arXiv subjects

Li Yu

Publications and source records attributed to Li Yu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Ill-Posedness Analysis of CSI-Based Electromagnetic Inverse Scattering for Material Reconstruction in ISAC Systems

Channel state information (CSI)-based electromagnetic inverse scattering for material reconstruction in ISAC systems enables physics-grounded, material-aware DT. Yet the resulting CSI-induced scattering operator is often severely ill-conditioned. To understand the origin of the ill-posedness, this paper analyzes the mathematical properties of the electromagnetic inverse problem and investigates the operator structure of the ISAC scattering matrix jointly shaped by in-domain scattering responses and Tx/Rx propagation channels. We show that background-related matrix columns are highly coherent and dominate the near rank deficiency, whereas scatterer-related columns are comparatively weakly correlated; their coherence decreases with the number of probing frequencies and thus contributes to the effective rank. Motivated by this analysis, we prove that restricting the ROI around the true scatterer yields a provable condition-number reduction and a tightened CRLB, and we quantify the impact of ROI mismatch numerically. To operationalize these insights, an ROI-constrained QP framework is adopted, where a linear sampling method delineates a coarse ROI and the QP update is performed in the reduced subspace. Full-wave FDTD simulations over multiple geometries and SNR validate pronounced conditioning improvement, substantial complexity savings, and improved robustness, consistent with the proposed analysis, compared with the full-domain formulation.

eess.SP↗

arXiv2026

Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution

Diffusion-based Real-World Image Super-Resolution (Real-ISR) achieves impressive perceptual quality but suffers from high computational costs due to iterative sampling. While recent distillation approaches leveraging large-scale Text-to-Image (T2I) priors have enabled one-step generation, they are typically hindered by prohibitive parameter counts and the inherent capability bounds imposed by teacher models. As a lightweight alternative, Consistency Models offer efficient inference but struggle with two critical limitations: the accumulation of consistency drift inherent to transitive training, and a phenomenon we term "Geometric Decoupling" - where the generative trajectory achieves pixel-wise alignment yet fails to preserve structural coherence. To address these challenges, we propose GTASR (Geometric Trajectory Alignment Super-Resolution), a simple yet effective consistency training paradigm for Real-ISR. Specifically, we introduce a Trajectory Alignment (TA) strategy to rectify the tangent vector field via full-path projection, and a Dual-Reference Structural Rectification (DRSR) mechanism to enforce strict structural constraints. Extensive experiments verify that GTASR delivers superior performance over representative baselines while maintaining minimal latency. The code and model will be released at https://github.com/Blazedengcy/GTASR.

cs.CV↗

arXiv2026

Ostrakon-VL: Towards Domain-Expert MLLM for Food-Service and Retail Stores

Multimodal Large Language Models (MLLMs) have recently achieved substantial progress in general-purpose perception and reasoning. Nevertheless, their deployment in Food-Service and Retail Stores (FSRS) scenarios encounters two major obstacles: (i) real-world FSRS data, collected from heterogeneous acquisition devices, are highly noisy and lack auditable, closed-loop data curation, which impedes the construction of high-quality, controllable, and reproducible training corpora; and (ii) existing evaluation protocols do not offer a unified, fine-grained and standardized benchmark spanning single-image, multi-image, and video inputs, making it challenging to objectively gauge model robustness. To address these challenges, we first develop Ostrakon-VL, an FSRS-oriented MLLM based on Qwen3-VL-8B. Second, we introduce ShopBench, the first public benchmark for FSRS. Third, we propose QUAD (Quality-aware Unbiased Automated Data-curation), a multi-stage multimodal instruction data curation pipeline. Leveraging a multi-stage training strategy, Ostrakon-VL achieves an average score of 60.1 on ShopBench, establishing a new state of the art among open-source MLLMs with comparable parameter scales and diverse architectures. Notably, it surpasses the substantially larger Qwen3-VL-235B-A22B (59.4) by +0.7, and exceeds the same-scale Qwen3-VL-8B (55.3) by +4.8, demonstrating significantly improved parameter efficiency. These results indicate that Ostrakon-VL delivers more robust and reliable FSRS-centric perception and decision-making capabilities. To facilitate reproducible research, we will publicly release Ostrakon-VL and the ShopBench benchmark.

cs.AI↗

arXiv2026

HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval approaches attempt to address this issue, they typically suffer from coarse-grained caching strategies and incur high I/O overhead. To overcome these limitations, we propose HeteroCache, a training-free dynamic compression framework. Our method is built on two key insights: attention heads exhibit diverse temporal heterogeneity, and there is significant spatial redundancy among heads within the same layer. Guided by these insights, HeteroCache categorizes heads based on stability and similarity, applying a fine-grained weighting strategy that allocates larger cache budgets to heads with rapidly shifting attention to capture context changes. Furthermore, it features a hierarchical storage mechanism where representative heads monitor attention drift to trigger asynchronous, on-demand context retrieval, thereby hiding I/O latency. Experiments demonstrate that HeteroCache achieves state-of-the-art performance on long-context benchmarks and accelerates decoding by up to $3\times$ compared to the original model with a 224K context. Our code is available at https://github.com/ponytaill/HeteroCache.

cs.CL↗

arXiv2025

Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution

Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a "passive accumulation" paradigm, treating memory as a static append-only archive. To bridge the gap between static storage and dynamic reasoning, we propose $\textbf{ReMe}$ ($\textit{Remember Me, Refine Me}$), a comprehensive framework for experience-driven agent evolution. ReMe innovates across the memory lifecycle via three mechanisms: 1) $\textit{multi-faceted distillation}$, which extracts fine-grained experiences by recognizing success patterns, analyzing failure triggers and generating comparative insights; 2) $\textit{context-adaptive reuse}$, which tailors historical insights to new contexts via scenario-aware indexing; and 3) $\textit{utility-based refinement}$, which autonomously adds valid memories and prunes outdated ones to maintain a compact, high-quality experience pool. Extensive experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system. Crucially, we observe a significant memory-scaling effect: Qwen3-8B equipped with ReMe outperforms larger, memoryless Qwen3-14B, suggesting that self-evolving memory provides a computation-efficient pathway for lifelong learning. We release our code and the $\texttt{reme.library}$ dataset to facilitate further research.

cs.AI↗

arXiv2025

MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices

Recently, video generation has witnessed rapid advancements, drawing increasing attention to image-to-video (I2V) synthesis on mobile devices. However, the substantial computational complexity and slow generation speed of diffusion models pose significant challenges for real-time, high-resolution video generation on resource-constrained mobile devices. In this work, we propose MobileI2V, a 270M lightweight diffusion model for real-time image-to-video generation on mobile devices. The core lies in: (1) We analyzed the performance of linear attention modules and softmax attention modules on mobile devices, and proposed a linear hybrid architecture denoiser that balances generation efficiency and quality. (2) We design a time-step distillation strategy that compresses the I2V sampling steps from more than 20 to only two without significant quality loss, resulting in a 10-fold increase in generation speed. (3) We apply mobile-specific attention optimizations that yield a 2-fold speed-up for attention operations during on-device inference. MobileI2V enables, for the first time, fast 720p image-to-video generation on mobile devices, with quality comparable to existing models. Under one-step conditions, the generation speed of each frame of 720p video is less than 100 ms. Our code is available at: https://github.com/hustvl/MobileI2V.

cs.CV↗

arXiv2025

Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs

Timestep distillation is an effective approach for improving the generation efficiency of diffusion models. The Consistency Model (CM), as a trajectory-based framework, demonstrates significant potential due to its strong theoretical foundation and high-quality few-step generation. Nevertheless, current continuous-time consistency distillation methods still rely heavily on training data and computational resources, hindering their deployment in resource-constrained scenarios and limiting their scalability to diverse domains. To address this issue, we propose Trajectory-Backward Consistency Model (TBCM), which eliminates the dependence on external training data by extracting latent representations directly from the teacher model's generation trajectory. Unlike conventional methods that require VAE encoding and large-scale datasets, our self-contained distillation paradigm significantly improves both efficiency and simplicity. Moreover, the trajectory-extracted samples naturally bridge the distribution gap between training and inference, thereby enabling more effective knowledge transfer. Empirically, TBCM achieves 6.52 FID and 28.08 CLIP scores on MJHQ-30k under one-step generation, while reducing training time by approximately 40% compared to Sana-Sprint and saving a substantial amount of GPU memory, demonstrating superior efficiency without sacrificing quality. We further reveal the diffusion-generation space discrepancy in continuous-time consistency distillation and analyze how sampling strategies affect distillation performance, offering insights for future distillation research. GitHub Link: https://github.com/hustvl/TBCM.

cs.CV↗

arXiv2025

Blind Quality Enhancement of Compressed Video via Fine-Grained Degradation-Guided Sequential Inference

Existing studies on quality enhancement for compressed video (QECV) predominantly rely on known quantization parameters (QPs), training separate enhancement models for each QP setting, which are referred to as non-blind methods. However, in practical scenarios such as transcoding and transmission, QPs may be partially or entirely unavailable, which limits the applicability of these methods and motivates the development of blind QECV techniques. Existing blind methods typically generate degradation vectors using classification models trained with cross-entropy loss, and employ them as channel attention to guide artifact reduction. Nevertheless, such degradation representations mainly capture global compression information and lack fine-grained spatial cues, making them less effective in handling spatially varying artifact patterns. To address this issue, we propose a pre-trained degradation representation learning module that decouples and extracts high-dimensional, multi-scale degradation representations from compressed video content, providing fine-grained guidance for artifact reduction. Furthermore, most existing blind and nonblind methods adopt a uniform inference architecture for all compression levels, ignoring the distinct computational demands of different QPs. To overcome this limitation, we introduce a sequential inference strategy that adaptively adjusts the number of artifact reduction stages according to the estimated compression level. Extensive experiments show that the proposed method significantly improves enhancement performance. In particular, at QP = 22, it raises PSNR improvement from 0.31 dB to 0.65 dB over the previous state-of-the-art blind method. Meanwhile, with the proposed sequential inference strategy, the average inference time at QP = 22 is reduced by 50% compared with that at QP = 42.

cs.CV↗

arXiv2025

Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment

Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances and classify categories. However, their objectives may tend to detect the most salient response segments, while neglecting to mine diverse normal patterns separated from anomalies, and are prone to category confusion due to similar appearance, leading to unsatisfactory fine-grained classification results. Therefore, we propose a novel Disentangled Semantic Alignment Network (DSANet) to explicitly separate abnormal and normal features from coarse-grained and fine-grained aspects, enhancing the distinguishability. Specifically, at the coarse-grained level, we introduce a self-guided normality modeling branch that reconstructs input video features under the guidance of learned normal prototypes, encouraging the model to exploit normality cues inherent in the video, thereby improving the temporal separation of normal patterns and anomalous events. At the fine-grained level, we present a decoupled contrastive semantic alignment mechanism, which first temporally decomposes each video into event-centric and background-centric components using frame-level anomaly scores and then applies visual-language contrastive learning to enhance class-discriminative representations. Comprehensive experiments on two standard benchmarks, namely XD-Violence and UCF-Crime, demonstrate that DSANet outperforms existing state-of-the-art methods.

cs.CV↗

arXiv2025

AgentEvolver: Towards Efficient Self-Evolving Agent System

Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to developing such agents remain costly and inefficient, as they typically require manually constructed task datasets and reinforcement learning (RL) pipelines with extensive random exploration. These limitations lead to prohibitively high data-construction costs, low exploration efficiency, and poor sample utilization. To address these challenges, we present AgentEvolver, a self-evolving agent system that leverages the semantic understanding and reasoning capabilities of LLMs to drive autonomous agent learning. AgentEvolver introduces three synergistic mechanisms: (i) self-questioning, which enables curiosity-driven task generation in novel environments, reducing dependence on handcrafted datasets; (ii) self-navigating, which improves exploration efficiency through experience reuse and hybrid policy guidance; and (iii) self-attributing, which enhances sample efficiency by assigning differentiated rewards to trajectory states and actions based on their contribution. By integrating these mechanisms into a unified framework, AgentEvolver enables scalable, cost-effective, and continual improvement of agent capabilities. Preliminary experiments indicate that AgentEvolver achieves more efficient exploration, better sample utilization, and faster adaptation compared to traditional RL-based baselines.

cs.LG↗

arXiv2025

Quantum Fisher Information With General Quantum Coherence in multi-dimensional quantum systems

Quantum metrology is a science about quantum measurements and it plays a key role in precision of quantum parameter estimation. Meanwhile, quantum coherence is an important quantum feature and quantum Fisher information (QFI) is an important indicator for precision of quantum parameter estimation. In this paper, we explore the relationship between QFI and quantum coherence in multi-dimensional quantum systems. We introduce a new concept referred to as General Quantum Coherence (GQC), which characterizes the quantum coherence and the eigenenergies of the Hamiltonian in the interaction processes. GQC captures quantum nature of high-dimensional quantum states and addresses shortcomings in coherence measurement. Additionally, we observe a stringent square relationship between GQC and QFI. This finding provides a crucial guideline for improving the precision of parameter estimation.

quant-ph↗

arXiv2025

A Robust CSI-Based Scatterer Geometric Reconstruction Method for 6G ISAC System

Digital twin (DT) is a core enabler of sixth generation (6G) mobile systems. As a prerequisite for DT, scatterer geometric reconstruction (SGR) in propagation environments is essential but typically requires extra sensors such as cameras and LiDAR. With integrated sensing and communication (ISAC) in 6G, we reinterpret the linear sampling method (LSM) from a wireless channel viewpoint and propose a CSI based variant for sensor free SGR: by exploiting the shared channel characteristics of multipath and scattering, in band CSI replaces the scattered field measurements usually required by LSM. However, aperture limited arrays reduce LSM robustness. To address this, we propose matched filtering enhanced multi frequency LSM (MF MLSM). Multi frequency data increases frequency diversity, and matched filtering coherently aligns inter frequency phases to avoid artifacts, both of which improve robustness. Experiments with apertures of 93.6 deg, 144 deg, and 180 deg and SNRs of 27 dB and 12 dB demonstrate robust SGR with this approach.

eess.SP↗

arXiv2025

RankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation

Cross-domain recommendation systems face the challenge of integrating fine-grained user and item relationships across various product domains. To address this, we introduce RankGraph, a scalable graph learning framework designed to serve as a core component in recommendation foundation models (FMs). By constructing and leveraging graphs composed of heterogeneous nodes and edges across multiple products, RankGraph enables the integration of complex relationships between users, posts, ads, and other entities. Our framework employs a GPU-accelerated Graph Neural Network and contrastive learning, allowing for dynamic extraction of subgraphs such as item-item and user-user graphs to support similarity-based retrieval and real-time clustering. Furthermore, RankGraph integrates graph-based pretrained representations as contextual tokens into FM sequence models, enriching them with structured relational knowledge. RankGraph has demonstrated improvements in click (+0.92%) and conversion rates (+2.82%) in online A/B tests, showcasing its effectiveness in cross-domain recommendation scenarios.

cs.IR↗

arXiv2025

LENS: Learning to Segment Anything with Unified Reinforced Reasoning

Text-prompted image segmentation enables fine-grained visual understanding and is critical for applications such as human-computer interaction and robotics. However, existing supervised fine-tuning methods typically ignore explicit chain-of-thought (CoT) reasoning at test time, which limits their ability to generalize to unseen prompts and domains. To address this issue, we introduce LENS, a scalable reinforcement-learning framework that jointly optimizes the reasoning process and segmentation in an end-to-end manner. We propose unified reinforcement-learning rewards that span sentence-, box-, and segment-level cues, encouraging the model to generate informative CoT rationales while refining mask quality. Using a publicly available 3-billion-parameter vision-language model, i.e., Qwen2.5-VL-3B-Instruct, LENS achieves an average cIoU of 81.2% on the RefCOCO, RefCOCO+, and RefCOCOg benchmarks, outperforming the strong fine-tuned method, i.e., GLaMM, by up to 5.6%. These results demonstrate that RL-driven CoT reasoning significantly enhances text-prompted segmentation and offers a practical path toward more generalizable Segment Anything models (SAM). Code is available at https://github.com/hustvl/LENS.

cs.CV↗

arXiv2025

Digital Twin Channel-Aided CSI Prediction: An Environment-Based Subspace Extraction Approach for Achieving Low Overhead and High Robustness

To meet the robust and high-speed communication requirements of the sixth-generation (6G) mobile communication system in complex scenarios, sensing- and artificial intelligence (AI)-based digital twin channel (DTC) techniques become a promising approach to reduce system overhead. In this paper, we propose an environment-specific channel subspace basis (ECB)-aided partial-to-whole channel state information (CSI) prediction method (ECB-P2WCP) for realizing DTC-enabled low-overhead channel prediction. Specifically, we introduce a wireless environment knowledge (WEK) construction method that extracts ECB from the digital twin environment via subspace estimation. This ECB characterizes the static statistical properties of the electromagnetic environment and serves as environment information prior to the prediction task. Then, we fuse ECB with real-time estimated local CSI to predict the entire spatial-frequency domain channel for both the present and future time instances. Hence, an ECB-based partial-to-whole CSI prediction network (ECB-P2WNet) is designed to achieve a robust channel prediction scheme in various complex scenarios. Simulation results indicate that incorporating ECB provides significant benefits under low signal-to-noise ratio and pilot ratio conditions, achieving a reduction of up to 50\% in pilot overhead. Additionally, the proposed method maintains robustness against multi-user interference, tolerating 3-meter localization errors with only a 0.5 dB normalized mean square error increase, and predicts CSI for the next channel coherent time within 1.3 milliseconds.

eess.SP↗

arXiv2025

Digital Twin Channel-Enabled Online Resource Allocation for 6G: Principle, Architecture and Application

Emerging applications such as holographic communication, autonomous driving, and the industrial Internet of Things impose stringent requirements on flexible, low-latency, and reliable resource allocation in 6G networks. Conventional methods, which rely on statistical modeling, have proven effective in general contexts but may fail to achieve optimal performance in specific and dynamic environments. Furthermore, acquiring real-time channel state information (CSI) typically requires excessive pilot overhead. To address these challenges, a digital twin channel (DTC)-enabled online optimization framework is proposed, in which DTC is employed to predict CSI based on environmental sensing. The predicted CSI is then utilized by lightweight game-theoretic algorithms to perform online resource allocation in a timely and efficient manner. Simulation results based on a digital replica of a realistic industrial workshop demonstrate that the proposed method achieves throughput improvements of up to 11.5\% compared with pilot-based ideal CSI schemes, validating its effectiveness for scalable, low-overhead, and environment-aware communication in future 6G networks.

cs.AI↗

arXiv2025

Fragility of Topology under Electronic Correlations in Iron Chalcogenides

The interplay between electronic correlations and topology is a central topic in the study of quantum materials. In this work, we investigate the impact of the orbital-selective Mott phase (OSMP) on the topological properties of FeTe1-xSex (FTS), an iron chalcogenide superconductor known to host both non-trivial Z2 topology and strong electronic correlations. Using angle-resolved photoemission spectroscopy, we track the evolution of topological surface states across various doping levels and temperatures. We identify a topological phase transition between trivial and non-trivial topology as a function of selenium content, with critical behavior observed between x = 0.04 and x = 0.09. Additionally, we find that at elevated temperatures, the coherence of the topological surface state deteriorates due to the emergence of OSMP, despite the topological invariant remaining intact. Our results demonstrate that the non-trivial topology in iron chalcogenide is fragile under strong electronic correlations.

cond-mat.str-el↗

arXiv2025

A safety governor for learning explicit MPC controllers from data

We tackle neural networks (NNs) to approximate model predictive control (MPC) laws. We propose a novel learning-based explicit MPC structure, which is reformulated into a dual-mode scheme over maximal constrained feasible set. The scheme ensuring the learning-based explicit MPC reduces to linear feedback control while entering the neighborhood of origin. We construct a safety governor to ensure that learning-based explicit MPC satisfies all the state and input constraints. Compare to the existing approach, our approach is computationally easier to implement even in high-dimensional system. The proof of recursive feasibility for the safety governor is given. Our approach is demonstrated on numerical examples.

eess.SY↗