Searcharxiv⌕ Search

arXiv subjects

Yunhuai Liu

Publications and source records attributed to Yunhuai Liu.

At least 19 recordsLinked to original sources
arXiv2026

Med-R$^3$: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning

In medical scenarios, effectively retrieving external knowledge and leveraging it for rigorous logical reasoning is of significant importance. Despite their potential, existing work has predominantly focused on enhancing either retrieval or reasoning capabilities of the models in isolation, with little attention given to their joint optimization, which leads to limited coordination between the two processes. Additionally, current methods rely heavily on supervised fine-tuning (SFT), which can cause models to memorize existing problem-solving pathways, thereby restricting their generalization ability when confronted with novel problem contexts. Furthermore, while some studies have explored to improve retrieval-augmented reasoning in general domains via reinforcement learning, their reward function designs do not adequately capture the specific demands of the medical domain. To address these challenges, we introduce **Med-R$^3$**, a **Med**ical **R**etrieval-augmented **R**easoning framework driven by progressive **R**einforcement learning. In this framework, we first develop the model's ability to perform logical reasoning over medical problems. Subsequently, on the basis of this foundation, we adaptively optimize the retrieval capability to better align with the characteristics of knowledge corpus and external information utilization throughout the reasoning process. Finally, we conduct joint optimization of the model's retrieval and reasoning coordination. Extensive experiments indicate that **Med-R$^3$** could achieve state-of-the-art performances, with Qwen3-8B + Med-R$^3$ surpassing closed-sourced GPT-4o-mini by 12.22% at a comparable parameter scale, while Qwen2.5-14B augmented with \ours shows a more substantial gain of 16.31%.

cs.CL↗
arXiv2026

PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning

Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces challenges when deploying LLMs in agent-based environments. The widely adopted agent paradigm ReAct centers on integrating single-step reasoning with immediate action execution, which limits its effectiveness in complex tasks requiring long-term strategic planning. Furthermore, the coordination between the planner and executor during problem-solving is also a critical factor to consider in agent design. Additionally, current approaches predominantly rely on supervised fine-tuning, which often leads models to memorize established task completion trajectories, thereby restricting their generalization ability when confronted with novel problem contexts. To address these challenges, we introduce an adaptive global plan-based agent paradigm AdaPlan, aiming to synergize high-level explicit guidance with execution to support effective long-horizon decision-making. Based on the proposed paradigm, we further put forward PilotRL, a global planning-guided training framework for LLM agents driven by progressive reinforcement learning. We first develop the model's ability to follow explicit guidance from global plans when addressing agent tasks. Subsequently, based on this foundation, we focus on optimizing the quality of generated plans. Finally, we conduct joint optimization of the model's planning and execution coordination. Experiments indicate that PilotRL could achieve state-of-the-art performances, with LLaMA3.1-8B-Instruct + PilotRL surpassing closed-sourced GPT-4o by 3.60%, while showing a more substantial gain of 55.78% comparing to GPT-4o-mini at a comparable parameter scale.

cs.CL↗
arXiv2026

REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs

Large Language Models (LLMs) are increasingly expected to interact with users over long time horizons. However, due to their finite context window, LLMs cannot retain all past interactions, making long-term memory management essential for storing, updating, and retrieving historical information beyond the context limit. Although recent memory systems attempt to address this issue by storing historical information externally, existing approaches suffer from three key limitations: flat text-based memory organizations fail to capture explicit relations among memories, structured memory systems often destructively overwrite evolving facts, and current retrieval mechanisms remain query-agnostic and passive when evidence is incomplete. REAL constructs long-term conversational memory as a temporal and confidence-aware directed property graph, where each atomic fact is represented with entities, relations, valid-time intervals, confidence scores, and exploration intent labels. During memory construction, REAL adopts a non-destructive temporal update strategy that preserves parallel fact versions and their validity intervals, enabling faithful tracking of fact evolution. During retrieval, REAL anchors query-relevant root entities, decouples their exploration intents, and performs semantic evaluator-guided hybrid beam search to extract compact memory subgraphs. It further incorporates counterfactual inference to repair unreliable retrieval states and recover missing memory evidence through implicit logical relations. Comprehensive experiments demonstrate that REAL substantially improves long-term memory performance over flat-text, graph-based, and existing memory baselines, achieving an average improvement of 22.72\%.

cs.CL↗
arXiv2026

Towards Efficient and Exact Forgetting Services in Pre-Trained-Model-based Continual Learning

In Continual Learning (CL), using a Pre-Trained Model (PTM) as the feature extractor has become a popular practice. Accompanied by analytic classifiers, the PTM-based methods have achieved state-of-the-art performance in CL, in pursuit of the non-forgetting goal. Meanwhile, actively forgetting specific knowledge acquired during the CL phase is also essential in most service construction paradigms, for example, Mobile Crowd Sensing (MCS), where mobile edge nodes continuously collect sensory data and demand not only non-forgetting adaptation but also specific knowledge forgetting for privacy preservation. Thus, a unique problem, called Continual Unlearning (CU), arises when the forgetting requests show sequentially in CL. However, existing unlearning methods focus on single-shot joint forgetting and prove highly inadequate when applied to CU, including (1) violating the historical data privacy in CL and (2) vulnerably being overwhelmed or degraded with adversarially frequent requests. To handle the challenges of CU, we propose a gradient-free approach, called Analytic Continual Unlearning (ACU), for efficient and exact forgetting with historical data privacy preservation in PTM-based CL. In response to each unlearning request, our ACU recursively derives the analytical (i.e., closed-form) solutions via least squares in an interpretable manner. By meticulous design, our ACU is compatible with both sample-level and class-level unlearning requests. The theoretical and experimental evaluations validate our ACU's superiority in unlearning effectiveness, model fidelity, and system efficiency.

cs.LG↗
arXiv2026

MAVEN: A Mesh-Aware Volumetric Encoding Network for Simulating 3D Flexible Deformation

Deep learning-based approaches, particularly graph neural networks (GNNs), have gained prominence in simulating flexible deformations and contacts of solids, due to their ability to handle unstructured physical fields and nonlinear regression on graph structures. However, existing GNNs commonly represent meshes with graphs built solely from vertices and edges. These approaches tend to overlook higher-dimensional spatial features, e.g., 2D facets and 3D cells, from the original geometry. As a result, it is challenging to accurately capture boundary representations and volumetric characteristics, though this information is critically important for modeling contact interactions and internal physical quantity propagation, particularly under sparse mesh discretization. In this paper, we introduce MAVEN, a mesh-aware volumetric encoding network for simulating 3D flexible deformation, which explicitly models geometric mesh elements of higher dimension to achieve a more accurate and natural physical simulation. MAVEN establishes learnable mappings among 3D cells, 2D facets, and vertices, enabling flexible mutual transformations. Explicit geometric features are incorporated into the model to alleviate the burden of implicitly learning geometric patterns. Experimental results show that MAVEN consistently achieves state-of-the-art performance across established datasets and a novel metal stretch-bending task featuring large deformations and prolonged contacts.

cs.LG↗
arXiv2026

CAMMSR: Category-Guided Attentive Mixture of Experts for Multimodal Sequential Recommendation

The explosion of multimedia data in information-rich environments has intensified the challenges of personalized content discovery, positioning recommendation systems as an essential form of passive data management. Multimodal sequential recommendation, which leverages diverse item information such as text and images, has shown great promise in enriching item representations and deepening the understanding of user interests. However, most existing models rely on heuristic fusion strategies that fail to capture the dynamic and context-sensitive nature of user-modal interactions. In real-world scenarios, user preferences for modalities vary not only across individuals but also within the same user across different items or categories. Moreover, the synergistic effects between modalities-where combined signals trigger user interest in ways isolated modalities cannot-remain largely underexplored. To this end, we propose CAMMSR, a Category-guided Attentive Mixture of Experts model for Multimodal Sequential Recommendation. At its core, CAMMSR introduces a category-guided attentive mixture of experts (CAMoE) module, which learns specialized item representations from multiple perspectives and explicitly models inter-modal synergies. This component dynamically allocates modality weights guided by an auxiliary category prediction task, enabling adaptive fusion of multimodal signals. Additionally, we design a modality swap contrastive learning task to enhance cross-modal representation alignment through sequence-level augmentation. Extensive experiments on four public datasets demonstrate that CAMMSR consistently outperforms state-of-the-art baselines, validating its effectiveness in achieving adaptive, synergistic, and user-centric multimodal sequential recommendation.

cs.IR↗
arXiv2026

DeepAFL: Deep Analytic Federated Learning

Federated Learning (FL) is a popular distributed learning paradigm to break down data silo. Traditional FL approaches largely rely on gradient-based updates, facing significant issues about heterogeneity, scalability, convergence, and overhead, etc. Recently, some analytic-learning-based work has attempted to handle these issues by eliminating gradient-based updates via analytical (i.e., closed-form) solutions. Despite achieving superior invariance to data heterogeneity, these approaches are fundamentally limited by their single-layer linear model with a frozen pre-trained backbone. As a result, they can only achieve suboptimal performance due to their lack of representation learning capabilities. In this paper, to enable representable analytic models while preserving the ideal invariance to data heterogeneity for FL, we propose our Deep Analytic Federated Learning approach, named DeepAFL. Drawing inspiration from the great success of ResNet in gradient-based learning, we design gradient-free residual blocks in our DeepAFL with analytical solutions. We introduce an efficient layer-wise protocol for training our deep analytic models layer by layer in FL through least squares. Both theoretical analyses and empirical evaluations validate our DeepAFL's superior performance with its dual advantages in heterogeneity invariance and representation learning, outperforming state-of-the-art baselines by up to 5.68%-8.42% across three benchmark datasets.

cs.LG↗
arXiv2026

Neural Latent Arbitrary Lagrangian-Eulerian Grids for Fluid-Solid Interaction

Fluid-solid interaction (FSI) problems are fundamental in many scientific and engineering applications, yet effectively capturing the highly nonlinear two-way interactions remains a significant challenge. Most existing deep learning methods are limited to simplified one-way FSI scenarios, often assuming rigid and static solid to reduce complexity. Even in two-way setups, prevailing approaches struggle to capture dynamic, heterogeneous interactions due to the lack of cross-domain awareness. In this paper, we introduce \textbf{Fisale}, a data-driven framework for handling complex two-way \textbf{FSI} problems. It is inspired by classical numerical methods, namely the Arbitrary Lagrangian-Eulerian (\textbf{ALE}) method and the partitioned coupling algorithm. Fisale explicitly models the coupling interface as a distinct component and leverages multiscale latent ALE grids to provide unified, geometry-aware embeddings across domains. A partitioned coupling module (PCM) further decomposes the problem into structured substeps, enabling progressive modeling of nonlinear interdependencies. Compared to existing models, Fisale introduces a more flexible framework that iteratively handles complex dynamics of solid, fluid and their coupling interface on a unified representation, and enables scalable learning of complex two-way FSI behaviors. Experimentally, Fisale excels in three reality-related challenging FSI scenarios, covering 2D, 3D and various tasks. The code is available at \href{https://github.com/therontau0054/Fisale}.

cs.LG↗
arXiv2026

Can LLMs Handle WebShell Detection? Overcoming Detection Challenges with Behavioral Function-Aware Framework

WebShell attacks - where adversaries implant malicious scripts on web servers - remain a persistent threat. Prior machine-learning and deep-learning detectors typically depend on task-specific supervision and can be brittle under data scarcity, rapid concept drift, and out-of-distribution (OOD) deployment. Large language models (LLMs) have recently shown strong code understanding capabilities, but their reliability for WebShell detection remains unclear. We address this gap by (i) systematically evaluating seven LLMs (including GPT-4, LLaMA-3.1-70B, and Qwen-2.5 variants) against representative sequence- and graph-based baselines on 26.59K PHP scripts, and (ii) proposing Behavioral Function-Aware Detection (BFAD), a behavior-centric framework that adapts LLM inference to WebShell-specific execution patterns. BFAD anchors analysis on security-sensitive PHP functions via a Critical Function Filter, constructs compact LLM inputs with Context-Aware Code Extraction, and selects in-context demonstrations using Weighted Behavioral Function Profiling, which ranks examples by a behavior-weighted, function-level similarity. Empirically, we observe a consistent precision-recall asymmetry: larger LLMs often achieve high precision but miss attacks (lower recall), while smaller models exhibit the opposite tendency; moreover, off-the-shelf LLM prompting underperforms established detectors. BFAD substantially improves all evaluated LLMs, boosting F1 by 13.82% on average; notably, GPT-4, LLaMA-3.1-70B, and Qwen-2.5-Coder-14B exceed prior SOTA benchmarks, while Qwen-2.5-Coder-3B becomes competitive with traditional methods. Overall, our results clarify when LLMs succeed or fail on WebShell detection, provide a practical recipe, and highlight future directions for making LLM-based detection more reliable.

cs.CR↗
arXiv2026

DREAM: Dynamic Red-teaming across Environments for AI Models

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static, single-turn assessments that miss vulnerabilities from adaptive, long-chain attacks. To fill this gap, we introduce DREAM, a framework for systematic evaluation of LLM agents against dynamic, multi-stage attacks. At its core, DREAM uses a Cross-Environment Adversarial Knowledge Graph (CE-AKG) to maintain stateful, cross-domain understanding of vulnerabilities. This graph guides a Contextualized Guided Policy Search (C-GPS) algorithm that dynamically constructs attack chains from a knowledge base of 1,986 atomic actions across 349 distinct digital environments. Our evaluation of 12 leading LLM agents reveals a critical vulnerability: these attack chains succeed in over 70% of cases for most models, showing the power of stateful, cross-environment exploits. Through analysis of these failures, we identify two key weaknesses in current agents: contextual fragility, where safety behaviors fail to transfer across environments, and an inability to track long-term malicious intent. Our findings also show that traditional safety measures, such as initial defense prompts, are largely ineffective against attacks that build context over multiple interactions. To advance agent safety research, we release DREAM as a tool for evaluating vulnerabilities and developing more robust defenses.

cs.CR↗
arXiv2026

FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data

The scientific computation of large deformations in elastic-plastic solids is crucial in various manufacturing applications. Traditional numerical methods exhibit several inherent limitations, prompting Deep Learning (DL) as a promising alternative. The effectiveness of current DL techniques typically depends on the availability of high-quantity and high-accuracy datasets, which are yet difficult to obtain in large deformation problems. During the dataset construction process, a dilemma stands between data quantity and data accuracy, leading to suboptimal performance in the DL models. To address this challenge, we focus on a representative application of large deformations, the stretch bending problem, and propose FilDeep, a Fidelity-based Deep Learning framework for large Deformation of elastic-plastic solids. Our FilDeep aims to resolve the quantity-accuracy dilemma by simultaneously training with both low-fidelity and high-fidelity data, where the former provides greater quantity but lower accuracy, while the latter offers higher accuracy but in less quantity. In FilDeep, we provide meticulous designs for the practical large deformation problem. Particularly, we propose attention-enabled cross-fidelity modules to effectively capture long-range physical interactions across MF data. To the best of our knowledge, our FilDeep presents the first DL framework for large deformation problems using MF data. Extensive experiments demonstrate that our FilDeep consistently achieves state-of-the-art performance and can be efficiently deployed in manufacturing.

cs.AI↗
arXiv2025

Collaborate sim and real: Robot Bin Packing Learning in Real-world and Physical Engine

The 3D bin packing problem, with its diverse industrial applications, has garnered significant research attention in recent years. Existing approaches typically model it as a discrete and static process, while real-world applications involve continuous gravity-driven interactions. This idealized simplification leads to infeasible deployments (e.g., unstable packing) in practice. Simulations with physical engine offer an opportunity to emulate continuous gravity effects, enabling the training of reinforcement learning (RL) agents to address such limitations and improve packing stability. However, a simulation-to-reality gap persists due to dynamic variations in physical properties of real-world objects, such as various friction coefficients, elasticity, and non-uniform weight distributions. To bridge this gap, we propose a hybrid RL framework that collaborates with physical simulation with real-world data feedback. Firstly, domain randomization is applied during simulation to expose agents to a spectrum of physical parameters, enhancing their generalization capability. Secondly, the RL agent is fine-tuned with real-world deployment feedback, further reducing collapse rates. Extensive experiments demonstrate that our method achieves lower collapse rates in both simulated and real-world scenarios. Large-scale deployments in logistics systems validate the practical effectiveness, with a 35\% reduction in packing collapse compared to baseline methods.

cs.RO↗
arXiv2025

Language Models Resist Alignment: Evidence From Data Compression

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment process can be easily circumvented, whether intentionally or accidentally. Does alignment fine-tuning yield have robust effects on models, or are its impacts merely superficial? In this work, we make the first exploration of this phenomenon from both theoretical and empirical perspectives. Empirically, we demonstrate the $\mathbf{elasticity}$ of post-alignment models, i.e., the tendency to revert to the behavior distribution formed during the pre-training phase upon further fine-tuning. Leveraging compression theory, we formally deduce that fine-tuning disproportionately undermines alignment relative to pre-training, potentially by orders of magnitude. We validate the presence of elasticity through experiments on models of varying types and scales. Specifically, we find that model performance declines rapidly before reverting to the pre-training distribution, after which the rate of decline drops significantly. Furthermore, we further reveal that elasticity positively correlates with the increased model size and the expansion of pre-training data. Our findings underscore the need to address the inherent elasticity of LLMs to mitigate their resistance to alignment. The model weight and code are available at pku-lm-resist-alignment.github.io.

cs.CL↗
arXiv2025

CIARD: Cyclic Iterative Adversarial Robustness Distillation

Adversarial robustness distillation (ARD) aims to transfer both performance and robustness from teacher model to lightweight student model, enabling resilient performance on resource-constrained scenarios. Though existing ARD approaches enhance student model's robustness, the inevitable by-product leads to the degraded performance on clean examples. We summarize the causes of this problem inherent in existing methods with dual-teacher framework as: 1. The divergent optimization objectives of dual-teacher models, i.e., the clean and robust teachers, impede effective knowledge transfer to the student model, and 2. The iteratively generated adversarial examples during training lead to performance deterioration of the robust teacher model. To address these challenges, we propose a novel Cyclic Iterative ARD (CIARD) method with two key innovations: a. A multi-teacher framework with contrastive push-loss alignment to resolve conflicts in dual-teacher optimization objectives, and b. Continuous adversarial retraining to maintain dynamic teacher robustness against performance degradation from the varying adversarial examples. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that CIARD achieves remarkable performance with an average 3.53 improvement in adversarial defense rates across various attack scenarios and a 5.87 increase in clean sample accuracy, establishing a new benchmark for balancing model robustness and generalization. Our code is available at https://github.com/eminentgu/CIARD

cs.CV↗
arXiv2025

APFL: Analytic Personalized Federated Learning via Dual-Stream Least Squares

Personalized Federated Learning (PFL) has presented a significant challenge to deliver personalized models to individual clients through collaborative training. Existing PFL methods are often vulnerable to non-IID data, which severely hinders collective generalization and then compromises the subsequent personalization efforts. In this paper, to address this non-IID issue in PFL, we propose an Analytic Personalized Federated Learning (APFL) approach via dual-stream least squares. In our APFL, we use a foundation model as a frozen backbone for feature extraction. Subsequent to the feature extractor, we develop dual-stream analytic models to achieve both collective generalization and individual personalization. Specifically, our APFL incorporates a shared primary stream for global generalization across all clients, and a dedicated refinement stream for local personalization of each individual client. The analytical solutions of our APFL enable its ideal property of heterogeneity invariance, theoretically meaning that each personalized model remains identical regardless of how heterogeneous the data are distributed across all other clients. Empirical results across various datasets also validate the superiority of our APFL over state-of-the-art baselines, with advantages of at least 1.10%-15.45% in accuracy.

cs.LG↗
arXiv2025

FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions

Lately, Personalized Federated Learning (PFL) has emerged as a prevalent paradigm to deliver personalized models by collaboratively training while simultaneously adapting to each client's local applications. Existing PFL methods typically face a significant challenge due to the ubiquitous data heterogeneity (i.e., non-IID data) across clients, which severely hinders convergence and degrades performance. We identify that the root issue lies in the long-standing reliance on gradient-based updates, which are inherently sensitive to non-IID data. To fundamentally address this issue and bridge the research gap, in this paper, we propose a Heterogeneity-invariant Personalized Federated learning scheme, named FedHiP, through analytical (i.e., closed-form) solutions to avoid gradient-based updates. Specifically, we exploit the trend of self-supervised pre-training, leveraging a foundation model as a frozen backbone for gradient-free feature extraction. Following the feature extractor, we further develop an analytic classifier for gradient-free training. To support both collective generalization and individual personalization, our FedHiP scheme incorporates three phases: analytic local training, analytic global aggregation, and analytic local personalization. The closed-form solutions of our FedHiP scheme enable its ideal property of heterogeneity invariance, meaning that each personalized model remains identical regardless of how non-IID the data are distributed across all other clients. Extensive experiments on benchmark datasets validate the superiority of our FedHiP scheme, outperforming the state-of-the-art baselines by at least 5.79%-20.97% in accuracy.

cs.LG↗
arXiv2025

Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems

Multi-solid systems are foundational to a wide range of real-world applications, yet modeling their complex interactions remains challenging. Existing deep learning methods predominantly rely on implicit modeling, where the factors influencing solid deformation are not explicitly represented but are instead indirectly learned. However, as the number of solids increases, these methods struggle to accurately capture intricate physical interactions. In this paper, we introduce a novel explicit modeling paradigm that incorporates factors influencing solid deformation through structured modules. Specifically, we present Unisoma, a unified and flexible Transformer-based model capable of handling variable numbers of solids. Unisoma directly captures physical interactions using contact modules and adaptive interaction allocation mechanism, and learns the deformation through a triplet relationship. Compared to implicit modeling techniques, explicit modeling is more well-suited for multi-solid systems with diverse coupling patterns, as it enables detailed treatment of each solid while preventing information blending and confusion. Experimentally, Unisoma achieves consistent state-of-the-art performance across seven well-established datasets and two complex multi-solid tasks. Code is avaiable at https://github.com/therontau0054/Unisoma.

cs.LG↗
arXiv2025

LaDEEP: A Deep Learning-based Surrogate Model for Large Deformation of Elastic-Plastic Solids

Scientific computing for large deformation of elastic-plastic solids is critical for numerous real-world applications. Classical numerical solvers rely primarily on local discrete linear approximation and are constrained by an inherent trade-off between accuracy and efficiency. Recently, deep learning models have achieved impressive progress in solving the continuum mechanism. While previous models have explored various architectures and constructed coefficient-solution mappings, they are designed for general instances without considering specific problem properties and hard to accurately handle with complex elastic-plastic solids involving contact, loading and unloading. In this work, we take stretch bending, a popular metal fabrication technique, as our case study and introduce LaDEEP, a deep learning-based surrogate model for \textbf{La}rge \textbf{De}formation of \textbf{E}lastic-\textbf{P}lastic Solids. We encode the partitioned regions of the involved slender solids into a token sequence to maintain their essential order property. To characterize the physical process of the solid deformation, a two-stage Transformer-based module is designed to predict the deformation with the sequence of tokens as input. Empirically, LaDEEP achieves five magnitudes faster speed than finite element methods with a comparable accuracy, and gains 20.47\% relative improvement on average compared to other deep learning baselines. We have also deployed our model into a real-world industrial production system, and it has shown remarkable performance in both accuracy and efficiency.

cs.LG↗