video generation model. To strengthen the fidelity of the latent representations, we propose a polisher capable of bridging the gap between real and synthetic video distributions. Subsequently, we design a prompter that conditions GPT-2 on the polished latent representations to generate the captions in the second training stage. During inference, an input video is encoded by a pretrained 3D Causal VAE and then fed directly into the prompter, which in turn guides GPT-2 to produce the final caption. Experimental results conducted on MSVD, MSR-VTT, and VATEX datasets demonstrate that our proposed method achieves scores of 52 and 95.7 on the B@4 and CIDEr metrics, respectively.

cs.CV↗

arXiv2026

Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents

Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically refine individual trajectories or abstract shared knowledge from related trajectories, but their experience representations are often disconnected from the underlying reasoning process. This limits feedback attribution, cross-task transfer, and update and retrieval efficiency, particularly in complex reasoning tasks with outcome-level feedback. To overcome this limitation, we propose \textbf{T}ree-\textbf{o}f-\textbf{E}xperience (ToE), a structured experience-management framework that aligns experience organization with the hierarchical reasoning process of LLM agents. Specifically, ToE organizes the experience into a shared tree of analytical perspectives and reasoning paths, whose reliability is calibrated through environmental outcomes to support systematic updating, transfer, and efficient retrieval. The experimental results on \textsc{Game of 24} and \textsc{FinEvolveBench} show that ToE substantially improves both problem-solving performance and efficiency. On \textsc{Game of 24}, ToE achieves a 31.4\% relative improvement in accuracy over the experience-free ToT baseline. On \textsc{FinEvolveBench}, ToE improves tsIC by an average of 41.24\% over the experience-free pipeline across 12 evaluation settings, whereas conventional experience-management methods often underperform experience-free baselines.

cs.CL↗

arXiv2026

TDVR: Joint Text Disambiguation and Viewpoint Reasoning for Zero-Shot 3D Visual Grounding

Zero-shot 3D visual grounding aims to localize specific objects based on textual descriptions and 3D visual input. However, the effectiveness of existing methods is significantly hindered by the ambiguous query text and deficient viewpoints. To address these issues, we propose TDVR, a training-free reasoning framework that disambiguates the input text and infers accurate viewpoints for zero-shot 3D visual grounding. First, we construct semantic 3D scene graph from the detected instances in the 3D point cloud. Subsequently, we put the original query, appearance and spatial relationship descriptions into the LLM for fusion, thereby disambiguating the initial input. We leverage chain-of-thought reasoning to generate the structured representation of disambiguated query. Then taking the scene graph and structured query as input, we get the optimal view via viewpoint reasoning to solve the problem of missing viewpoints during grounding. Based on the obtained optimal viewpoint, we further discriminate the distracting objects, enabling the model with the ability to distinguish similar instances. After that, we match the category text and appearance images with the query by computing the similarity of feature vectors. Finally, the target object was identified by integrating the viewpoint score, confusion score, category score, and appearance score. Compared with previous methods, our TDVR has stronger capabilities in viewpoint reasoning, similar object discrimination, and ambiguous query understanding. Experimental results on the public ScanRefer dataset show that our method outperforms the existing state-of-the-art methods by 15.25% and 14.46% in Acc@0.25 and Acc@0.5 respectively, demonstrating the effectiveness of our TDVR in addressing ambiguous query text and deficient viewpoints.

cs.CV↗

arXiv2026

Adaptive Emotional Video Captioning via Affective Heterogeneous Graph Reasoning and Multi-task Joint Learning

Emotional video captioning (EVC) aims to describe a video with both factual correctness and affective expressiveness. It requires a model to perceive subtle, ambiguous, and temporally varying emotional cues and translate them into natural language without weakening objective visual content. Existing methods have progressively introduced contextual attention, emotion interpretation, emotion priors, dynamic emotion perception and emotion-cause reasoning. Nevertheless, most of them still depend on either global emotion vectors or rigid hierarchical priors. In recent methods, the tree-structured emotion prior establishes a coarse-to-fine connection between psychological emotion categories and daily emotion words, but its hard subordinate masking may irreversibly suppress correct lexical emotions once the coarse category prediction is inaccurate. It is also limited in representing mixed or overlapping emotions that frequently occur in real videos. To address the issues, we propose SAGML, an adaptive EVC framework via affective heterogeneous graph and multi-task language modeling. Instead of treating the emotion prior as a discrete tree, SAGML constructs a soft affective heterogeneous graph containing catalog-level emotion nodes and lexical-level emotion word nodes. The soft gate is injected into video-to-emotion graph attention as a continuous bias, allowing visually supported lexical emotions to remain recoverable rather than being removed by a hard mask. The resulting affective representation is fed together with visual tokens into a causal language decoder, while dual catalog and lexical heads impose explicit emotion distribution learning on the prompt hidden states. The overall model is trained with a joint objective that combines autoregressive caption generation and emotion distribution supervision. SAGML provides an error-resilient and multi-emotion-aware baseline for EVC.

cs.CV↗

arXiv2026

Characterization of the RF Board for microwave SQUID multiplexing readout electronics

Microwave SQUID multiplexing ($\mu$MUX) is a widely used readout technique for large-scale transition-edge sensor (TES) arrays. It uses radio-frequency (RF) probe tones to interrogate cryogenic resonators, requiring frequency conversion between the baseband electronics and the cryogenic RF signal chain. This work describes the RF Board, a room-temperature frequency-conversion board deployed in the AliCPT $\mu$MUX readout system. The board up-converts 0-4 GHz baseband I/Q signals to the 4-8 GHz RF band for injection into the cryogenic chain and down-converts returned RF signals to baseband I/Q for ADC digitization. For the current 1000-tone operation, with a DAC output tone power of -30 dBm/tone, the required power windows are -35 to -25 dBm/tone for the RF tones transmitted to the cryostat and -45 to -35 dBm/tone at the ADC input for the returned tones. The RF Board is characterized using swept single-tone measurements covering up-conversion, down-conversion, and RF loopback. Based on these measurements, the RF output power is calculated to be -31.06 to -25.53 dBm, satisfying the RF output window. Assuming a representative cryogenic-chain transmission of -40 dB, the loopback result gives an estimated returned power of -45 to -35 dBm, within the target range. These results show that the RF Board meets the wideband frequency-conversion and tone-power requirements for the $\mu$MUX readout system.

astro-ph.IM↗

arXiv2026

FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards

Experience-based self-evolution enables language-model agents to improve their behavior by accumulating and updating experience at test time, yet existing evaluations often assume recurring task patterns and explicit success signals. We introduce \textsc{FinEvolveBench}, a benchmark for self-evolving agents on low-repetition tasks with implicit rewards. The benchmark reconstructs a daily financial information stream over 31 Chinese A-share industry indices and aligns 177,324 public news articles with market observations. Researchers can define prediction horizons over this stream; we evaluate predictive market-sentiment factors against delayed market-adjusted returns after 10, 20, and 40 trading days. Unlike static benchmarks that score each prediction independently, \textsc{FinEvolveBench} interleaves new decisions with delayed outcomes from earlier ones, testing whether agents can convert noisy real-world feedback into reusable experience at test time. Experiments with two backbone models show that the evaluated general-purpose memory systems do not consistently outperform the no-experience pipeline. A matched ablation further shows that feedback-driven utility updates help at shorter horizons on one backbone but hurt in most settings on the other. Together, these results position \textsc{FinEvolveBench} as a diagnostic testbed for experience-based self-evolution under noisy, delayed, and outcome-level feedback.

cs.CL↗

arXiv2026

Joint Design of Doppler-Resilient Unimodular Discrete-Phase Waveforms and Receiving Filters for MIMO Radars

Designing Doppler-resilient unimodular discrete phase-coded waveforms (DPWs) with low delay-Doppler sidelobes is critical for multiple-input multiple-output (MIMO) radar. Existing block coordinate descent (BCD) methods suffer from high computational cost for designing long sequences or large waveform sets. Meanwhile, learning-based alternatives such as the soft-quantization network (SQN) only address correlation optimization in the delay domain, without considering ambiguity function (AF) optimization in the joint delay-Doppler domain. To address these issues, this paper proposes a novel Doppler-resilient DPW design framework, termed SQNGD, for joint transmit-receive optimization that simultaneously optimizes the auto-AF, cross-AF (CAF), and signal-to-noise ratio loss (SNRL) under unimodular constraints. To solve the multi-objective optimization problem (MOOP), a joint transmit-receive design and an alternating optimization strategy are developed. The transmit waveforms are optimized via soft-quantization-based differentiable parameterization, while the receive filters are updated by gradient descent (GD) with an energy constraint and SNRL penalty. An FFT-accelerated evaluation of the AF and CAF is further incorporated, reducing the optimization time by 1.9x - 11x compared with the state-of-the-art (SOTA) majorization-minimization-coordinate descent (MMCD) method. Numerical results show that SQNGD achieves a peak sidelobe level (PSL) of approximately -43 dB over the Doppler range [-0.5,0.5] and -31 dB over [-600,600], respectively, outperforming MMCD by 5.85 dB and 3.45 dB, while maintaining the same SNRL of 0.5 dB.

eess.SP↗

arXiv2026

DiffVC: A Non-autoregressive Framework Based on Diffusion Model for Video Captioning

Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore, the few non-autoregressive counterparts suffer from deficiencies in generation quality due to the lack of sufficient multimodal interaction modeling. Therefore, we propose a non-autoregressive framework based on Diffusion model for Video Captioning (DiffVC) to address these issues. Its parallel decoding can effectively solve the problems of generation speed and cumulative error. At the same time, our proposed discriminative conditional Diffusion Model can generate higher-quality textual descriptions. Specifically, we first encode the video into a visual representation. During training, Gaussian noise is added to the textual representation of the ground-truth caption. Then, a new textual representation is generated via the discriminative denoiser with the visual representation as a conditional constraint. Finally, we input the new textual representation into a non-autoregressive language model to generate captions. During inference, we directly sample noise from the Gaussian distribution for generation. Experiments on MSVD, MSR-VTT, and VATEX show that our method can outperform previous non-autoregressive methods and achieve comparable performance to autoregressive methods, e.g., it achieved a maximum improvement of 9.9 on the CIDEr and improvement of 2.6 on the B@4, while having faster generation speed. The source code will be available soon.

cs.CV↗

arXiv2026

EPIR: An Efficient Patch Tokenization, Integration and Representation Framework for Micro-expression Recognition

Micro-expression recognition can obtain the real emotion of the individual at the current moment. Although deep learning-based methods, especially Transformer-based methods, have achieved impressive results, these methods have high computational complexity due to the large number of tokens in the multi-head self-attention. In addition, the existing micro-expression datasets are small-scale, which makes it difficult for Transformer-based models to learn effective micro-expression representations. Therefore, we propose a novel Efficient Patch tokenization, Integration and Representation framework (EPIR), which can balance high recognition performance and low computational complexity. Specifically, we first propose a dual norm shifted tokenization (DNSPT) module to learn the spatial relationship between neighboring pixels in the face region, which is implemented by a refined spatial transformation and dual norm projection. Then, we propose a token integration module to integrate partial tokens among multiple cascaded Transformer blocks, thereby reducing the number of tokens without information loss. Furthermore, we design a discriminative token extractor, which first improves the attention in the Transformer block to reduce the unnecessary focus of the attention calculation on self-tokens, and uses the dynamic token selection module (DTSM) to select key tokens, thereby capturing more discriminative micro-expression representations. We conduct extensive experiments on four popular public datasets (i.e., CASME II, SAMM, SMIC, and CAS(ME)3. The experimental results show that our method achieves significant performance gains over the state-of-the-art methods, such as 9.6% improvement on the CAS(ME)$^3$ dataset in terms of UF1 and 4.58% improvement on the SMIC dataset in terms of UAR metric.

cs.CV↗

arXiv2026

KG-CMI: Knowledge graph enhanced cross-Mamba interaction for medical visual question answering

Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent methods fail to fully leverage domain-specific medical knowledge, making it difficult to accurately associate lesion features in medical images with key diagnostic criteria. Additionally, classification-based approaches typically rely on predefined answer sets. Treating Med-VQA as a simple classification problem limits its ability to adapt to the diversity of free-form answers and may overlook detailed semantic information in those answers. To address these challenges, we propose a knowledge graph enhanced cross-Mamba interaction (KG-CMI) framework, which consists of a fine-grained cross-modal feature alignment (FCFA) module, a knowledge graph embedding (KGE) module, a cross-modal interaction representation (CMIR) module, and a free-form answer enhanced multi-task learning (FAMT) module. The KG-CMI learns cross-modal feature representations for images and texts by effectively integrating professional medical knowledge through a graph, establishing associations between lesion features and disease knowledge. Moreover, FAMT leverages auxiliary knowledge from open-ended questions, improving the model's capability for open-ended Med-VQA. Experimental results demonstrate that KG-CMI outperforms existing state-of-the-art methods on three Med-VQA datasets, i.e., VQA-RAD, SLAKE, and OVQA. Additionally, we conduct interpretability experiments to further validate the framework's effectiveness.

cs.CV↗

arXiv2026

SDD-YOLO: A Small-Target Detection Framework for Ground-to-Air Anti-UAV Surveillance with Edge-Efficient Deployment

Detecting small unmanned aerial vehicles (UAVs) from a ground-to-air (G2A) perspective presents significant challenges, including extremely low pixel occupancy, cluttered aerial backgrounds, and strict real-time constraints. Existing YOLO-based detectors are primarily optimized for general object detection and often lack adequate feature resolution for sub-pixel targets, while introducing complexities during deployment. In this paper, we propose SDD-YOLO, a small-target detection framework tailored for G2A anti-UAV surveillance. To capture fine-grained spatial details critical for micro-targets, SDD-YOLO introduces a P2 high-resolution detection head operating at 4 times downsampling. Furthermore, we integrate the recent architectural advancements from YOLO26, including a DFL-free, NMS-free architecture for streamlined inference, and the MuSGD hybrid training strategy with ProgLoss and STAL, which substantially mitigates gradient oscillation on sparse small-target signals. To support our evaluation, we construct DroneSOD-30K, a large-scale G2A dataset comprising approximately 30,000 annotated images covering diverse meteorological conditions. Experiments demonstrate that SDD-YOLO-n achieves a mAP@0.5 of 86.0% on DroneSOD-30K, surpassing the YOLOv5n baseline by 7.8 percentage points. Extensive inference analysis shows our model attains 226 FPS on an NVIDIA RTX 5090 and 35 FPS on an Intel Xeon CPU, demonstrating exceptional efficiency for future edge deployment.

cs.CV↗

arXiv2026

SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation

Modern large language models (LLMs) excel at generating fluent and faithful translations. However, they struggle to preserve an author's unique literary style, often producing semantically correct but generic outputs. This limitation stems from the inability of current single-model and static multi-agent systems to perceive and adapt to stylistic variations. To address this, we introduce the Style-Adaptive Multi-Agent System (SAMAS), a novel framework that treats style preservation as a signal processing task. Specifically, our method quantifies literary style into a Stylistic Feature Spectrum (SFS) using the wavelet packet transform. This SFS serves as a control signal to dynamically assemble a tailored workflow of specialized translation agents based on the source text's structural patterns. Extensive experiments on translation benchmarks show that SAMAS achieves competitive semantic accuracy against strong baselines, primarily by leveraging its statistically significant advantage in style fidelity.

cs.CL↗

arXiv2026

ExoGS: A 4D Real-to-Sim-to-Real Framework for Scalable Manipulation Data Collection

Real-to-Sim-to-Real technique is gaining increasing interest for robotic manipulation, as it can generate scalable data in simulation while having narrower sim-to-real gap. However, previous methods mainly focused on environment-level visual real-to-sim transfer, ignoring the transfer of interactions, which could be challenging and inefficient to obtain purely in simulation especially for contact-rich tasks. We propose ExoGS, a robot-free 4D Real-to-Sim-to-Real framework that captures both static environments and dynamic interactions in the real world and transfers them seamlessly to a simulated environment. It provides a new solution for scalable manipulation data collection and policy learning. ExoGS employs a self-designed robot-isomorphic passive exoskeleton AirExo-3 to capture kinematically consistent trajectories with millimeter-level accuracy and synchronized RGB observations during direct human demonstrations. The robot, objects, and environment are reconstructed as editable 3D Gaussian Splatting assets, enabling geometry-consistent replay and large-scale data augmentation. Additionally, a lightweight Mask Adapter injects instance-level semantics into the policy to enhance robustness under visual domain shifts. Real-world experiments demonstrate that ExoGS significantly improves data efficiency and policy generalization compared to teleoperation-based baselines. Code and hardware files have been released on https://github.com/zaixiabalala/ExoGS.

cs.RO↗

arXiv2025

ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment

Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and realistic motion. However, there exists a misalignment between text and motion distributions in diffusion models, which leads to semantically inconsistent or low-quality motions. To address this limitation, we propose Reward-guided sampling Alignment (ReAlign), comprising a step-aware reward model to assess alignment quality during the denoising sampling and a reward-guided strategy that directs the diffusion process toward an optimally aligned distribution. This reward model integrates step-aware tokens and combines a text-aligned module for semantic consistency and a motion-aligned module for realism, refining noisy motions at each timestep to balance probability density and alignment. Extensive experiments of both motion generation and retrieval tasks demonstrate that our approach significantly improves text-motion alignment and motion quality compared to existing state-of-the-art methods.

cs.CV↗

arXiv2025

CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering

Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent self-attention based methods struggle to effectively handle cross-modal semantic alignments between vision and language. Moreover, classification-based methods rely on predefined answer sets. Treating this task as a simple classification problem may make it unable to adapt to the diversity of free-form answers and overlook the detailed semantic information of free-form answers. In order to tackle these challenges, we introduce a Cross-Mamba Interaction based Multi-Task Learning (CMI-MTL) framework that learns cross-modal feature representations from images and texts. CMI-MTL comprises three key modules: fine-grained visual-text feature alignment (FVTA), cross-modal interleaved feature representation (CIFR), and free-form answer-enhanced multi-task learning (FFAE). FVTA extracts the most relevant regions in image-text pairs through fine-grained visual-text feature alignment. CIFR captures cross-modal sequential interactions via cross-modal interleaved feature representation. FFAE leverages auxiliary knowledge from open-ended questions through free-form answer-enhanced multi-task learning, improving the model's capability for open-ended Med-VQA. Experimental results show that CMI-MTL outperforms the existing state-of-the-art methods on three Med-VQA datasets: VQA-RAD, SLAKE, and OVQA. Furthermore, we conduct more interpretability experiments to prove the effectiveness. The code is publicly available at https://github.com/BioMedIA-repo/CMI-MTL.

cs.CV↗

arXiv2025

MMED: A Multimodal Micro-Expression Dataset based on Audio-Visual Fusion

Micro-expressions (MEs) are crucial leakages of concealed emotion, yet their study has been constrained by a reliance on silent, visual-only data. To solve this issue, we introduce two principal contributions. First, MMED, to our knowledge, is the first dataset capturing the spontaneous vocal cues that co-occur with MEs in ecologically valid, high-stakes interactions. Second, the Asymmetric Multimodal Fusion Network (AMF-Net) is a novel method that effectively fuses a global visual summary with a dynamic audio sequence via an asymmetric cross-attention framework. Rigorous Leave-One-Subject-Out Cross-Validation (LOSO-CV) experiments validate our approach, providing conclusive evidence that audio offers critical, disambiguating information for ME analysis. Collectively, the MMED dataset and our AMF-Net method provide valuable resources and a validated analytical approach for micro-expression recognition.

cs.MM↗

arXiv2025

Foundation Model for Skeleton-Based Human Action Understanding

Human action understanding serves as a foundational pillar in the field of intelligent motion perception. Skeletons serve as a modality- and device-agnostic representation for human modeling, and skeleton-based action understanding has potential applications in humanoid robot control and interaction. \RED{However, existing works often lack the scalability and generalization required to handle diverse action understanding tasks. There is no skeleton foundation model that can be adapted to a wide range of action understanding tasks}. This paper presents a Unified Skeleton-based Dense Representation Learning (USDRL) framework, which serves as a foundational model for skeleton-based human action understanding. USDRL consists of a Transformer-based Dense Spatio-Temporal Encoder (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT). The DSTE module adopts two parallel streams to learn temporal dynamic and spatial structure features. The MG-FD module collaboratively performs feature decorrelation across temporal, spatial, and instance domains to reduce dimensional redundancy and enhance information extraction. The MPCT module employs both multi-view and multi-modal self-supervised consistency training. The former enhances the learning of high-level semantics and mitigates the impact of low-level discrepancies, while the latter effectively facilitates the learning of informative multimodal features. We perform extensive experiments on 25 benchmarks across across 9 skeleton-based action understanding tasks, covering coarse prediction, dense prediction, and transferred prediction. Our approach significantly outperforms the current state-of-the-art methods. We hope that this work would broaden the scope of research in skeleton-based action understanding and encourage more attention to dense prediction tasks.

cs.CV↗

arXiv2025

Iterative pseudo-labeling based adaptive copy-paste supervision for semi-supervised tumor segmentation

Semi-supervised learning (SSL) has attracted considerable attention in medical image processing. The latest SSL methods use a combination of consistency regularization and pseudo-labeling to achieve remarkable success. However, most existing SSL studies focus on segmenting large organs, neglecting the challenging scenarios where there are numerous tumors or tumors of small volume. Furthermore, the extensive capabilities of data augmentation strategies, particularly in the context of both labeled and unlabeled data, have yet to be thoroughly investigated. To tackle these challenges, we introduce a straightforward yet effective approach, termed iterative pseudo-labeling based adaptive copy-paste supervision (IPA-CP), for tumor segmentation in CT scans. IPA-CP incorporates a two-way uncertainty based adaptive augmentation mechanism, aiming to inject tumor uncertainties present in the mean teacher architecture into adaptive augmentation. Additionally, IPA-CP employs an iterative pseudo-label transition strategy to generate more robust and informative pseudo labels for the unlabeled samples. Extensive experiments on both in-house and public datasets show that our framework outperforms state-of-the-art SSL methods in medical image segmentation. Ablation study results demonstrate the effectiveness of our technical contributions.

cs.CV↗