Searcharxiv⌕ Search

arXiv subjects

Yu Wang

Publications and source records attributed to Yu Wang.

At least 343 records · Page 19Linked to original sources
arXiv2026

Teacher-Guided Student Self-Knowledge Distillation Using Diffusion Model

Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due to the difference in feature distributions between the teacher and student, the student model may learn incompatible information from the teacher. To address this problem, we propose teacher-guided student Diffusion Self-KD, dubbed as DSKD. Instead of the direct teacher-student alignment, we leverage the teacher classifier to guide the sampling process of denoising student features through a light-weight diffusion model. We then propose a novel locality-sensitive hashing (LSH)-guided feature distillation method between the original and denoised student features. The denoised student features encapsulate teacher knowledge and could be regarded as a teacher role. In this way, our DSKD method could eliminate discrepancies in mapping manners and feature distributions between the teacher and student, while learning meaningful knowledge from the teacher. Experiments on visual recognition tasks demonstrate that DSKD significantly outperforms existing KD methods across various models and datasets. Our code is attached in supplementary material.

cs.CV↗
arXiv2026

From Intents to Actions: Agentic AI in Autonomous Networks

Telecommunication networks are increasingly expected to operate autonomously while supporting heterogeneous services with diverse and often conflicting intents -- that is, performance objectives, constraints, and requirements specific to each service. However, transforming high-level intents -- such as ultra-low latency, high throughput, or energy efficiency -- into concrete control actions (i.e., low-level actuator commands) remains beyond the capability of existing heuristic approaches. This work introduces an Agentic AI system for intent-driven autonomous networks, structured around three specialized agents. A supervisory interpreter agent, powered by language models, performs both lexical parsing of intents into executable optimization templates and cognitive refinement based on feedback, constraint feasibility, and evolving network conditions. An optimizer agent converts these templates into tractable optimization problems, analyzes trade-offs, and derives preferences across objectives. Lastly, a preference-driven controller agent, based on multi-objective reinforcement learning, leverages these preferences to operate near the Pareto frontier of network performance that best satisfies the original intent. Collectively, these agents enable networks to autonomously interpret, reason over, adapt to, and act upon diverse intents and network conditions in a scalable manner.

cs.LG↗
arXiv2026

SCR2-ST: Combine Single Cell with Spatial Transcriptomics for Efficient Active Sampling via Reinforcement Learning

Spatial transcriptomics (ST) is an emerging technology that enables researchers to investigate the molecular relationships underlying tissue morphology. However, acquiring ST data remains prohibitively expensive, and traditional fixed-grid sampling strategies lead to redundant measurements of morphologically similar or biologically uninformative regions, thus resulting in scarce data that constrain current methods. The well-established single-cell sequencing field, however, could provide rich biological data as an effective auxiliary source to mitigate this limitation. To bridge these gaps, we introduce SCR2-ST, a unified framework that leverages single-cell prior knowledge to guide efficient data acquisition and accurate expression prediction. SCR2-ST integrates a single-cell guided reinforcement learning-based (SCRL) active sampling and a hybrid regression-retrieval prediction network SCR2Net. SCRL combines single-cell foundation model embeddings with spatial density information to construct biologically grounded reward signals, enabling selective acquisition of informative tissue regions under constrained sequencing budgets. SCR2Net then leverages the actively sampled data through a hybrid architecture combining regression-based modeling with retrieval-augmented inference, where a majority cell-type filtering mechanism suppresses noisy matches and retrieved expression profiles serve as soft labels for auxiliary supervision. We evaluated SCR2-ST on three public ST datasets, demonstrating SOTA performance in both sampling efficiency and prediction accuracy, particularly under low-budget scenarios. Code is publicly available at: https://github.com/hrlblab/SCR2ST

cs.CV↗
arXiv2026

Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis

Language models are revolutionizing the biochemistry domain, assisting scientists in drug design and chemical synthesis with high efficiency. Yet current approaches struggle between small language models prone to hallucination and limited knowledge retention, and large cloud-based language models plagued by privacy risks and high inference costs. To bridge this gap, we introduce ChemCRAFT, a novel framework leveraging agentic reinforcement learning to decouple chemical reasoning from knowledge storage. Instead of forcing the model to memorize vast chemical data, our approach empowers the language model to interact with a sandbox for precise information retrieval. This externalization of knowledge allows a locally deployable small model to achieve superior performance with minimal inference costs. To enable small language models for agent-calling ability, we build an agentic trajectory construction pipeline and a comprehensive chemical-agent sandbox. Based on sandbox interactions, we constructed ChemToolDataset, the first large-scale chemical tool trajectory dataset. Simultaneously, we propose SMILES-GRPO to build a dense chemical reward function, promoting the model's ability to call chemical agents. Evaluations across diverse aspects of drug design show that ChemCRAFT outperforms current cloud-based LLMs in molecular structure analysis, molecular optimization, and synthesis pathway prediction, demonstrating that scientific reasoning is not solely an emergent ability of model scale, but a learnable policy of tool orchestration. This work establishes a cost-effective and privacy-preserving paradigm for AI-aided chemistry, opening new avenues for accelerating molecular discovery with locally deployable agents. Code available at https://github.com/HowardLi1984/ChemCraft.

cs.LG↗
arXiv2026

On-chip electrically reconfigurable octave-bandwidth optical amplification from visible to near-infrared

Achieving broadband on-chip optical amplification spanning the visible and near-infrared (NIR) can enable diverse quantum sensing, metrology, and classical communication applications within a single unified device. However, conventional semiconductor and ion-doped amplifiers suffer from limited gain bandwidths set by fixed energy levels, while optical parametric amplifiers (OPAs) operating continuously from the visible to the NIR have remained elusive due to dispersion-limited bandwidth and the high pump powers required in the visible or ultraviolet (UV). Here, we overcome these limitations by introducing an electrically reconfigurable OPA architecture on lithium niobate integrated photonics. By synergistically combining ultra-high effective $χ^{(2)}$ nonlinearity ($\sim$7,000\%/W-cm$^2$), high-order dispersion engineering, and local electro-thermal tuning of quasi-phase matching, our device achieves record gain spectral spanning more than an optical octave, from 770 to 1650 nm. This range covers key transitions of many photonic quantum systems and all telecommunication bands. Moreover, our approach eliminates the need for high-power, wavelength-tunable visible or UV pumps, delivering a peak on-chip gain of 23.67 dB with a single 1060 nm pump at 90 mW average on-chip power. This work opens new avenues for multi-functional, reconfigurable photonics unifying the visible and infrared regimes, with broad implications for quantum sensing and communications.

physics.optics↗
arXiv2026

$π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models

Vision-Language-Action (VLA) models enable robots to understand and perform complex tasks from multimodal input. Although recent work explores using reinforcement learning (RL) to automate the laborious data collection process in scaling supervised fine-tuning (SFT), applying RL to large-scale flow-based VLAs (\eg, $π_0$, $π_{0.5}$) remains challenging due to intractable action log-likelihoods raised from flow matching. We address this challenge with $π_{\texttt{RL}}$, featuring two technical approaches: (1) \textbf{Flow-Noise} models the denoising process as a discrete-time MDP with a learnable noise network for exact log-likelihood computation. (2) \textbf{Flow-SDE} integrates denoising with agent-environment interaction, formulating a two-layer MDP that employs ODE-to-SDE conversion for efficient RL exploration. We evaluate $π_{\texttt{RL}}$ across various benchmarks, with experiments demonstrating that RL yields significant performance improvements in both in-distribution and out-of-distribution settings.

cs.LG↗
arXiv2026

Pulse-resolved Classification and Characteristics of Long-duration GRBs with \emph{Swift}-BAT Data.I. Precursors versus Main Bursts

We present a systematic pulse-by-pulse analysis of 22 long-duration GRBs observed by \emph{Swift}, each exhibiting a well-separated precursor before the main burst. We compare duration, spectral hardness ratio, minimum variability timescale (MVT), and spectral lag between these components. Both precursors and main bursts have durations and hardness broadly consistent with Type II GRBs. However, precursors show longer MVTs (by factors of 3-10) and diverse lags with near-zero median values, while main bursts display variable MVTs and positive lags. These differences suggest precursors may originate from distinct dissipation conditions, possibly due to cocoon shock breakout or early magnetically dominated outflows. Despite temporal differences, both episodes are consistent with a single collapsar origin, providing no evidence for dual-progenitor events. Our findings support pulse-resolved classification and show that precursors offer critical insights into jet formation and pre-burst activity.

astro-ph.HE↗
arXiv2026

Generalization in Reinforcement Learning for Radio Access Networks

Modern RAN operate in highly dynamic and heterogeneous environments, where hand-tuned, rule-based RRM algorithms often underperform. While RL can surpass such heuristics in constrained settings, the diversity of deployments and unpredictable radio conditions introduce major generalization challenges. Data-driven policies frequently overfit to training conditions, degrading performance in unseen scenarios. To address this, we propose a generalization-centered RL framework for RAN control that: (i) robustly reconstructs dynamically varying states from partial and noisy observations, while encoding static and semi-static information, such as radio nodes, cell attributes, and their topology, through graph representations; (ii) applies domain randomization to broaden the training distribution; and (iii) distributes data generation across multiple actors while centralizing training in a cloud-compatible architecture aligned with O-RAN principles. Although generalization increases computational and data-management complexity, our distributed design mitigates this by scaling data collection and training across diverse network conditions. Applied to downlink link adaptation in five 5G benchmarks, our policy improves average throughput and spectral efficiency by ~10% over an OLLA baseline (10% BLER target) in full-buffer MIMO/mMIMO and by >20% under high mobility. It matches specialized RL in full-buffer traffic and achieves up to 4- and 2-fold gains in eMBB and mixed-traffic benchmarks, respectively. In nine-cell deployments, GAT models offer 30% higher throughput over MLP baselines. These results, combined with our scalable architecture, offer a path toward AI-native 6G RAN using a single, generalizable RL agent.

cs.LG↗
arXiv2026

Energy-Aware DNN Graph Optimization

Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices. We present a method that allows users to optimize energy consumption or balance between energy and inference performance for DNN graphs. This method efficiently searches through the space of equivalent graphs, and identifies a graph and the corresponding algorithms that incur the least cost in execution. We implement the method and evaluate it with multiple DNN models on a GPU-based machine. Results show that our method achieves significant energy savings, i.e., 24% with negligible performance impact.

cs.LG↗
arXiv2026

From Atom to Community: Structured and Evolving Agent Memory for User Behavior Modeling

User behavior modeling lies at the heart of personalized applications like recommender systems. With LLM-based agents, user preference representation has evolved from latent embeddings to semantic memory. While existing memory mechanisms show promise in textual dialogues, modeling non-textual behaviors remains challenging, as preferences must be inferred from implicit signals like clicks without ground truth supervision. Current approaches rely on a single unstructured summary, updated through simple overwriting. However, this is suboptimal: users exhibit multi-faceted interests that get conflated, preferences evolve yet naive overwriting causes forgetting, and sparse individual interactions necessitate collaborative signals. We present STEAM (\textit{\textbf{ST}ructured and \textbf{E}volving \textbf{A}gent \textbf{M}emory}), a novel framework that reimagines how agent memory is organized and updated. STEAM decomposes preferences into atomic memory units, each capturing a distinct interest dimension with explicit links to observed behaviors. To exploit collaborative patterns, STEAM organizes similar memories across users into communities and generates prototype memories for signal propagation. The framework further incorporates adaptive evolution mechanisms, including consolidation for refining memories and formation for capturing emerging interests. Experiments on three real-world datasets demonstrate that STEAM substantially outperforms state-of-the-art baselines in recommendation accuracy, simulation fidelity, and diversity.

cs.IR↗
arXiv2026

Exact Controllability for Stochastic First-Order Multi-Dimensional Hyperbolic Systems

This paper investigates the exact controllability problem for multi-dimensional stochastic first-order symmetric hyperbolic systems with control inputs acting in two distinct ways: an internal control applied to the diffusion term and a boundary control applied to the drift term. By means of a classical duality argument, the controllability problem is reduced to an observability estimate for the corresponding backward stochastic system. The main technical contribution is the establishment of a new global Carleman estimate for such backward systems, combined with a weighted energy identity. This enables us to prove the desired observability inequality under a geometric structural condition (Condition \ref{cond1}), which ensures that all characteristic rays propagate toward the boundary within a finite time. As a result, we obtain exact controllability provided the control time $T$ exceeds a sharp threshold $T_0$ given explicitly in terms of the system geometry. Furthermore, we complement the positive result with several negative controllability theorems, which demonstrate that both controls are necessary and must act in a distributed manner. Our analysis not only extends controllability theory from deterministic to stochastic multi-dimensional hyperbolic systems but also provides, as a byproduct, new results for deterministic systems under a structural hypothesis. Applications to stochastic traffic flow, epidemiological models, and shallow-water equations are discussed.

math.OC↗
arXiv2026

Bridging Expectation Signals: LLM-Based Experiments and a Behavioral Kalman Filter Framework

As LLMs increasingly function as economic agents, the specific mechanisms LLMs use to update their belief with heterogeneous signals remain opaque. We design experiments and develop a Behavioral Kalman Filter framework to quantify how LLM-based agents update expectations, acting as households or firm CEOs, update expectations when presented with individual and aggregate signals. The results from experiments and model estimation reveal four consistent patterns: (1) agents' weighting of priors and signals deviates from unity; (2) both household and firm CEO agents place substantially larger weights on individual signals compared to aggregate signals; (3) we identify a significant and negative interaction between concurrent signals, implying that the presence of multiple information sources diminishes the marginal weight assigned to each individual signal; and (4) expectation formation patterns differ significantly between household and firm CEO agents. Finally, we demonstrate that LoRA fine-tuning mitigates, but does not fully eliminate, behavioral biases in LLM expectation formation.

econ.GN↗
arXiv2026

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent

Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive rich visual-text alignment, instruction-tuning is often text-driven with weaker visual supervision, leading to the degradation of pre-trained visual understanding and causing visual forgetting. Existing approaches, such as direct fine-tuning and continual learning methods, fail to explicitly address this issue, often compressing visual representations and prioritizing task alignment over visual retention, which further worsens visual forgetting. To overcome this limitation, we introduce a novel perspective leveraging effective rank to quantify the degradation of visual representation richness, interpreting this degradation through the information bottleneck principle as excessive compression that leads to the degradation of crucial pre-trained visual knowledge. Building on this view, we propose a modality-decoupled gradient descent (MDGD) method that regulates gradient updates to maintain the effective rank of visual representations while mitigating the over-compression effects described by the information bottleneck. By explicitly disentangling the optimization of visual understanding from task-specific alignment, MDGD preserves pre-trained visual knowledge while enabling efficient task adaptation. To enable lightweight instruction-tuning, we further develop a memory-efficient fine-tuning approach using gradient masking, which selectively updates a subset of model parameters to enable parameter-efficient fine-tuning (PEFT), reducing computational overhead while preserving rich visual representations. Extensive experiments across various downstream tasks and backbone MLLMs demonstrate that MDGD effectively mitigates visual forgetting from pre-trained tasks while enabling strong adaptation to new tasks.

cs.LG↗
arXiv2026

LLM Reasoning for Cold-Start Item Recommendation

Large Language Models (LLMs) have shown significant potential for improving recommendation systems through their inherent reasoning capabilities and extensive knowledge base. Yet, existing studies predominantly address warm-start scenarios with abundant user-item interaction data, leaving the more challenging cold-start scenarios, where sparse interactions hinder traditional collaborative filtering methods, underexplored. To address this limitation, we propose novel reasoning strategies designed for cold-start item recommendations within the Netflix domain. Our method utilizes the advanced reasoning capabilities of LLMs to effectively infer user preferences, particularly for newly introduced or rarely interacted items. We systematically evaluate supervised fine-tuning, reinforcement learning-based fine-tuning, and hybrid approaches that combine both methods to optimize recommendation performance. Extensive experiments on real-world data demonstrate significant improvements in both methodological efficacy and practical performance in cold-start recommendation contexts. Remarkably, our reasoning-based fine-tuned models outperform Netflix's production ranking model by up to 8% in certain cases.

cs.IR↗
arXiv2026

Burst Mode Ultrafast Laser Welding of Sapphire and Fe-36Ni Alloy with Non-optical Contact Condition

Ultrafast laser welding provides a promising approach for high precision integration of transparent and metallic materials. However, its practical application remains constrained by the precise regulation of the interfacial gap. This study investigates the interfacial response and bonding mechanism of sapphire and Fe-36Ni alloy joints under controlled non-optical contact conditions using burst mode ultrafast laser irradiation. A polymer interlayer was introduced between naturally stacked samples to establish a variable interfacial gap, allowing systematic evaluation of gap-dependent morphology, melting behavior, and elemental transport. By redistributing the pulse energy into sequential sub-pulses, the burst mode reconstructs the temporal energy-deposition process, yielding enhanced plasma-material coupling and stable thermal accumulation. Compared with single pulse irradiation, burst mode sustains continuous bonding across gaps exceeding 10 um--far beyond the failure threshold of the single pulse mode--and forms a fusion zone 82% larger. Fracture surface and cross-sectional analyses of SEM and EDS results confirm that sequential sub-pulses promote extensive sapphire melting, droplet-driven gap bridging, and enhanced Al-Fe interdiffusion at the interface. These results provide a scientific basis for high-gap-tolerance ultrafast laser welding and scalable integration of transparent-metal hybrid components in advanced optoelectronic and precision engineering applications.

physics.optics↗
arXiv2026

Scaffold-Aware Generative Augmentation and Reranking for Enhanced Virtual Screening

Ligand-based virtual screening (VS) is an essential step in drug discovery that evaluates large chemical libraries to identify compounds that potentially bind to a therapeutic target. However, VS faces three major challenges: class imbalance due to the low active rate, structural imbalance among active molecules where certain scaffolds dominate, and the need to identify structurally diverse active compounds for novel drug development. We introduce ScaffAug, a scaffold-aware VS framework that addresses these challenges through three modules. The augmentation module first generates synthetic data conditioned on scaffolds of actual hits using generative models, specifically a graph diffusion model. This helps mitigate the class imbalance and furthermore the structural imbalance, due to our proposed scaffold-aware sampling algorithm, designed to produce more samples for active molecules with underrepresented scaffolds. A model-agnostic self-training module is then used to safely integrate the generated synthetic data from our augmentation module with the original labeled data. Lastly, we introduce a reranking module that improves VS by enhancing scaffold diversity in the top recommended set of molecules, while still maintaining and even enhancing the overall general performance of identifying novel, active compounds. We conduct comprehensive computational experiments across five target classes, comparing ScaffAug against existing baseline methods by reporting the performance of multiple evaluation metrics and performing ablation studies on ScaffAug. Overall, this work introduces novel perspectives on effectively enhancing VS by leveraging generative augmentations, reranking, and general scaffold-awareness.

cs.LG↗
arXiv2026

AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization

Large Language Models have demonstrated profound utility in the medical domain. However, their application to autonomous Electronic Health Records~(EHRs) navigation remains constrained by a reliance on curated inputs and simplified retrieval tasks. To bridge the gap between idealized experimental settings and realistic clinical environments, we present AgentEHR. This benchmark challenges agents to execute complex decision-making tasks, such as diagnosis and treatment planning, requiring long-range interactive reasoning directly within raw and high-noise databases. In tackling these tasks, we identify that existing summarization methods inevitably suffer from critical information loss and fractured reasoning continuity. To address this, we propose RetroSum, a novel framework that unifies a retrospective summarization mechanism with an evolving experience strategy. By dynamically re-evaluating interaction history, the retrospective mechanism prevents long-context information loss and ensures unbroken logical coherence. Additionally, the evolving strategy bridges the domain gap by retrieving accumulated experience from a memory bank. Extensive empirical evaluations demonstrate that RetroSum achieves performance gains of up to 29.16% over competitive baselines, while significantly decreasing total interaction errors by up to 92.3%.

cs.CL↗
arXiv2026

ParkingTwin: Training-Free Streaming 3D Reconstruction for Parking-Lot Digital Twins

High-fidelity parking-lot digital twins provide essential priors for path planning, collision checking, and perception validation in Automated Valet Parking (AVP). Yet robot-oriented reconstruction faces a trilemma: sparse forward-facing views cause weak parallax and ill-posed geometry; dynamic occlusions and extreme lighting hinder stable texture fusion; and neural rendering typically needs expensive offline optimization, violating edge-side streaming constraints. We propose ParkingTwin, a training-free, lightweight system for online streaming 3D reconstruction. First, OSM-prior-driven geometric construction uses OpenStreetMap semantic topology to directly generate a metric-consistent TSDF, replacing blind geometric search with deterministic mapping and avoiding costly optimization. Second, geometry-aware dynamic filtering employs a quad-modal constraint field (normal/height/depth consistency) to reject moving vehicles and transient occlusions in real time. Third, illumination-robust fusion in CIELAB decouples luminance and chromaticity via adaptive L-channel weighting and depth-gradient suppression, reducing seams under abrupt lighting changes. ParkingTwin runs at 30+ FPS on an entry-level GTX 1660. On a 68,000 m^2 real-world dataset, it achieves SSIM 0.87 (+16.0%), delivers about 15x end-to-end speedup, and reduces GPU memory by 83.3% compared with state-of-the-art 3D Gaussian Splatting (3DGS) that typically requires high-end GPUs (RTX 4090D). The system outputs explicit triangle meshes compatible with Unity/Unreal digital-twin pipelines. Project page: https://mihoutao-liu.github.io/ParkingTwin/

cs.CV↗