arXiv subjects

Yue Wang

Publications and source records attributed to Yue Wang.

At least 289 records · Page 16Linked to original sources

arXiv2025

RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services

As a primary medium for modern information dissemination, social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement. Recently, the development of large language models (LLMs) has offered potential solutions but existing studies focus on isolated tasks, which not only encounter diminishing benefit from the data scaling within individual scenarios but also fail to flexibly adapt to diverse real-world context. To address these challenges, we introduce RedOne, a domain-specific LLM designed to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for the SNS. RedOne was developed through a three-stage training strategy consisting of continue pretraining, supervised fine-tuning, and preference optimization, using a large-scale real-world dataset. Through extensive experiments, RedOne maintains strong general capabilities, and achieves an average improvement up to 14.02% across 8 major SNS tasks and 7.56% in SNS bilingual evaluation benchmark, compared with base models. Furthermore, through online testing, RedOne reduced the exposure rate in harmful content detection by 11.23% and improved the click page rate in post-view search by 14.95% compared with single-tasks finetuned baseline models. These results establish RedOne as a robust domain-specific LLM for SNS, demonstrating excellent generalization across various tasks and promising applicability in real-world scenarios.

cs.LG↗

arXiv2025

EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework

Recent advances in reinforcement learning (RL) have significantly enhanced the reasoning capabilities of large language models (LLMs). Group Relative Policy Optimization (GRPO), a lightweight variant of Proximal Policy Optimization (PPO), improves efficiency but suffers from limited exploration and training instability, limiting its effectiveness on complex reasoning tasks. To address these challenges, we introduce EFRame, an Exploration-Filter-Replay framework that augments GRPO across three dimensions: additional rollouts enable deeper and more targeted exploration, online filtering removes low-quality samples to stabilize gradients and accelerate training, and experience replay amplifies rare yet informative trajectories for stable convergence. This unified framework establishes a principled training cycle that balances exploration, efficiency, and stability. Experiments on diverse reasoning benchmarks demonstrate that EFRame achieves consistent gains, including a 37.9\% relative improvement on Geometry3K over GRPO. EFRame further supports fine-grained sample categorization and precise entropy control, highlighting it as a robust solution for advancing deeper reasoning in LLMs. Our code is available at https://github.com/597358816/EFRame.

cs.LG↗

arXiv2025

Robot Learning from Any Images

We introduce RoLA, a framework that transforms any in-the-wild image into an interactive, physics-enabled robotic environment. Unlike previous methods, RoLA operates directly on a single image without requiring additional hardware or digital assets. Our framework democratizes robotic data generation by producing massive visuomotor robotic demonstrations within minutes from a wide range of image sources, including camera captures, robotic datasets, and Internet images. At its core, our approach combines a novel method for single-view physical scene recovery with an efficient visual blending strategy for photorealistic data collection. We demonstrate RoLA's versatility across applications like scalable robotic data generation and augmentation, robot learning from Internet images, and single-image real-to-sim-to-real systems for manipulators and humanoids. Video results are available at https://sihengz02.github.io/RoLA .

cs.RO↗

arXiv2025

ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning

Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks. While recent advances in general motion tracking (GMT) have enabled humanoids to reproduce diverse human motions, these policies lack the precision and object awareness required for loco-manipulation. To this end, we introduce ResMimic, a two-stage residual learning framework for precise and expressive humanoid control from human motion data. First, a GMT policy, trained on large-scale human-only motion, serves as a task-agnostic base for generating human-like whole-body movements. An efficient but precise residual policy is then learned to refine the GMT outputs to improve locomotion and incorporate object interaction. To further facilitate efficient training, we design (i) a point-cloud-based object tracking reward for smoother optimization, (ii) a contact reward that encourages accurate humanoid body-object interactions, and (iii) a curriculum-based virtual object controller to stabilize early training. We evaluate ResMimic in both simulation and on a real Unitree G1 humanoid. Results show substantial gains in task success, training efficiency, and robustness over strong baselines. Videos are available at https://resmimic.github.io/ .

cs.RO↗

arXiv2025

Break the ID-Language Barrier: An Adaption Framework for LLM-based Sequential Recommendation

The recent breakthrough of large language models (LLMs) in natural language processing has sparked exploration in recommendation systems, however, their limited domain-specific knowledge remains a critical bottleneck. Specifically, LLMs lack key pieces of information crucial for sequential recommendations, such as user behavior patterns. To address this critical gap, we propose IDLE-Adapter, a novel framework that integrates pre-trained ID embeddings, rich in domain-specific knowledge, into LLMs to improve recommendation accuracy. IDLE-Adapter acts as a bridge, transforming sparse user-item interaction data into dense, LLM-compatible representations through a Pre-trained ID Sequential Model, Dimensionality Alignment, Layer-wise Embedding Refinement, and Layer-wise Distribution Alignment. Furthermore, IDLE-Adapter demonstrates remarkable flexibility by seamlessly integrating ID embeddings from diverse ID-based sequential models and LLM architectures. Extensive experiments across various datasets demonstrate the superiority of IDLE-Adapter, achieving over 10\% and 20\% improvements in HitRate@5 and NDCG@5 metrics, respectively, compared to state-of-the-art methods.

cs.IR↗

arXiv2025

Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare

Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. However, the principles and values that guide these models when distributing scarce societal resources remain largely unexamined. To address this, we introduce the Social Welfare Function (SWF) Benchmark, a dynamic simulation environment where an LLM acts as a sovereign allocator, distributing tasks to a heterogeneous community of recipients. The benchmark is designed to create a persistent trade-off between maximizing collective efficiency (measured by Return on Investment) and ensuring distributive fairness (measured by the Gini coefficient). We evaluate 20 state-of-the-art LLMs and present the first leaderboard for social welfare allocation. Our findings reveal three key insights: (i) A model's general conversational ability, as measured by popular leaderboards, is a poor predictor of its allocation skill. (ii) Most LLMs exhibit a strong default utilitarian orientation, prioritizing group productivity at the expense of severe inequality. (iii) Allocation strategies are highly vulnerable, easily perturbed by output-length constraints and social-influence framing. These results highlight the risks of deploying current LLMs as societal decision-makers and underscore the need for specialized benchmarks and targeted alignment for AI governance.

cs.CL↗

arXiv2025

Ultrasensitive Alzheimer's Disease Biomarker Detection with Nanopillar Photonic Crystal Biosensors

The recent development of drugs able to mitigate neurodegenerative diseases has created an urgent need for novel diagnostics. Although biomarker detection directly in patients' blood is now possible, low-cost point-of-care tests remain a challenge, because relevant biomarkers, especially amyloid-β(A$β$) peptides, are small, they occur at very low concentrations, and detecting a single marker is insufficient. Here, we introduce an optical biosensor based on a nanopillar structure that employs a gold nanoparticle amplification strategy. The sensor is able to detect 20 pg/ml of A$β$42 and A$β$40 in undiluted serum, which is the clinically required level. We also show the detection of the A$β$42 and A$β$40 peptides in the same channel, which is highly relevant for assessing disease progress and opens a route towards multiplexing. Alongside their simplicity and portability, these nanotechnology innovations make a major contribution to the ability to detect and monitor the progression of neurodegenerative diseases such as Alzheimer's.

physics.optics↗

arXiv2025

Highly robust factored principal component analysis for matrix-valued outlier accommodation and explainable detection via matrix minimum covariance determinant

Principal component analysis (PCA) is a classical and widely used method for dimensionality reduction, with applications in data compression, computer vision, pattern recognition, and signal processing. However, PCA is designed for vector-valued data and encounters two major challenges when applied to matrix-valued data with heavy-tailed distributions or outliers: (1) vectorization disrupts the intrinsic matrix structure, leading to information loss and the curse of dimensionality, and (2) PCA is highly sensitive to outliers. Factored PCA (FPCA) addresses the first issue through probabilistic modeling, using a matrix normal distribution that explicitly represents row and column covariances via a separable covariance structure, thereby preserving the two-way dependency and matrix form of the data. Building on FPCA, we propose highly robust FPCA (HRFPCA), a robust extension that replaces maximum likelihood estimators with the matrix minimum covariance determinant (MMCD) estimators. This modification enables HRFPCA to retain FPCA's ability to model matrix-valued data while achieving a breakdown point close to 50\%, substantially improving resistance to outliers. Furthermore, HRFPCA produces the score--orthogonal distance analysis (SODA) plot, which effectively visualizes and classifies matrix-valued outliers. Extensive simulations and real-data analyses demonstrate that HRFPCA consistently outperforms competing methods in robustness and outlier detection, underscoring its effectiveness and broad applicability.

stat.ME↗

arXiv2025

BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs

The rise of Large Language Models (LLMs) is reshaping multimodel models, with speech synthesis being a prominent application. However, existing approaches often underutilize the linguistic intelligence of these models, typically failing to leverage their powerful instruction-following capabilities. This limitation hinders the model's ability to follow text instructions for controllable Text-to-Speech~(TTS). To address this, we propose a new paradigm inspired by ``operationalism'' that decouples instruction understanding from speech generation. We introduce BatonVoice, a framework where an LLM acts as a ``conductor'', understanding user instructions and generating a textual ``plan'' -- explicit vocal features (e.g., pitch, energy). A separate TTS model, the ``orchestra'', then generates the speech from these features. To realize this component, we develop BatonTTS, a TTS model trained specifically for this task. Our experiments demonstrate that BatonVoice achieves strong performance in controllable and emotional speech synthesis, outperforming strong open- and closed-source baselines. Notably, our approach enables remarkable zero-shot cross-lingual generalization, accurately applying feature control abilities to languages unseen during post-training. This demonstrates that objectifying speech into textual vocal features can more effectively unlock the linguistic intelligence of LLMs.

cs.CL↗

arXiv2025

QWENDY: Gene Regulatory Network Inference by Quadruple Covariance Matrices

Knowing gene regulatory networks (GRNs) is important for understanding various biological mechanisms. In this paper, we present a method, QWENDY, that uses single-cell gene expression data measured at four time points to infer GRNs. Based on a linear gene expression model, it solves the transformation of the covariance matrices. Unlike its predecessor WENDY, QWENDY avoids solving a non-convex optimization problem and produces a unique solution. We test the performance of QWENDY on three experimental data sets and two synthetic data sets. Compared to previously tested methods on the same data sets, QWENDY ranks the first on experimental data, although it does not perform well on synthetic data.

q-bio.MN↗

arXiv2025

Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback

Generating human-like and adaptive trajectories is essential for autonomous driving in dynamic environments. While generative models have shown promise in synthesizing feasible trajectories, they often fail to capture the nuanced variability of personalized driving styles due to dataset biases and distributional shifts. To address this, we introduce TrajHF, a human feedback-driven finetuning framework for generative trajectory models, designed to align motion planning with diverse driving styles. TrajHF incorporates multi-conditional denoiser and reinforcement learning with human feedback to refine multi-modal trajectory generation beyond conventional imitation learning. This enables better alignment with human driving preferences while maintaining safety and feasibility constraints. TrajHF achieves performance comparable to the state-of-the-art on NavSim benchmark. TrajHF sets a new paradigm for personalized and adaptable trajectory generation in autonomous driving.

cs.RO↗

arXiv2025

The relationship between the structural transitions of DMPG membranes and the melting process, and their interaction with water

During the melting transition of dimyristoyl phosphatidylglycerol (DMPG), the order of the lipid chains and the three-dimensional, vesicular structural arrangement change simultaneously. These changes result in peculiar heat capacity profiles extended over a broad temperature range with seven $c_p$-maxima. Here, we present calorimetric, viscosity, and volume expansion coefficient data at various ionic strengths and charges. We propose a simple theory that explains the calorimetric data in terms of the coexistence of two membrane geometries, both of which can melt. During the transition, the equilibrium between these two geometries changes cooperatively. This equilibrium depends on the interactions between the membranes and the solvent, on the membrane's charge and the ionic strength of the buffer. Solvent interactions also contribute to the volume change of the membrane phases. Unlike uncharged membranes, we find that enthalpy changes are no longer proportional to volume changes. Therefore, the pressure dependence of the calorimetric profiles differs from that of uncharged membranes. Our theory explains the pressure dependence of calorimetric profiles qualitatively and quantitatively. Furthermore, we demonstrate that the same theory can be used to describe pretransition and ripple formation in phosphatidylcholines. A key takeaway from this article is that solvent molecules (e.g., H2O) are part of the membrane and, in the case of DMPG, water cannot be considered a separate phase.

physics.bio-ph↗

arXiv2025

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language Models (VLMs) to interpret and interact with complex real-world environments. However, these methods remain constrained by the limitations of imitation learning, which struggles to inherently encode physical rules during training. Existing approaches often rely on complex rule-based post-refinement, employ reinforcement learning that remains largely limited to simulation, or utilize diffusion guidance that requires computationally expensive gradient calculations. To address these challenges, we introduce ReflectDrive, a novel learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion. We first discretize the two-dimensional driving space to construct an action codebook, enabling the use of pre-trained Diffusion Language Models for planning tasks through fine-tuning. Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient computation. Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors. Based on this, we apply local search methods to identify unsafe tokens and determine feasible solutions, which then serve as safe anchors for inpainting-based regeneration. Evaluated on the NAVSIM benchmark, ReflectDrive demonstrates significant advantages in safety-critical trajectory generation, offering a scalable and reliable solution for autonomous driving systems.

cs.RO↗

arXiv2025

Multi-Worker Selection based Distributed Swarm Learning for Edge IoT with Non-i.i.d. Data

Recent advances in distributed swarm learning (DSL) offer a promising paradigm for edge Internet of Things. Such advancements enhance data privacy, communication efficiency, energy saving, and model scalability. However, the presence of non-independent and identically distributed (non-i.i.d.) data pose a significant challenge for multi-access edge computing, degrading learning performance and diverging training behavior of vanilla DSL. Further, there still lacks theoretical guidance on how data heterogeneity affects model training accuracy, which requires thorough investigation. To fill the gap, this paper first study the data heterogeneity by measuring the impact of non-i.i.d. datasets under the DSL framework. This then motivates a new multi-worker selection design for DSL, termed M-DSL algorithm, which works effectively with distributed heterogeneous data. A new non-i.i.d. degree metric is introduced and defined in this work to formulate the statistical difference among local datasets, which builds a connection between the measure of data heterogeneity and the evaluation of DSL performance. In this way, our M-DSL guides effective selection of multiple works who make prominent contributions for global model updates. We also provide theoretical analysis on the convergence behavior of our M-DSL, followed by extensive experiments on different heterogeneous datasets and non-i.i.d. data settings. Numerical results verify performance improvement and network intelligence enhancement provided by our M-DSL beyond the benchmarks.

cs.LG↗

arXiv2025

High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics

The complex nonlinear dynamics of hydraulic excavators, such as time delays and control coupling, pose significant challenges to achieving high-precision trajectory tracking. Traditional control methods often fall short in such applications due to their inability to effectively handle these nonlinearities, while commonly used learning-based methods require extensive interactions with the environment, leading to inefficiency. To address these issues, we introduce EfficientTrack, a trajectory tracking method that integrates model-based learning to manage nonlinear dynamics and leverages closed-loop dynamics to improve learning efficiency, ultimately minimizing tracking errors. We validate our method through comprehensive experiments both in simulation and on a real-world excavator. Comparative experiments in simulation demonstrate that our method outperforms existing learning-based approaches, achieving the highest tracking precision and smoothness with the fewest interactions. Real-world experiments further show that our method remains effective under load conditions and possesses the ability for continual learning, highlighting its practical applicability. For implementation details and source code, please refer to https://github.com/ZiqingZou/EfficientTrack.

cs.RO↗

arXiv2025

Toward Embodiment Equivariant Vision-Language-Action Policy

Vision-language-action policies learn manipulation skills across tasks, environments and embodiments through large-scale pre-training. However, their ability to generalize to novel robot configurations remains limited. Most approaches emphasize model size, dataset scale and diversity while paying less attention to the design of action spaces. This leads to the configuration generalization problem, which requires costly adaptation. We address this challenge by formulating cross-embodiment pre-training as designing policies equivariant to embodiment configuration transformations. Building on this principle, we propose a framework that (i) establishes a embodiment equivariance theory for action space and policy design, (ii) introduces an action decoder that enforces configuration equivariance, and (iii) incorporates a geometry-aware network architecture to enhance embodiment-agnostic spatial reasoning. Extensive experiments in both simulation and real-world settings demonstrate that our approach improves pre-training effectiveness and enables efficient fine-tuning on novel robot embodiments. Our code is available at https://github.com/hhcaz/e2vla

cs.RO↗

arXiv2025

Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives

Generating regulatorily compliant Suspicious Activity Report (SAR) remains a high-cost, low-scalability bottleneck in Anti-Money Laundering (AML) workflows. While large language models (LLMs) offer promising fluency, they suffer from factual hallucination, limited crime typology alignment, and poor explainability -- posing unacceptable risks in compliance-critical domains. This paper introduces Co-Investigator AI, an agentic framework optimized to produce Suspicious Activity Reports (SARs) significantly faster and with greater accuracy than traditional methods. Drawing inspiration from recent advances in autonomous agent architectures, such as the AI Co-Scientist, our approach integrates specialized agents for planning, crime type detection, external intelligence gathering, and compliance validation. The system features dynamic memory management, an AI-Privacy Guard layer for sensitive data handling, and a real-time validation agent employing the Agent-as-a-Judge paradigm to ensure continuous narrative quality assurance. Human investigators remain firmly in the loop, empowered to review and refine drafts in a collaborative workflow that blends AI efficiency with domain expertise. We demonstrate the versatility of Co-Investigator AI across a range of complex financial crime scenarios, highlighting its ability to streamline SAR drafting, align narratives with regulatory expectations, and enable compliance teams to focus on higher-order analytical work. This approach marks the beginning of a new era in compliance reporting -- bringing the transformative benefits of AI agents to the core of regulatory processes and paving the way for scalable, reliable, and transparent SAR generation.

cs.AI↗

arXiv2025

UnIRe: Unsupervised Instance Decomposition for Dynamic Urban Scene Reconstruction

Reconstructing and decomposing dynamic urban scenes is crucial for autonomous driving, urban planning, and scene editing. However, existing methods fail to perform instance-aware decomposition without manual annotations, which is crucial for instance-level scene editing.We propose UnIRe, a 3D Gaussian Splatting (3DGS) based approach that decomposes a scene into a static background and individual dynamic instances using only RGB images and LiDAR point clouds. At its core, we introduce 4D superpoints, a novel representation that clusters multi-frame LiDAR points in 4D space, enabling unsupervised instance separation based on spatiotemporal correlations. These 4D superpoints serve as the foundation for our decomposed 4D initialization, i.e., providing spatial and temporal initialization to train a dynamic 3DGS for arbitrary dynamic classes without requiring bounding boxes or object templates.Furthermore, we introduce a smoothness regularization strategy in both 2D and 3D space, further improving the temporal stability.Experiments on benchmark datasets show that our method outperforms existing methods in decomposed dynamic scene reconstruction while enabling accurate and flexible instance-level editing, making it a practical solution for real-world applications.

cs.CV↗