arXiv subjects

Zhenyu Yan

Publications and source records attributed to Zhenyu Yan.

At least 19 recordsLinked to original sources

arXiv2026

The 1st PortraitCraft Challenge: A CVPR 2026 Workshop Competition on Portrait Composition Understanding and Generation

This paper presents an overview of the inaugural PortraitCraft Challenge, held as one of the official competitions at CVPR 2026. The challenge focuses on portrait composition understanding and generation, aiming to advance AI research in portrait aesthetics analysis and controllable image synthesis. Unlike existing datasets and tasks that primarily focus on global aesthetic scoring, PortraitCraft introduces a unified evaluation framework comprising two complementary tracks. Track 1 requires models to perform structured portrait composition understanding, and Track 2 requires models to generate portrait images from structured composition descriptions under explicit compositional constraints. To support the challenge, we constructed and publicly released a large-scale portrait composition dataset consisting of approximately 50,000 curated real portrait images, providing multi-level supervision. This report describes the challenge setup, evaluation protocols, dataset composition, and final results, along with an analysis of the technical characteristics of the submitted solutions. The PortraitCraft Challenge provides a standardized and reproducible platform for research on portrait composition understanding and generation, and is expected to foster further progress in the fields of portrait aesthetics and controllable image generation.

cs.CV↗

arXiv2026

Guiding LLM-based Loop Invariant Synthesis via Feedback on Local Reasoning Errors

We propose a novel framework that provides constructive feedback to an LLM in the "guess-and-check" paradigm by formally verifying its own thinking process and detecting local reasoning errors. We apply this framework to the loop invariant synthesis problem. We prompt the model to produce a step-by-step natural language proof justifying its thinking process for the failed verification condition of its generated loop invariants. Then, we use an LLM to translate the reasoning steps into first-order logic implications, which can be checked automatically. An invalid implication pinpoints the exact logical flaw in the LLM's thinking process, which we then use to construct targeted feedback for refinement. We have implemented our approach in a tool called LORIS and evaluated it on a main benchmark suite of 460 C programs and an additional benchmark suite of 50 C programs each of which involves non-linear properties. On the main benchmark suite, LORIS solved 445 of the programs, and achieved an overall success rate of $93.1\%$. LORIS also demonstrates robustness on the challenging non-linear benchmark suite.

cs.PL↗

arXiv2026

Pro$^2$Assist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks

Procedural tasks with multiple ordered steps are ubiquitous in daily life. Recent advances in multimodal large language models (MLLMs) have enabled personal assistants that support daily activities. However, existing systems primarily provide reactive guidance triggered by user queries, or limited proactive assistance for isolated short-term events rather than long-horizon procedural tasks. In this work, we introduce Pro$^2$Assist, a step-aware proactive assistant that continuously tracks fine-grained task progress and reasons over the user's evolving state to provide timely assistance throughout tasks. Pro$^2$Assist leverages multimodal data from augmented reality (AR) glasses to achieve motion-based perception. It then extracts step-oriented procedural context from multi-scale temporal dynamics and task-specific expert knowledge. Based on both sensory input and procedural context, Pro$^2$Assist performs continuous reasoning to infer user needs and display timely assistance on AR glasses. We evaluate Pro$^2$Assist using a dataset curated from public sources and a real-world dataset collected on our testbed with AR glasses. Extensive evaluations show that Pro$^2$Assist outperforms the best-performing baselines by over 21% in procedural action understanding accuracy, and it achieves up to 2.29x the proactive timing accuracy of baselines. A user study with 20 participants further shows that 90% find Pro$^2$Assist useful, indicating its effectiveness for real-world procedural assistance.

cs.AI↗

arXiv2026

WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior

Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training costs, lack natural language controllability, or compromise semantic coherence. To bridge this gap, we propose WASD (unWeaving Actionable Sufficient Directives), a novel framework that explains model behavior by identifying sufficient neural conditions for token generation. Our method represents candidate conditions as neuron-activation predicates and iteratively searches for a minimal set that guarantees the current output under input perturbations. Experiments on SST-2 and CounterFact with the Gemma-2-2B model demonstrate that our approach produces explanations that are more stable, accurate, and concise than conventional attribution graphs. Moreover, through a case study on controlling cross-lingual output generation, we validated the practical effectiveness of WASD in controlling model behavior.

cs.CL↗

arXiv2026

SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams

Personalization is essential for Large Language Model (LLM)-based agents to adapt to users' preferences and improve response quality and task performance. However, most existing approaches infer personas from chat histories, which capture only self-disclosed information rather than users' everyday behaviors in the physical world, limiting the ability to infer comprehensive user personas. In this work, we introduce SensorPersona, an LLM-empowered system that continuously infers stable user personas from multimodal longitudinal sensor streams unobtrusively collected from users' mobile devices. SensorPersona first performs person-oriented context encoding on continuous sensor streams to enrich the semantics of sensor contexts. It then employs hierarchical persona reasoning that integrates intra- and inter-episode reasoning to infer personas spanning physical patterns, psychosocial traits, and life experiences. Finally, it employs clustering-aware incremental verification and temporal evidence-aware updating to adapt to evolving personas. We evaluate SensorPersona on a self-collected dataset containing 1,580 hours of sensor data from 20 participants, collected over up to 3 months across 17 cities on 3 continents. Results show that SensorPersona achieves up to 31.4% higher recall in persona extraction, an 85.7% win rate in persona-aware agent responses, and notable improvements in user satisfaction compared to state-of-the-art baselines.

cs.CL↗

arXiv2026

Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection

As Large Language Models (LLMs) scale to handle massive context windows, achieving surgical feature-level interpretation is essential for high-stakes tasks like legal auditing and code debugging. However, existing local model-agnostic explanation methods face a critical dilemma in these scenarios: feature-based methods suffer from attribution dilution due to high feature dimensionality, thus failing to provide faithful explanations. In this paper, we propose Focus-LIME, a coarse-to-fine framework designed to restore the tractability of surgical interpretation. Focus-LIME utilizes a proxy model to curate the perturbation neighborhood, allowing the target model to perform fine-grained attribution exclusively within the optimized context. Empirical evaluations on long-context benchmarks demonstrate that our method makes surgical explanations practicable and provides faithful explanations to users.

cs.CL↗

arXiv2025

PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices

Retrieval-augmented generation (RAG) has been extensively used as a de facto paradigm in various large language model (LLM)-driven applications on mobile devices, such as mobile assistants leveraging personal emails or meeting records. However, due to the lengthy prompts and the resource constraints, mobile RAG systems exhibit significantly high response latency. On this issue, one promising approach is to reuse intermediate computational results across different queries to eliminate redundant computation. But most existing approaches, such as KV cache reuse and semantic cache reuse, are designed for cloud settings and perform poorly, overlooking the distinctive characteristics of mobile RAG. We propose PerCache, a novel hierarchical cache solution designed for reducing end-to-end latency of personalized RAG applications on mobile platforms. PerCache adopts a hierarchical architecture that progressively matches similar queries and QKV cache to maximize the reuse of intermediate results at different computing stages. To improve cache hit rate, PerCache applies a predictive method to populate cache with queries that are likely to be raised in the future. In addition, PerCache can adapt its configurations to dynamic system loads, aiming at maximizing the caching utility with minimal resource consumption. We implement PerCache on top of an existing mobile LLM inference engine with commodity mobile phones. Extensive evaluations show that PerCache can surpass the best-performing baseline by 34.4% latency reduction across various applications and maintain optimal latency performance under dynamic resource changes.

cs.DC↗

arXiv2025

DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignals

Biosignals collected from wearable devices are widely utilized in healthcare applications. Machine learning models used in these applications often rely on features extracted from biosignals due to their effectiveness, lower data dimensionality, and wide compatibility across various model architectures. However, existing feature extraction methods often lack task-specific contextual knowledge, struggle to identify optimal features in high-dimensional combinatorial feature space, and are prone to automated code generation and execution errors. In this paper, we propose DeepFeature, the first LLM-empowered, context-aware feature generation framework for wearable biosignals. DeepFeature introduces a multi-source feature generation mechanism that integrates the inherent ability of LLMs, expert knowledge and inter-feature interactions. It also employs an iterative feature refinement process that uses feature assessment-based feedback for feature re-selection. Additionally, DeepFeature utilizes a robust multi-layer filtering and verification approach for feature description-to-code translation to ensure that the feature extraction functions run without crashing. Experimental evaluation results show that DeepFeature achieves the highest average AUROC across eight tasks under both sample-level and subject-level settings, outperforming the best baselines by 4.56% and 4.61%, respectively. DeepFeature achieves the most pronounced gains on the PPG-BP tasks, while remaining competitive with the best-performing baselines on Epilepsy, WESAD, and our self-collected SEN dataset.

cs.AI↗

arXiv2025

A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning

Multimodal human action recognition (HAR) leverages complementary sensors for activity classification. Beyond recognition, recent advances in large language models (LLMs) enable detailed descriptions and causal reasoning, motivating new tasks: human action understanding (HAU) and human action reasoning (HARn). However, most LLMs, especially large vision language models (LVLMs), struggle with non-RGB modalities such as depth, IMU, and mmWave due to the lack of large-scale data-caption resources. Existing HAR datasets mainly provide coarse data-label annotations, which are insufficient to capture fine-grained action dynamics needed for HAU and HARn. We consider two ground-truth pair types: (1) data label (discrete category) and (2) data caption (textual description). Naively generating captions from labels often lacks logical and spatiotemporal consistency. We introduce CUHK-X, a large-scale multimodal dataset and benchmark suite for HAR, HAU, and HARn. CUHK-X contains 58,445 samples covering 40 actions performed by 30 participants across two indoor environments. To improve caption consistency, we propose a prompt-based scene creation method that leverages LLMs to generate logically connected activity sequences, followed by human validation. CUHK-X includes three benchmarks with six evaluation tasks. Experiments report average accuracies of 76.52% (HAR), 40.76% (HAU), and 70.25% (HARn). CUHK-X aims to enable the community to apply and develop data-intensive learning methods for robust, multimodal human activity analysis. Project page and code: https://openaiotlab.github.io/CUHK-X/ and https://github.com/openaiotlab/CUHK-X.

cs.CV↗

arXiv2025

ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild

Recent studies have begun to explore proactive large language model (LLM) agents that provide unobtrusive assistance by automatically leveraging contextual information, such as in code editing and in-app suggestions. However, most focus on short, task-specific episodes or on-screen contexts, rather than continuously perceiving and assisting users throughout daily life. Enabling such in-the-wild assistance requires continuous sensing of users' surroundings, which can incur substantial system overhead. In this work, we propose ProAgent, an end-to-end proactive agent system that harnesses on-demand sensory contexts to provide in-the-wild assistance. ProAgent first employs on-demand tiered perception to continuously sense users' surroundings by integrating low-cost contextual cues with richer perception on demand, and uses proactive-oriented context extraction to derive hierarchical contexts integrating both sensory contexts and human preferences. ProAgent then employs a context-aware proactive reasoner to infer user needs and invokes external tools to deliver proactive assistance. We implement ProAgent on AR glasses and evaluate it on a public dataset and a real-world dataset. Results demonstrate that ProAgent achieves up to 27.7% higher proactive prediction accuracy and 20.5% lower false detection than state-of-the-art baselines. A user study with 20 participants shows that 85% were satisfied with ProAgent and willing to use it in daily life.

cs.AI↗

arXiv2025

VibOmni: Towards Scalable Bone-conduction Speech Enhancement on Earables

Earables, such as True Wireless Stereo earphones and VR/AR headsets, are increasingly popular, yet their compact design poses challenges for robust voice-related applications like telecommunication and voice assistant interactions in noisy environments. Existing speech enhancement systems, reliant solely on omnidirectional microphones, struggle with ambient noise like competing speakers. To address these issues, we propose VibOmni, a lightweight, end-to-end multi-modal speech enhancement system for earables that leverages bone-conducted vibrations captured by widely available Inertial Measurement Units (IMUs). VibOmni integrates a two-branch encoder-decoder deep neural network to fuse audio and vibration features. To overcome the scarcity of paired audio-vibration datasets, we introduce a novel data augmentation technique that models Bone Conduction Functions (BCFs) from limited recordings, enabling synthetic vibration data generation with only 4.5% spectrogram similarity error. Additionally, a multi-modal SNR estimator facilitates continual learning and adaptive inference, optimizing performance in dynamic, noisy settings without on-device back-propagation. Evaluated on real-world datasets from 32 volunteers with different devices, VibOmni achieves up to 21% improvement in Perceptual Evaluation of Speech Quality (PESQ), 26% in Signal-to-Noise Ratio (SNR), and about 40% WER reduction with much less latency on mobile devices. A user study with 35 participants showed 87% preferred VibOmni over baselines, demonstrating its effectiveness for deployment in diverse acoustic environments.

cs.SD↗

arXiv2025

Synera: Synergistic LLM Serving across Device and Cloud at Scale

Large Language Models (LLMs) are becoming key components in various mobile operating systems, driving smart applications like interactive chatbots and personal assistants. While bringing enhanced intelligence to mobile ends, their deployment suffers from a set of performance challenges, especially the generation quality degradation and prolonged latency. Prior works have mainly relied on solutions of cloud offloading or on-device Small Language Models (SLMs). However, the former is usually limited by the communication bottleneck, and the latter sacrifices generation quality due to resource constraints. To mitigate these limitations, this paper proposes Synera, a device-cloud synergistic LLM serving system that applies an efficient SLM-LLM synergistic mechanism. Through empirical studies on LLM's unique computing characteristics, Synera identifies a set of underexplored optimization opportunities in device-cloud synergistic LLM inference, including offloading decisions, pipeline stalls, and batching bottlenecks. To translate them into enhanced performance, Synera introduces tailored designs of communication-efficient selective offloading, stall-free parallel inference, and scalable cloud batching. Extensive evaluations with real-world testbeds show that Synera enables 1.20-5.47x better generation quality against competitive baselines with on-par latency performance. Compared with existing cloud serving, Synera achieves 8.2-16.5% lower cloud serving cost on various benchmarks.

cs.DC↗

arXiv2025

CoHear: Conversation Enhancement via Multi-Earphone Collaboration

In crowded places such as conferences, background noise, overlapping voices, and lively interactions make it difficult to have clear conversations. This situation often worsens the phenomenon known as "cocktail party deafness." We present ClearSphere, the collaborative system that enhances speech at the conversation level with multi-earphones. Real-time conversation enhancement requires a holistic modeling of all the members in the conversation, and an effective way to extract the speech from the mixture. ClearSphere bridges the acoustic sensor system and state-of-the-art deep learning for target speech extraction by making two key contributions: 1) a conversation-driven network protocol, and 2) a robust target conversation extraction model. Our networking protocol enables mobile, infrastructure-free coordination among earphone devices. Our conversation extraction model can leverage the relay audio in a bandwidth-efficient way. ClearSphere is evaluated in both real-world experiments and simulations. Results show that our conversation network obtains more than 90\% accuracy in group formation, improves the speech quality by up to 8.8 dB over state-of-the-art baselines, and demonstrates real-time performance on a mobile device. In a user study with 20 participants, ClearSphere has a much higher score than baseline with good usability.

cs.SD↗

arXiv2025

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either rely exclusively on observations from enclosed environments (e.g., desktop UIs) with direct LLM inference or employ rule-based proactive notifications, leading to suboptimal user intent understanding and limited functionality for proactive service. In this paper, we introduce ContextAgent, the first context-aware proactive agent that incorporates extensive sensory contexts surrounding humans to enhance the proactivity of LLM agents. ContextAgent first extracts multi-dimensional contexts from massive sensory perceptions on wearables (e.g., video and audio) to understand user intentions. ContextAgent then leverages the sensory contexts and personas from historical data to predict the necessity for proactive services. When proactive assistance is needed, ContextAgent further automatically calls the necessary tools to assist users unobtrusively. To evaluate this new task, we curate ContextAgentBench, the first benchmark for evaluating context-aware proactive LLM agents, covering 1,000 samples across nine daily scenarios and twenty tools. Experiments on ContextAgentBench show that ContextAgent outperforms baselines by achieving up to 8.5% and 6.0% higher accuracy in proactive predictions and tool calling, respectively. We hope our research can inspire the development of more advanced, human-centric, proactive AI assistants. The code and dataset are publicly available at https://github.com/openaiotlab/ContextAgent.

cs.AI↗

arXiv2025

Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models

Post-hoc explanations provide transparency and are essential for guiding model optimization, such as prompt engineering and data sanitation. However, applying model-agnostic techniques to Large Language Models (LLMs) is hindered by prohibitive computational costs, rendering these tools dormant for real-world applications. To revitalize model-agnostic interpretability, we propose a budget-friendly proxy framework that leverages efficient models to approximate the decision boundaries of expensive LLMs. We introduce a screen-and-apply mechanism to statistically verify local alignment before deployment. Our empirical evaluation confirms that proxy explanations achieve over 90% fidelity with only 11% of the oracle's cost. Building on this foundation, we demonstrate the actionable utility of our framework in prompt compression and poisoned example removal. Results show that reliable proxy explanations effectively guide optimization, transforming interpretability from a passive observation tool into a scalable primitive for LLM development. Additionally, we open-source code and datasets to facilitate future research.

cs.LG↗

arXiv2025

An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding

The rapid advancements in Large Vision Language Models (LVLMs) offer the potential to surpass conventional labeling by generating richer, more detailed descriptions of on-device human behavior understanding (HBU) in low-resolution vision systems, such as depth, thermal, and infrared. However, existing large vision language model (LVLM) approaches are unable to understand low-resolution data well as they are primarily designed for high-resolution data, such as RGB images. A quick fixing approach is to caption a large amount of low-resolution data, but it requires a significant amount of labor-intensive annotation efforts. In this paper, we propose a novel, labor-saving system, Llambda, designed to support low-resolution HBU. The core idea is to leverage limited labeled data and a large amount of unlabeled data to guide LLMs in generating informative captions, which can be combined with raw data to effectively fine-tune LVLM models for understanding low-resolution videos in HBU. First, we propose a Contrastive-Oriented Data Labeler, which can capture behavior-relevant information from long, low-resolution videos and generate high-quality pseudo labels for unlabeled data via contrastive learning. Second, we propose a Physical-Knowledge Guided Captioner, which utilizes spatial and temporal consistency checks to mitigate errors in pseudo labels. Therefore, it can improve LLMs' understanding of sequential data and then generate high-quality video captions. Finally, to ensure on-device deployability, we employ LoRA-based efficient fine-tuning to adapt LVLMs for low-resolution data. We evaluate Llambda using a region-scale real-world testbed and three distinct low-resolution datasets, and the experiments show that Llambda outperforms several state-of-the-art LVLM systems up to $40.03\%$ on average Bert-Score.

cs.CV↗

arXiv2025

EgoLog: Ego-Centric Fine-Grained Daily Log with Ubiquitous Wearables

Despite advances in human activity recognition (HAR) with different modalities, a precise, robust, and accurate daily log system is not yet available. Current solutions primarily rely on controlled, lab-based data collection, which limits their real-world applicability. The challenges towards a fine-grained daily log are 1) contextual awareness, 2) spatial awareness, and 3) effective fusion of multi-modal sensor data. To solve them, we propose EgoLog, which integrates effective audio-IMU fusion for daily log with ubiquitous wearables. Our approach first fuses audio and IMU data from two perspectives: temporal understanding and spatial understanding. We extract scenario-level features and aggregate them in the time dimension, while using motion compensation to enhance the performance of sound source localization. The knowledge obtained from these steps is then integrated into a multi-modal HAR framework. Here, the scenario provides prior knowledge, and the spatial location helps differentiate the user from the background. Furthermore, we integrate a LLM to enhance scenario recognition through logical reasoning. The knowledge derived from the LLM is subsequently transferred back to the local device to enable efficient, on-device inference. Evaluated on both public and self-collected dataset, EgoLog achieves effective multimodal fusion for both activity and scenraio recognition, outperforms the baseline by 12% and 15%, respectively.

cs.HC↗

arXiv2025

MMLNB: Multi-Modal Learning for Neuroblastoma Subtyping Classification Assisted with Textual Description Generation

Neuroblastoma (NB), a leading cause of childhood cancer mortality, exhibits significant histopathological variability, necessitating precise subtyping for accurate prognosis and treatment. Traditional diagnostic methods rely on subjective evaluations that are time-consuming and inconsistent. To address these challenges, we introduce MMLNB, a multi-modal learning (MML) model that integrates pathological images with generated textual descriptions to improve classification accuracy and interpretability. The approach follows a two-stage process. First, we fine-tune a Vision-Language Model (VLM) to enhance pathology-aware text generation. Second, the fine-tuned VLM generates textual descriptions, using a dual-branch architecture to independently extract visual and textual features. These features are fused via Progressive Robust Multi-Modal Fusion (PRMF) Block for stable training. Experimental results show that the MMLNB model is more accurate than the single modal model. Ablation studies demonstrate the importance of multi-modal fusion, fine-tuning, and the PRMF mechanism. This research creates a scalable AI-driven framework for digital pathology, enhancing reliability and interpretability in NB subtyping classification. Our source code is available at https://github.com/HovChen/MMLNB.

cs.CV↗