arXiv subjects

Jinrui Zhang

Publications and source records attributed to Jinrui Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Trading with the Devil: Risk and Return in Foundation Model Strategies

Foundation models - already transformative in domains such as natural language processing - are now starting to emerge for time-series tasks in finance. While these pretrained architectures promise versatile predictive signals, little is known about how they shape the risk profiles of the trading strategies built atop them, leaving practitioners reluctant to commit serious capital. In this paper, we propose an extension to the Capital Asset Pricing Model (CAPM) that disentangles the systematic risk introduced by a shared foundation model - potentially capable of generating alpha if the underlying model is genuinely predictive - from the idiosyncratic risk attributable to custom fine-tuning, which typically accrues no systematic premium. To enable a practical estimation of these separate risks, we align this decomposition with the concepts of uncertainty disentanglement, casting systematic risk as epistemic uncertainty (rooted in the pretrained model) and idiosyncratic risk as aleatory uncertainty (introduced during custom adaptations). Under the Aleatory Collapse Assumption, we illustrate how Monte Carlo dropout - among other methods in the uncertainty-quantization toolkit - can directly measure the epistemic risk, thereby mapping trading strategies to a more transparent risk-return plane. Our experiments show that isolating these distinct risk factors yields deeper insights into the performance limits of foundation-model-based strategies, their model degradation over time, and potential avenues for targeted refinements. Taken together, our results highlight both the promise and the pitfalls of deploying large pretrained models in competitive financial markets.

cs.CE↗

arXiv2025

DynaKV: Enabling Accurate and Efficient Long-Sequence LLM Decoding on Smartphones

As the demand for human-like reasoning, multi-turn dialogues, and long-form responses grows, large language models (LLMs) are increasingly expected to support efficient and effective long-sequence decoding. However, due to limited DRAM capacity, long-seuqence LLM decoding on smartphones is constrained by the key-value cache (KVCache), whose memory footprint increases linearly with sequence length. Retrieval-based methods mitigate DRAM pressure by offloading KVCache to flash and retrieving query-relevant entries through cluster-based indexing. Unfortunately, as decoding progresses, KVCache distribution shifts render static or local cluster updates progressively misaligned, excluding essential entries or fetching redundant ones. These issues are further exacerbated by smartphone-specific limitations in bandwidth, IOPS, and memory capacity. We propose DynaKV, the first adaptive KVCache management approach that jointly addresses accuracy and efficiency for long-sequence decoding on smartphones. DynaKV integrates three key techniques: (1) Migration-Free Cluster Adaptation, which adaptively splits clusters during retrieval without incurring additional transfers; (2) Continuity-Centric Flash Management, which co-locates correlated entries and clusters and employs a dual-head layout for efficient updates; and (3) Memory-Efficient Cache Design, which virtualizes cache space across DRAM and flash and extends replacement policies to align with cluster-level access patterns. Evaluations demonstrate that DynaKV improves retrieval accuracy and reduces end-to-end latency compared to state-of-the-art solutions, achieving average gains of $1.38\times$ in accuracy and $1.47\times$ speedups. Furthermore, the insights of DynaKV naturally extend to other long-context workloads and multi-tier memory hierarchies, underscoring its broader applicability.

cs.DC↗

arXiv2025

LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning

Our winning entry for the CVPR 2023 Generic Event Boundary Captioning (GEBC) competition is detailed in this paper. Unlike conventional video captioning tasks, GEBC demands that the captioning model possess an understanding of immediate changes in status around the designated video boundary, making it a difficult task. This paper proposes an effective model LLMVA-GEBC (Large Language Model with Video Adapter for Generic Event Boundary Captioning): (1) We utilize a pretrained LLM for generating human-like captions with high quality. (2) To adapt the model to the GEBC task, we take the video Q-former as an adapter and train it with the frozen visual feature extractors and LLM. Our proposed method achieved a 76.14 score on the test set and won the first place in the challenge. Our code is available at https://github.com/zjr2000/LLMVA-GEBC .

cs.CV↗

arXiv2025

Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors

Recent advancements in large video-language models have revolutionized video understanding tasks. However, their efficiency is significantly constrained by processing high volumes of visual tokens. Existing token compression strategies apply a fixed compression ratio, ignoring the variability in semantic density among different video clips. Consequently, this lead to inadequate representation of information-rich clips due to insufficient tokens and unnecessary computation on static or content-poor ones. To address this, we propose LangDC, a Language-aware Dynamic Token Compressor. LangDC leverages a lightweight language model to describe video clips, converting them into soft caption tokens as visual representations. Trained with our proposed semantic density-aware supervision, LangDC aims to 1) cover key visual cues necessary for downstream task reasoning and 2) dynamically adjust compression ratios based on scene richness, reflected by descriptions length. Our design mimics how humans dynamically express what they see: complex scenes (seeing more) elicit more detailed language to convey nuances (saying more), whereas simpler scenes are described with fewer words. Experimental results show that our method reduces FLOPs by 49% compared to VideoGPT+ while maintaining competitive performance. Furthermore, qualitative results demonstrate our approach adaptively adjusts the token compression ratio based on video segment richness.

cs.CV↗

arXiv2025

LLM-Driven Self-Refinement for Embodied Drone Task Planning

We introduce SRDrone, a novel system designed for self-refinement task planning in industrial-grade embodied drones. SRDrone incorporates two key technical contributions: First, it employs a continuous state evaluation methodology to robustly and accurately determine task outcomes and provide explanatory feedback. This approach supersedes conventional reliance on single-frame final-state assessment for continuous, dynamic drone operations. Second, SRDrone implements a hierarchical Behavior Tree (BT) modification model. This model integrates multi-level BT plan analysis with a constrained strategy space to enable structured reflective learning from experience. Experimental results demonstrate that SRDrone achieves a 44.87% improvement in Success Rate (SR) over baseline methods. Furthermore, real-world deployment utilizing an experience base optimized through iterative self-refinement attains a 96.25% SR. By embedding adaptive task refinement capabilities within an industrial-grade BT planning framework, SRDrone effectively integrates the general reasoning intelligence of Large Language Models (LLMs) with the stringent physical execution constraints inherent to embodied drones. Code is available at https://github.com/ZXiiiC/SRDrone.

cs.RO↗

arXiv2025

Prompt-aware of Frame Sampling for Efficient Text-Video Retrieval

Enabling efficient text-video retrieval on edge-end devices is critical for real-world applications. Yet, existing methods face a critical challenge in balancing accuracy and computational efficiency: uniform frame sampling methods ensure content coverage but incur prohibitive computational costs, while salient-frame sampling methods reduce overhead but suffer from query-agnostic frame selection that biases retrieval results. To address this, we propose ProCLIP, a user-centric framework that achieves state-of-the-art accuracy with significantly improved efficiency. We design a prompt-aware frame sampling strategy that dynamically guides lightweight feature extractors using textual prompts to select semantically relevant frames, overcoming the limitations of existing salient-frame sampling methods which rely on static, query-agnostic selection criteria. Moreover, we adopt a two-stage candidate pruning strategy that combines rapid coarse filtering via a lightweight module with CLIP-powered fine-grained re-ranking, enhancing retrieval efficiency while preserving accuracy. Experiments across benchmarks show ProCLIP achieves 75.3% latency reduction versus baselines while maintaining competitive accuracy, i.e., R@1=49.0 in MSR-VTT dataset. Code is available at https://github.com/tiffylong/ProCLIP.

cs.MM↗

arXiv2025

Learning Speaker-Invariant Visual Features for Lipreading

Lipreading is a challenging cross-modal task that aims to convert visual lip movements into spoken text. Existing lipreading methods often extract visual features that include speaker-specific lip attributes (e.g., shape, color, texture), which introduce spurious correlations between vision and text. These correlations lead to suboptimal lipreading accuracy and restrict model generalization. To address this challenge, we introduce SIFLip, a speaker-invariant visual feature learning framework that disentangles speaker-specific attributes using two complementary disentanglement modules (Implicit Disentanglement and Explicit Disentanglement) to improve generalization. Specifically, since different speakers exhibit semantic consistency between lip movements and phonetic text when pronouncing the same words, our implicit disentanglement module leverages stable text embeddings as supervisory signals to learn common visual representations across speakers, implicitly decoupling speaker-specific features. Additionally, we design a speaker recognition sub-task within the main lipreading pipeline to filter speaker-specific features, then further explicitly disentangle these personalized visual features from the backbone network via gradient reversal. Experimental results demonstrate that SIFLip significantly enhances generalization performance across multiple public datasets. Experimental results demonstrate that SIFLip significantly improves generalization performance across multiple public datasets, outperforming state-of-the-art methods.

cs.CV↗

arXiv2025

Selective focusing of multiple particles in a layered medium

Inverse scattering in layered media has a wide range of applications, examples including geophysical exploration, medical imaging, and remote sensing. In this paper, we develop a selective focusing method for identifying multiple unknown buried scatterers in a layered medium. The method is derived through the asymptotic analysis of the time reversal operator using the layered Green's function and limited aperture measurements. We begin by showing the global focusing property of the time reversal operator. Then we demonstrate that each small sound-soft particle gives rise to one significant eigenvalue of the time reversal operator, while each sound-hard particle gives three. The associated eigenfunction generates an incident wave focusing selectively on the corresponding unknown particle. Finally, we employ the time reversal method as an initial indicator and propose an effective Bayesian inversion scheme to reconstruct multiple buried extended scatterers for enhanced resolution. Numerical experiments are provided to demonstrate the efficiency.

math.NA↗

arXiv2025

$γ$-FedHT: Stepsize-Aware Hard-Threshold Gradient Compression in Federated Learning

Gradient compression can effectively alleviate communication bottlenecks in Federated Learning (FL). Contemporary state-of-the-art sparse compressors, such as Top-$k$, exhibit high computational complexity, up to $\mathcal{O}(d\log_2{k})$, where $d$ is the number of model parameters. The hard-threshold compressor, which simply transmits elements with absolute values higher than a fixed threshold, is thus proposed to reduce the complexity to $\mathcal{O}(d)$. However, the hard-threshold compression causes accuracy degradation in FL, where the datasets are non-IID and the stepsize $γ$ is decreasing for model convergence. The decaying stepsize reduces the updates and causes the compression ratio of the hard-threshold compression to drop rapidly to an aggressive ratio. At or below this ratio, the model accuracy has been observed to degrade severely. To address this, we propose $γ$-FedHT, a stepsize-aware low-cost compressor with Error-Feedback to guarantee convergence. Given that the traditional theoretical framework of FL does not consider Error-Feedback, we introduce the fundamental conversation of Error-Feedback. We prove that $γ$-FedHT has the convergence rate of $\mathcal{O}(\frac{1}{T})$ ($T$ representing total training iterations) under $μ$-strongly convex cases and $\mathcal{O}(\frac{1}{\sqrt{T}})$ under non-convex cases, \textit{same as FedAVG}. Extensive experiments demonstrate that $γ$-FedHT improves accuracy by up to $7.42\%$ over Top-$k$ under equal communication traffic on various non-IID image datasets.

cs.LG↗

arXiv2025

LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos

Despite impressive advancements in video understanding, most efforts remain limited to coarse-grained or visual-only video tasks. However, real-world videos encompass omni-modal information (vision, audio, and speech) with a series of events forming a cohesive storyline. The lack of multi-modal video data with fine-grained event annotations and the high cost of manual labeling are major obstacles to comprehensive omni-modality video perception. To address this gap, we propose an automatic pipeline consisting of high-quality multi-modal video filtering, semantically coherent omni-modal event boundary detection, and cross-modal correlation-aware event captioning. In this way, we present LongVALE, the first-ever Vision-Audio-Language Event understanding benchmark comprising 105K omni-modal events with precise temporal boundaries and detailed relation-aware captions within 8.4K high-quality long videos. Further, we build a baseline that leverages LongVALE to enable video large language models (LLMs) for omni-modality fine-grained temporal video understanding for the first time. Extensive experiments demonstrate the effectiveness and great potential of LongVALE in advancing comprehensive multi-modal video understanding.

cs.CV↗

arXiv2024

MobiFuse: A High-Precision On-device Depth Perception System with Multi-Data Fusion

We present MobiFuse, a high-precision depth perception system on mobile devices that combines dual RGB and Time-of-Flight (ToF) cameras. To achieve this, we leverage physical principles from various environmental factors to propose the Depth Error Indication (DEI) modality, characterizing the depth error of ToF and stereo-matching. Furthermore, we employ a progressive fusion strategy, merging geometric features from ToF and stereo depth maps with depth error features from the DEI modality to create precise depth maps. Additionally, we create a new ToF-Stereo depth dataset, RealToF, to train and validate our model. Our experiments demonstrate that MobiFuse excels over baselines by significantly reducing depth measurement errors by up to 77.7%. It also showcases strong generalization across diverse datasets and proves effectiveness in two downstream tasks: 3D reconstruction and 3D segmentation. The demo video of MobiFuse in real-life scenarios is available at the de-identified YouTube link(https://youtu.be/jy-Sp7T1LVs).

cs.CV↗

arXiv2024

Differential Informed Auto-Encoder

In this article, an encoder was trained to obtain the inner structure of the original data by obtain a differential equations. A decoder was trained to resample the original data domain, to generate new data that obey the differential structure of the original data using the physics-informed neural network.

cs.LG↗

arXiv2024

MultiCounter: Multiple Action Agnostic Repetition Counting in Untrimmed Videos

Multi-instance Repetitive Action Counting (MRAC) aims to estimate the number of repetitive actions performed by multiple instances in untrimmed videos, commonly found in human-centric domains like sports and exercise. In this paper, we propose MultiCounter, a fully end-to-end deep learning framework that enables simultaneous detection, tracking, and counting of repetitive actions of multiple human instances. Specifically, MultiCounter incorporates two novel modules: 1) mixed spatiotemporal interaction for efficient context correlation across consecutive frames, and 2) task-specific heads for accurate perception of periodic boundaries and generalization for action-agnostic human instances. We train MultiCounter on a synthetic dataset called MultiRep generated from annotated real-world videos. Experiments on the MultiRep dataset validate the fundamental challenge of MRAC tasks and showcase the superiority of our proposed model. Compared to ByteTrack+RepNet, a solution that combines an advanced tracker with a single repetition counter, MultiCounter substantially improves Period-mAP by 41.0%, reduces AvgMAE by 58.6%, and increases AvgOBO 1.48 times. This sets a new benchmark in the field of MRAC. Moreover, MultiCounter runs in real-time on a commodity GPU server and is insensitive to the number of human instances in a video.

cs.CV↗

arXiv2024

Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models

Large vision-language models (LVLMs) have shown promising performance on a variety of vision-language tasks. However, they remain susceptible to hallucinations, generating outputs misaligned with visual content or instructions. While various mitigation strategies have been proposed, they often neglect a key contributor to hallucinations: lack of fine-grained reasoning supervision during training. Without intermediate reasoning steps, models may establish superficial shortcuts between instructions and responses, failing to internalize the inherent reasoning logic. To address this challenge, we propose reflective instruction tuning, which integrates rationale learning into visual instruction tuning. Unlike previous methods that learning from responses only, our approach entails the model predicting rationales justifying why responses are correct or incorrect. This fosters a deeper engagement with the fine-grained reasoning underlying each response, thus enhancing the model's reasoning proficiency. To facilitate this approach, we propose REVERIE, the first large-scale instruction-tuning dataset with ReflEctiVE RatIonalE annotations. REVERIE comprises 115k machine-generated reasoning instructions, each meticulously annotated with a corresponding pair of correct and confusing responses, alongside comprehensive rationales elucidating the justification behind the correctness or erroneousness of each response. Experimental results on multiple LVLM benchmarks reveal that reflective instruction tuning with the REVERIE dataset yields noticeable performance gain over the baseline model, demonstrating the effectiveness of reflecting from the rationales. Project page is at https://zjr2000.github.io/projects/reverie.

cs.CV↗

arXiv2023

Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views

We present Ego3DPose, a highly accurate binocular egocentric 3D pose reconstruction system. The binocular egocentric setup offers practicality and usefulness in various applications, however, it remains largely under-explored. It has been suffering from low pose estimation accuracy due to viewing distortion, severe self-occlusion, and limited field-of-view of the joints in egocentric 2D images. Here, we notice that two important 3D cues, stereo correspondences, and perspective, contained in the egocentric binocular input are neglected. Current methods heavily rely on 2D image features, implicitly learning 3D information, which introduces biases towards commonly observed motions and leads to low overall accuracy. We observe that they not only fail in challenging occlusion cases but also in estimating visible joint positions. To address these challenges, we propose two novel approaches. First, we design a two-path network architecture with a path that estimates pose per limb independently with its binocular heatmaps. Without full-body information provided, it alleviates bias toward trained full-body distribution. Second, we leverage the egocentric view of body limbs, which exhibits strong perspective variance (e.g., a significantly large-size hand when it is close to the camera). We propose a new perspective-aware representation using trigonometry, enabling the network to estimate the 3D orientation of limbs. Finally, we develop an end-to-end pose reconstruction network that synergizes both techniques. Our comprehensive evaluations demonstrate that Ego3DPose outperforms state-of-the-art models by a pose estimation error (i.e., MPJPE) reduction of 23.1% in the UnrealEgo dataset. Our qualitative results highlight the superiority of our approach across a range of scenarios and challenges.

cs.CV↗

arXiv2023

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning

Image-to-text generation aims to describe images using natural language. Recently, zero-shot image captioning based on pre-trained vision-language models (VLMs) and large language models (LLMs) has made significant progress. However, we have observed and empirically demonstrated that these methods are susceptible to modality bias induced by LLMs and tend to generate descriptions containing objects (entities) that do not actually exist in the image but frequently appear during training (i.e., object hallucination). In this paper, we propose ViECap, a transferable decoding model that leverages entity-aware decoding to generate descriptions in both seen and unseen scenarios. ViECap incorporates entity-aware hard prompts to guide LLMs' attention toward the visual entities present in the image, enabling coherent caption generation across diverse scenes. With entity-aware hard prompts, ViECap is capable of maintaining performance when transferring from in-domain to out-of-domain scenarios. Extensive experiments demonstrate that ViECap sets a new state-of-the-art cross-domain (transferable) captioning and performs competitively in-domain captioning compared to previous VLMs-based zero-shot methods. Our code is available at: https://github.com/FeiElysia/ViECap

cs.CV↗

arXiv2023

Caption Anything: Interactive Image Description with Diverse Multimodal Controls

Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\textit{e.g.}$, looking at the specified regions or telling in a particular text style. State-of-the-art methods are trained on annotated pairs of input controls and output captions. However, the scarcity of such well-annotated multimodal data largely limits their usability and scalability for interactive AI systems. Leveraging unimodal instruction-following foundation models is a promising alternative that benefits from broader sources of data. In this paper, we present Caption AnyThing (CAT), a foundation model augmented image captioning framework supporting a wide range of multimodel controls: 1) visual controls, including points, boxes, and trajectories; 2) language controls, such as sentiment, length, language, and factuality. Powered by Segment Anything Model (SAM) and ChatGPT, we unify the visual and language prompts into a modularized framework, enabling the flexible combination between different controls. Extensive case studies demonstrate the user intention alignment capabilities of our framework, shedding light on effective user interaction modeling in vision-language applications. Our code is publicly available at https://github.com/ttengwang/Caption-Anything.

cs.CV↗

arXiv2023

Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos

Joint video-language learning has received increasing attention in recent years. However, existing works mainly focus on single or multiple trimmed video clips (events), which makes human-annotated event boundaries necessary during inference. To break away from the ties, we propose a grounded vision-language learning framework for untrimmed videos, which automatically detects informative events and effectively excavates the alignments between multi-sentence descriptions and corresponding event segments. Instead of coarse-level video-language alignments, we present two dual pretext tasks to encourage fine-grained segment-level alignments, i.e., text-to-event grounding (TEG) and event-to-text generation (ETG). TEG learns to adaptively ground the possible event proposals given a set of sentences by estimating the cross-modal distance in a joint semantic space. Meanwhile, ETG aims to reconstruct (generate) the matched texts given event proposals, encouraging the event representation to retain meaningful semantic information. To encourage accurate label assignment between the event set and the text set, we propose a novel semantic-aware cost to mitigate the sub-optimal matching results caused by ambiguous boundary annotations. Our framework is easily extensible to tasks covering visually-grounded language understanding and generation. We achieve state-of-the-art dense video captioning performance on ActivityNet Captions, YouCook2 and YouMakeup, and competitive performance on several other language generation and understanding tasks. Our method also achieved 1st place in both the MTVG and MDVC tasks of the PIC 4th Challenge. Our code is publicly available at https://github.com/zjr2000/GVL.

cs.CV↗