arXiv subjects

Junbo Wang

Publications and source records attributed to Junbo Wang.

At least 19 recordsLinked to original sources

arXiv2026

Trimodal Context-Aware Micro-Expression Recognition in Real-World Conversations: A Dataset and a Hierarchical Fusion Network

Recognizing micro-expressions in real-world conversations is challenging, as these facial movements are brief and faint, and their interpretations are strongly dependent on the contextual circumstances of their occurrence. Most existing methods are de-contextualized, as they analyze isolated video clips while disregarding the semantic and acoustic cues in the surrounding dialogue that help explain the emergence of an expression. Decades of psychological studies have shown that social context exerts influences on facial behavior over two key dimensions: how an expression is interpreted and how strongly it is generated to begin with. However, existing micro-expression research rarely incorporates such contextual factors into its models. As an example, provocative utterances from an interlocutor may elicit suppressed negative affective reactions, which isolated silent clips are unable to account for. We propose TriCoME, a trimodal dataset consisting of visual, audio and text data sourced from real-world conversations. In this dataset, each micro-expression is paired with its concurrent utterance and preceding context. We further annotate the context based on conversational role to denote two categories: external stimuli from an interlocutor's utterance and internal background from the subject's own utterance. On this basis, we propose the Hierarchical Focusing Fusion Network (HFFNet), which aligns acoustic and semantic streams at fine granularity, compresses long dialogue sequences, modulates attention toward conversational roles via a context-type embedding, and routes each sample between visual-only and multimodal decisions based on visual confidence to prevent noisy context from degrading recognition performance.

cs.CV↗

arXiv2026

EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding

Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although retrieval-augmented approaches have been introduced to provide additional context, most of them operate at the frame or snippet level, which limits their ability to model how events evolve over time and relate to each other. In this paper, we propose Event Chain Retrieval-Augmented Generation (EC-RAG), a training-free framework that organizes video content into an explicit event chain before question answering. Instead of retrieving isolated frames or text segments, EC-RAG first partitions the video into semantically coherent segments, represents each segment using multi-modal signals, and then links them into a structured chain that preserves temporal order and captures inter-event relationships. Given a query, the system identifies relevant events within this chain and gathers supporting evidence from the associated modalities. Our approach offers several practical advantages: (i) event-level abstraction that better reflects how video content is naturally structured, enabling more reliable localization compared to frame-level retrieval; (ii) structured multi-modal fusion that aggregates speech, text, and visual cues at the event level, allowing complementary information to be more effectively utilized during reasoning; and (iii) plug-and-play compatibility with existing LVLM backbones, requiring no additional training or reliance on proprietary models. Experiments on Video-MME, MLVU, and LongVideoBench show that this event-centric design consistently outperforms frame-level retrieval baselines, highlighting the importance of modeling temporal structure for long-video understanding.

cs.CV↗

arXiv2026

Bidirectional Preference Synthesis: Learning Prompt-Conditioned Preferences from Boundary Failures

Correction-based offline preference pipelines commonly treat model failures only as rejected responses under the original prompt. This supervision is incomplete for boundary failures: responses that violate the given instruction yet coherently satisfy a nearby intent or constraint setting. We introduce Bidirectional Preference Synthesis (BPS), a data-construction method for standard Direct Preference Optimization (DPO) that makes this missing prompt dependence explicit. For each validated boundary failure, BPS keeps the conventional forward pair under the original prompt and adds a reverse pair under a synthesized achieved prompt, so the same response is rejected where it is wrong and chosen where it is right, without changing the DPO objective, training a reward model, or requiring online sampling. On Qwen3-4B-Instruct-2507, BPS preserves original-side pairwise ranking while raising achieved-side ranking accuracy from 6.8% to 62.3% on held-out crossed anchors, with a similar shift under a Kimi-K2.6 cross-teacher probe. A blind human audit supports the intended reverse preference direction, and downstream evaluations show the clearest separation from Forward-DPO in multilingual multi-turn instruction following, with consistent capability-retention patterns on agentic, tool-use, and code checks.

cs.AI↗

arXiv2026

Characterization of the RF Board for microwave SQUID multiplexing readout electronics

Microwave SQUID multiplexing ($μ$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 $μ$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 $μ$MUX readout system.

astro-ph.IM↗

arXiv2026

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

Large language model (LLM) agents increasingly rely on external experience to continually adapt to changing environments without modifying their underlying models. Recent experience mechanisms have demonstrated promising results across diverse tasks. However, their effectiveness is typically evaluated within individual benchmark settings, and how experience mechanisms generalize across different scenarios remains insufficiently explored. In this work, we present a scenario-oriented analysis of experience mechanisms for LLM agents. We characterize existing evaluation scenarios along four dimensions: outcome observability, credit assignment complexity, environmental dynamics, and experience reusability. Our analysis shows that existing benchmarks often evaluate experience mechanisms under scenarios where at least one dimension is comparatively favorable, leaving more challenging combinations of scenario properties underexplored. To address this gap, we introduce \textsc{FinEvolveBench}, a reproducible benchmark built on a chronological stream of rich financial news and market data that enables systematic evaluation of experience-based self-evolution under challenging experience regimes characterized by noisy feedback, ambiguous credit assignment, environmental non-stationarity, and limited experience reusability. Experiments show that existing approaches exhibit substantially reduced or inconsistent gains in this setting, highlighting the scenario-dependent nature of experience mechanisms and the challenge of maintaining valid experience under changing environments.

cs.CL↗

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

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

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

MulFSA: Multi-level Financial Sentiment Analysis Framework for Bond Market

Existing financial sentiment analysis methods often fail to capture the multi-faceted nature of risk in bond markets due to their single-level approach and neglect of temporal dynamics. We propose Multi-level Financial Sentiment Analysis (MulFSA) based on pre-trained language models (PLMs) and large language models (LLMs), a novel framework that systematically integrates firm-specific micro-level sentiment, industry-specific meso-level sentiment, and duration-aware smoothing to model the latency and persistence of textual impact. Applying MulFSA to the comprehensive Chinese bond market corpus constructed by us (2013-2023, 1.35M texts), we extracted a daily composite sentiment index. Empirical results show statistically measurable improvements in credit spread forecasting when incorporating sentiment (10.25% MAE and 11.94% MAPE reduction), with sentiment shifts closely correlating with major social risk events and firm-specific crises. Project Page: https://mulfsa.github.io/.

cs.CE↗

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

SounDiT: Geo-Contextual Soundscape-to-Landscape Generation

Recent audio-to-image models have shown impressive performance in generating images of specific objects conditioned on their corresponding sounds. However, these models fail to reconstruct real-world landscapes conditioned on environmental soundscapes. To address this gap, we present Geo-contextual Soundscape-to-Landscape (GeoS2L) generation, a novel and practically significant task that aims to synthesize geographically realistic landscape images from environmental soundscapes. To support this task, we construct two large-scale geo-contextual multi-modal datasets, SoundingSVI and SonicUrban, which pair diverse environmental soundscapes with real-world landscape images. We propose SounDiT, a diffusion transformer (DiT)-based model that incorporates environmental soundscapes and geo-contextual scene conditioning to synthesize geographically coherent landscape images. Furthermore, we propose the Place Similarity Score (PSS), a practically-informed geo-contextual evaluation framework to measure consistency between input soundscapes and generated landscape images. Extensive experiments demonstrate that SounDiT outperforms existing baselines in the GeoS2L, while the PSS effectively captures multi-level generation consistency across element, scene,and human perception. Project page: https://gisense.github.io/SounDiT-Page/

cs.SD↗

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↗