arXiv subjects

Yu Wang

Publications and source records attributed to Yu Wang.

At least 397 records · Page 22Linked to original sources

arXiv2026

A Chromatographic Process Design and Optimization Platform Powered by Large Language Models: A Case Application on Extract of Ginkgo Biloba Leaf

Chromatographic separation technology has been widely applied in pharmaceutical, chemical, and food industries due to its high efficiency. However, traditional human-dependent chromatographic process development faces challenges such as reliance on expert experience, long development cycles, and labor intensity. ChromR, a large language model (LLM)-driven platform for chromatographic process design and optimization, is presented in this work. The platform integrates ChromLLM, a domain-specific LLM trained for chromatography, along with a multi-agent system and an automated chromatographic experimental device. The multi-agent system comprises four agents: domain knowledge answering, experimental design, experimental execution, and data analysis. ChromR enables automatic completion of the entire workflow-including initial process parameter recommendation, experimental design, automated execution, data analysis, and multi-objective optimization. By utilizing ChromR, dependency on expert knowledge is effectively reduced, while labor input and development time are significantly decreased. Chromatographic purification of the extract of Ginkgo biloba leaf (EGBL) was selected as a case study. ChromR successfully developed a chromatographic process within one week that meets multiple objectives, including fraction quality and production efficiency, reducing development time to approximately one-seventh of that required by the conventional paradigm. An intelligent, automated, and universally applicable new paradigm was established for chromatographic process development.

cs.MA↗

arXiv2026

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. We further introduce the GLM-4.6V series, open-source multimodal models with native tool use and a 128K context window. A brief overview is available at https://z.ai/blog/glm-4.6v. Code, models and more information are released at https://github.com/zai-org/GLM-V.

cs.CV↗

arXiv2025

Benchmark of Segmentation Techniques for Pelvic Fracture in CT and X-ray: Summary of the PENGWIN 2024 Challenge

The segmentation of pelvic fracture fragments in CT and X-ray images is crucial for trauma diagnosis, surgical planning, and intraoperative guidance. However, accurately and efficiently delineating the bone fragments remains a significant challenge due to complex anatomy and imaging limitations. The PENGWIN challenge, organized as a MICCAI 2024 satellite event, aimed to advance automated fracture segmentation by benchmarking state-of-the-art algorithms on these complex tasks. A diverse dataset of 150 CT scans was collected from multiple clinical centers, and a large set of simulated X-ray images was generated using the DeepDRR method. Final submissions from 16 teams worldwide were evaluated under a rigorous multi-metric testing scheme. The top-performing CT algorithm achieved an average fragment-wise intersection over union (IoU) of 0.930, demonstrating satisfactory accuracy. However, in the X-ray task, the best algorithm achieved an IoU of 0.774, which is promising but not yet sufficient for intra-operative decision-making, reflecting the inherent challenges of fragment overlap in projection imaging. Beyond the quantitative evaluation, the challenge revealed methodological diversity in algorithm design. Variations in instance representation, such as primary-secondary classification versus boundary-core separation, led to differing segmentation strategies. Despite promising results, the challenge also exposed inherent uncertainties in fragment definition, particularly in cases of incomplete fractures. These findings suggest that interactive segmentation approaches, integrating human decision-making with task-relevant information, may be essential for improving model reliability and clinical applicability.

eess.IV↗

arXiv2025

RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation

Reinforcement learning (RL) has demonstrated immense potential in advancing artificial general intelligence, agentic intelligence, and embodied intelligence. However, the inherent heterogeneity and dynamicity of RL workflows often lead to low hardware utilization and slow training on existing systems. In this paper, we present RLinf, a high-performance RL training system based on our key observation that the major roadblock to efficient RL training lies in system flexibility. To maximize flexibility and efficiency, RLinf is built atop a novel RL system design paradigm called macro-to-micro flow transformation (M2Flow), which automatically breaks down high-level, easy-to-compose RL workflows at both the temporal and spatial dimensions, and recomposes them into optimized execution flows. Supported by RLinf worker's adaptive communication capability, we devise context switching and elastic pipelining to realize M2Flow transformation, and a profiling-guided scheduling policy to generate optimal execution plans. Extensive evaluations on both reasoning RL and embodied RL tasks demonstrate that RLinf consistently outperforms state-of-the-art systems, achieving $1.07\times-2.43\times$ speedup in end-to-end training throughput.

cs.LG↗

arXiv2025

Learning Multi-Modal Mobility Dynamics for Generalized Next Location Recommendation

The precise prediction of human mobility has produced significant socioeconomic impacts, such as location recommendations and evacuation suggestions. However, existing methods suffer from limited generalization capability: unimodal approaches are constrained by data sparsity and inherent biases, while multi-modal methods struggle to effectively capture mobility dynamics caused by the semantic gap between static multi-modal representation and spatial-temporal dynamics. Therefore, we leverage multi-modal spatial-temporal knowledge to characterize mobility dynamics for the location recommendation task, dubbed as \textbf{M}ulti-\textbf{M}odal \textbf{Mob}ility (\textbf{M}$^3$\textbf{ob}). First, we construct a unified spatial-temporal relational graph (STRG) for multi-modal representation, by leveraging the functional semantics and spatial-temporal knowledge captured by the large language models (LLMs)-enhanced spatial-temporal knowledge graph (STKG). Second, we design a gating mechanism to fuse spatial-temporal graph representations of different modalities, and propose an STKG-guided cross-modal alignment to inject spatial-temporal dynamic knowledge into the static image modality. Extensive experiments on six public datasets show that our proposed method not only achieves consistent improvements in normal scenarios but also exhibits significant generalization ability in abnormal scenarios.

cs.AI↗

arXiv2025

FUSCO: High-Performance Distributed Data Shuffling via Transformation-Communication Fusion

Large-scale Mixture-of-Experts (MoE) models rely on \emph{expert parallelism} for efficient training and inference, which splits experts across devices and necessitates distributed data shuffling to route each token to its assigned experts. However, existing communication libraries handle this shuffling poorly; its overhead can account for over half of end-to-end runtime. We present FUSCO, an MoE-friendly communication library that achieves efficient and lightweight data shuffling through fused data transformation and communication, based on the key observation that MoE's expert-major data layout conflicts with the device-major layout expected by communication operations. FUSCO captures the fine-grained data layout, which is then interpreted by a pipelined communication engine that performs the required shuffling efficiently along the communication path. Lightweight planning and load-balancing mechanisms complement the engine by eliminating redundant communication and dispersing traffic. Evaluations on representative benchmarks illustrate that FUSCO achieves up to 3.84$\times$ and 2.01$\times$ speedups over NCCL and DeepEP (the state-of-the-art MoE communication library), respectively. In end-to-end MoE tasks, compared to NCCL and DeepEP, FUSCO reduces the training latency by 1.17-1.39$\times$ and 1.10-1.19$\times$, and lowers the first-token generation latency in inference by 1.09-1.25$\times$ and 1.06-1.16$\times$.

cs.DC↗

arXiv2025

HistoWAS: A Pathomics Framework for Large-Scale Feature-Wide Association Studies of Tissue Topology and Patient Outcomes

High-throughput "pathomic" analysis of Whole Slide Images (WSIs) offers new opportunities to study tissue characteristics and for biomarker discovery. However, the clinical relevance of the tissue characteristics at the micro- and macro-environment level is limited by the lack of tools that facilitate the measurement of the spatial interaction of individual structure characteristics and their association with clinical parameters. To address these challenges, we introduce HistoWAS (Histology-Wide Association Study), a computational framework designed to link tissue spatial organization to clinical outcomes. Specifically, HistoWAS implements (1) a feature space that augments conventional metrics with 30 topological and spatial features, adapted from Geographic Information Systems (GIS) point pattern analysis, to quantify tissue micro-architecture; and (2) an association study engine, inspired by Phenome-Wide Association Studies (PheWAS), that performs mass univariate regression for each feature with statistical correction. As a proof of concept, we applied HistoWAS to analyze a total of 102 features (72 conventional object-level features and our 30 spatial features) using 385 PAS-stained WSIs from 206 participants in the Kidney Precision Medicine Project (KPMP). The code and data have been released to https://github.com/hrlblab/histoWAS.

cs.CV↗

arXiv2025

Trion ordering in the attractive three-color Hubbard model on a $π$-flux square lattice

Ultracold multicomponent fermions (atoms/molecules) loaded in optical lattices provide an ideal platform for simulating SU($N$) Hubbard models that host unconventional many-body quantum states beyond SU(2). A prime example is the attractive three-color Hubbard model, in which trion states emerge at strong coupling. Nevertheless, much of its trion ordering on two-dimensional lattices remains uncertain. Here, we employ the determinant quantum Monte Carlo (DQMC) method to simulate the attractive three-color Hubbard model on a $π$-flux square lattice at half filling. We show that color-dependent attractive interaction can induce coexisting charge density wave (CDW) and Néel ordered states in the three-color $π$-flux Hubbard model. In particular, enhanced charge fluctuations (cf. honeycomb lattice) cause much stronger Néel ordering on the $π$-flux square lattice. The coexisting charge and Néel orders survive up to a melting temperature, at which they vanish simultaneously. The Ginzburg-Landau (GL) analysis on the coexistence of CDW and Néel orders demonstrates how color-dependent Hubbard interactions stabilize coexisting orders from the perspective of GL free energy principle.

cond-mat.quant-gas↗

arXiv2025

MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Image

Whole-slide images (WSIs) are an important data modality in computational pathology, yet their gigapixel resolution and lack of fine-grained annotations challenge conventional deep learning models. Multiple instance learning (MIL) offers a solution by treating each WSI as a bag of patch-level instances, but effectively modeling ultra-long sequences with rich spatial context remains difficult. Recently, Mamba has emerged as a promising alternative for long sequence learning, scaling linearly to thousands of tokens. However, despite its efficiency, it still suffers from limited spatial context modeling and memory decay, constraining its effectiveness to WSI analysis. To address these limitations, we propose MambaMIL+, a new MIL framework that explicitly integrates spatial context while maintaining long-range dependency modeling without memory forgetting. Specifically, MambaMIL+ introduces 1) overlapping scanning, which restructures the patch sequence to embed spatial continuity and instance correlations; 2) a selective stripe position encoder (S2PE) that encodes positional information while mitigating the biases of fixed scanning orders; and 3) a contextual token selection (CTS) mechanism, which leverages supervisory knowledge to dynamically enlarge the contextual memory for stable long-range modeling. Extensive experiments on 20 benchmarks across diagnostic classification, molecular prediction, and survival analysis demonstrate that MambaMIL+ consistently achieves state-of-the-art performance under three feature extractors (ResNet-50, PLIP, and CONCH), highlighting its effectiveness and robustness for large-scale computational pathology

cs.CV↗

arXiv2025

Automatic Reward Shaping from Multi-Objective Human Heuristics

Designing effective reward functions remains a central challenge in reinforcement learning, especially in multi-objective environments. In this work, we propose Multi-Objective Reward Shaping with Exploration (MORSE), a general framework that automatically combines multiple human-designed heuristic rewards into a unified reward function. MORSE formulates the shaping process as a bi-level optimization problem: the inner loop trains a policy to maximize the current shaped reward, while the outer loop updates the reward function to optimize task performance. To encourage exploration in the reward space and avoid suboptimal local minima, MORSE introduces stochasticity into the shaping process, injecting noise guided by task performance and the prediction error of a fixed, randomly initialized neural network. Experimental results in MuJoCo and Isaac Sim environments show that MORSE effectively balances multiple objectives across various robotic tasks, achieving task performance comparable to those obtained with manually tuned reward functions.

cs.LG↗

arXiv2025

GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection

Active Speaker Detection (ASD) aims to identify who is currently speaking in each frame of a video. Most state-of-the-art approaches rely on late fusion to combine visual and audio features, but late fusion often fails to capture fine-grained cross-modal interactions, which can be critical for robust performance in unconstrained scenarios. In this paper, we introduce GateFusion, a novel architecture that combines strong pretrained unimodal encoders with a Hierarchical Gated Fusion Decoder (HiGate). HiGate enables progressive, multi-depth fusion by adaptively injecting contextual features from one modality into the other at multiple layers of the Transformer backbone, guided by learnable, bimodally-conditioned gates. To further strengthen multimodal learning, we propose two auxiliary objectives: Masked Alignment Loss (MAL) to align unimodal outputs with multimodal predictions, and Over-Positive Penalty (OPP) to suppress spurious video-only activations. GateFusion establishes new state-of-the-art results on several challenging ASD benchmarks, achieving 77.8% mAP (+9.4%), 86.1% mAP (+2.9%), and 96.1% mAP (+0.5%) on Ego4D-ASD, UniTalk, and WASD benchmarks, respectively, and delivering competitive performance on AVA-ActiveSpeaker. Out-of-domain experiments demonstrate the generalization of our model, while comprehensive ablations show the complementary benefits of each component.

cs.CV↗

arXiv2025

Dynamic stacking ensemble learning with investor knowledge representations for stock market index prediction based on multi-source financial data

The patterns of different financial data sources vary substantially, and accordingly, investors exhibit heterogeneous cognition behavior in information processing. To capture different patterns, we propose a novel approach called the two-stage dynamic stacking ensemble model based on investor knowledge representations, which aims to effectively extract and integrate the features from multi-source financial data. In the first stage, we identify different financial data property from global stock market indices, industrial indices, and financial news based on the perspective of investors. And then, we design appropriate neural network architectures tailored to these properties to generate effective feature representations. Based on learned feature representations, we design multiple meta-classifiers and dynamically select the optimal one for each time window, enabling the model to effectively capture and learn the distinct patterns that emerge across different temporal periods. To evaluate the performance of the proposed model, we apply it to predicting the daily movement of Shanghai Securities Composite index, SZSE Component index and Growth Enterprise index in Chinese stock market. The experimental results demonstrate the effectiveness of our model in improving the prediction performance. In terms of accuracy metric, our approach outperforms the best competing models by 1.42%, 7.94%, and 7.73% on the SSEC, SZEC, and GEI indices, respectively. In addition, we design a trading strategy based on the proposed model. The economic results show that compared to the competing trading strategies, our strategy delivers a superior performance in terms of the accumulated return and Sharpe ratio.

cs.CE↗

arXiv2025

Data-driven Supervisory Control under Attacks via Spectral Learning

The technological advancements facilitating the rapid development of cyber-physical systems (CPS) also render such systems vulnerable to cyber attacks with devastating effects. Supervisory control is a commonly used control method to neutralize attacks on CPS. The supervisor strives to confine the (symbolic) paths of the system to a desired language via sensors and actuators in a closed control loop, even when attackers can manipulate the symbols received by the sensors and actuators. Currently, supervisory control methods face limitations when effectively identifying and mitigating unknown, broad-spectrum attackers. In order to capture the behavior of broad-spectrum attacks on both sensing and actuation channels we model the plant, supervisors, and attackers with finite-state transducers (FSTs). Our general method for addressing unknown attackers involves constructing FST models of the attackers from spectral analysis of their input and output symbol sequences recorded from a history of attack behaviors observed in a supervisory control loop. To construct these FST models, we devise a novel learning method based on the recorded history of attack behaviors. A supervisor is synthesized using such models to neutralize the attacks.

eess.SY↗

arXiv2025

ProEx: A Unified Framework Leveraging Large Language Model with Profile Extrapolation for Recommendation

The powerful text understanding and generation capabilities of large language models (LLMs) have brought new vitality to general recommendation with implicit feedback. One possible strategy involves generating a unique user (or item) profile from historical interaction data, which is then mapped to a semantic representation in the language space. However, a single-instance profile may be insufficient to comprehensively capture the complex intentions behind a user's interacted items. Moreover, due to the inherent instability of LLMs, a biased or misinterpreted profile could even undermine the original recommendation performance. Consequently, an intuitive solution is to generate multiple profiles for each user (or item), each reflecting a distinct aspect of their characteristics. In light of this, we propose a unified recommendation framework with multi-faceted profile extrapolation (ProEx) in this paper. By leveraging chain-of-thought reasoning, we construct multiple distinct profiles for each user and item. These new profiles are subsequently mapped into semantic vectors, extrapolating from the position of the original profile to explore a broader region of the language space. Subsequently, we introduce the concept of environments, where each environment represents a possible linear combination of all profiles. The differences across environments are minimized to reveal the inherent invariance of user preferences. We apply ProEx to three discriminative methods and three generative methods, and conduct extensive experiments on three datasets. The experimental results demonstrate that ProEx significantly enhances the performance of these base recommendation models.

cs.IR↗

arXiv2025

Advancing Identification method of Gamma-Ray Bursts with Data and Feature Enhancement

Gamma-ray bursts (GRBs) are challenging to identify due to their transient nature, complex temporal profiles, and limited observational datasets. We address this with a one-dimensional convolutional neural network integrated with an Adaptive Frequency Feature Enhancement module and physics-informed data augmentation. Our framework generates 100,000 synthetic GRB samples, expanding training data diversity and volume while preserving physical fidelity-especially for low-significance events. The model achieves 97.46% classification accuracy, outperforming all tested variants with conventional enhancement modules, highlighting enhanced domain-specific feature capture. Feature visualization shows model focuses on deep-seated morphological features and confirms the capability of extracting physically meaningful burst characteristics. Dimensionality reduction and clustering reveal GRBs with similar morphologies or progenitor origins cluster in the feature space, linking learned features to physical properties. This perhaps offers a novel diagnostic tool for identifying kilonova- and supernova-associated GRB candidates, establishing criteria to enhance multi-messenger early-warning systems. The framework aids current time-domain surveys, generalizes to other rare transients, and advances automated detection in large-volume observational data.

astro-ph.HE↗

arXiv2025

SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation

Large autoregressive models can generate high-quality, high-resolution images but suffer from slow generation speed, because these models require hundreds to thousands of sequential forward passes for next-token prediction during inference. To accelerate autoregressive text-to-image generation, we propose Speculative Jacobi Decoding++ (SJD++), a training-free probabilistic parallel decoding algorithm. Unlike traditional next-token prediction, SJD++ performs multi-token prediction in each forward pass, drastically reducing generation steps. Specifically, it integrates the iterative multi-token prediction mechanism from Jacobi decoding, with the probabilistic drafting-and-verification mechanism from speculative sampling. More importantly, for further acceleration, SJD++ reuses high-confidence draft tokens after each verification phase instead of resampling them all. We conduct extensive experiments on several representative autoregressive text-to-image generation models and demonstrate that SJD++ achieves $2\times$ to $3\times$ inference latency reduction and $2\times$ to $7\times$ step compression, while preserving visual quality with no observable degradation.

cs.CV↗

arXiv2025

Structured Light at the Extreme: Harnessing Spatiotemporal Control for High-Field Laser-Matter Interactions

This review charts the emerging paradigm of intelligent structured light for high-field laser-matter interactions, where the precise spatiotemporal and vectorial control of light is a critical degree of freedom. We outline a transformative framework built upon three synergistic pillars. First, we survey the advanced electromagnetic toolkit, moving beyond conventional spatial light modulators to include robust static optics and the promising frontier of plasma light modulators. Second, we detail the optimization engine for this high-dimensional design space, focusing on physics-informed digital twins and AI-driven inverse design to automate the discovery of optimal light structures. Finally, we explore the groundbreaking applications enabled by this integrated approach, including programmable electron beams, orbital-angular-momentum-carrying γ-rays, compact THz accelerators, and robust communications. The path forward necessitates overcoming grand challenges in material science, real-time adaptive control at MHz rates, and the extension of these principles to the quantum realm. This review serves as a call to action for a coordinated, interdisciplinary effort to command, rather than merely observe, light-matter interactions at the extreme.

physics.optics↗

arXiv2025

Complete characterization of beam deflection based on double weak value amplification system

The precise measurement of spatial attitude parameters is critical for applications in inertial navigation, industrial monitoring, instrument calibration, quantum metrology, etc. In this work, we theoretically investigate and experimentally realize the simultaneous measurement of the yaw and pitch angles using a Hermite-Gaussian-postselected double weak value system integrated with two sets of high-order-mode balanced homodyne detections, thereby achieving a complete characterization of the beam deflection. Signals of the yaw and pitch angles that are involved in TEM$_{10}$ and TEM$_{01}$ modes output from two dark ports of the system can be measured independently. As a result, the obtained minimum measurable yaw and pitch angles of beam deflection are 83 prad and 89 prad, respectively. Meanwhile, the corresponding displacements are 0.79 pm and 0.85 pm, respectively. This work expands the beam deflection measurement to two dimensions, which provides a new insight for future high-precision multi-parameter spatial precise detection.

quant-ph↗