arXiv subjects

Jie Zhang

Publications and source records attributed to Jie Zhang.

At least 361 records · Page 20Linked to original sources

arXiv2025

Predictive Hydrodynamic Simulations for Laser Direct-drive Implosion Experiments via Artificial Intelligence

This work presents predictive hydrodynamic simulations empowered by artificial intelligence (AI) for laser driven implosion experiments, taking the double-cone ignition (DCI) scheme as an example. A Transformer-based deep learning model MULTI-Net is established to predict implosion features according to laser waveforms and target radius. A Physics-Informed Decoder (PID) is proposed for high-dimensional sampling, significantly reducing the prediction errors compared to Latin hypercube sampling. Applied to DCI experiments conducted on the SG-II Upgrade facility, the MULTI-Net model is able to predict the implosion dynamics measured by the x-ray streak camera. It is found that an effective laser absorption factor about 65\% is suitable for the one-dimensional simulations of the DCI-R10 experiments. For shot 33, the mean implosion velocity and collided plasma density reached 195 km/s and 117 g/cc, respectively. This study demonstrates a data-driven AI framework that enhances the prediction ability of simulations for complicated laser fusion experiments.

physics.plasm-ph↗

arXiv2025

ToFe: Lagged Token Freezing and Reusing for Efficient Vision Transformer Inference

Although vision transformers (ViT) have shown remarkable success in various vision tasks, their computationally expensive self-attention hinder their deployment on resource-constrained devices. Token reduction, which discards less important tokens during forward propagation, has been proposed to enhance the efficiency of transformer models. However, existing methods handle unimportant tokens irreversibly, preventing their reuse in subsequent blocks. Considering that transformers focus on different information among blocks, tokens reduced in early blocks might be useful later. Furthermore, to adapt transformer models for resource-constrained devices, it is crucial to strike a balance between model performance and computational overhead. To address these challenges, in this paper, we introduce a novel Token Freezing and Reusing (ToFe) framework, where we identify important tokens at each stage and temporarily freeze the unimportant ones, allowing their lagged reusing at a later stage. Specifically, we design a prediction module for token identification and an approximate module for recovery of the frozen tokens. By jointly optimizing with the backbone through computation budget-aware end-to-end training, ToFe can adaptively process the necessary tokens at each block, thereby reducing computational cost while maintaining performance. Extensive experiments demonstrate that ToFe reduces the computational cost of LV-ViT model by 50% with less than 2% drop in Top-1 accuracy, achieving a better trade-off between performance and complexity compared to state-of-the-art methods.

cs.CV↗

arXiv2025

RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark

Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement learning (RL) has recently shown significant benefits in solving CO problems, reducing reliance on domain expertise and improving computational efficiency. However, the absence of a unified benchmarking framework leads to inconsistent evaluations, limits reproducibility, and increases engineering overhead, raising barriers to adoption for new researchers. To address these challenges, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 27 CO problem environments and 23 state-of-the-art baselines. Built on efficient software libraries and best practices in implementation, RL4CO features modularized implementation and flexible configurations of diverse environments, policy architectures, RL algorithms, and utilities with extensive documentation. RL4CO helps researchers build on existing successes while exploring and developing their own designs, facilitating the entire research process by decoupling science from heavy engineering. We finally provide extensive benchmark studies to inspire new insights and future work. RL4CO has already attracted numerous researchers in the community and is open-sourced at https://github.com/ai4co/rl4co.

cs.LG↗

arXiv2025

Tidal-Like Concept Drift in RIS-Covered Buildings: When Programmable Wireless Environments Meet Human Behaviors

Indoor mobile networks handle the majority of data traffic, with their performance limited by building materials and structures. However, building designs have historically not prioritized wireless performance. Prior to the advent of reconfigurable intelligent surfaces (RIS), the industry passively adapted to wireless propagation challenges within buildings. Inspired by RIS's successes in outdoor networks, we propose embedding RIS into building structures to manipulate and enhance building wireless performance comprehensively. Nonetheless, the ubiquitous mobility of users introduces complex dynamics to the channels of RIS-covered buildings. A deep understanding of indoor human behavior patterns is essential for achieving wireless-friendly building design. This article is the first to systematically examine the tidal evolution phenomena emerging in the channels of RIS-covered buildings driven by complex human behaviors. We demonstrate that a universal channel model is unattainable and focus on analyzing the challenges faced by advanced deep learning-based prediction and control strategies, including high-order Markov dependencies, concept drift, and generalization issues caused by human-induced disturbances. Possible solutions for orchestrating the coexistence of RIS-covered buildings and crowd mobility are also laid out.

cs.NI↗

arXiv2025

VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting

This paper presents Variables Adaptive Mixture of Experts (VAMoE), a novel framework for incremental weather forecasting that dynamically adapts to evolving spatiotemporal patterns in real time data. Traditional weather prediction models often struggle with exorbitant computational expenditure and the need to continuously update forecasts as new observations arrive. VAMoE addresses these challenges by leveraging a hybrid architecture of experts, where each expert specializes in capturing distinct subpatterns of atmospheric variables (temperature, humidity, wind speed). Moreover, the proposed method employs a variable adaptive gating mechanism to dynamically select and combine relevant experts based on the input context, enabling efficient knowledge distillation and parameter sharing. This design significantly reduces computational overhead while maintaining high forecast accuracy. Experiments on real world ERA5 dataset demonstrate that VAMoE performs comparable against SoTA models in both short term (1 days) and long term (5 days) forecasting tasks, with only about 25% of trainable parameters and 50% of the initial training data.

cs.LG↗

arXiv2025

LLM-Driven Dual-Level Multi-Interest Modeling for Recommendation

Recently, much effort has been devoted to modeling users' multi-interests based on their behaviors or auxiliary signals. However, existing methods often rely on heuristic assumptions, e.g., co-occurring items indicate the same interest of users, failing to capture user multi-interests aligning with real-world scenarios. While large language models (LLMs) show significant potential for multi-interest analysis due to their extensive knowledge and powerful reasoning capabilities, two key challenges remain. First, the granularity of LLM-driven multi-interests is agnostic, possibly leading to overly fine or coarse interest grouping. Second, individual user analysis provides limited insights due to the data sparsity issue. In this paper, we propose an LLM-driven dual-level multi-interest modeling framework for more effective recommendation. At the user-individual level, we exploit LLMs to flexibly allocate items engaged by users into different semantic clusters, indicating their diverse and distinct interests. To alleviate the agnostic generation of LLMs, we adaptively assign these semantic clusters to users' collaborative multi-interests learned from global user-item interactions, allowing the granularity to be automatically adjusted according to the user's behaviors using an alignment module. To alleviate the limited insights derived from individual users' behaviors, at the user-crowd level, we propose aggregating user cliques into synthesized users with rich behaviors for more comprehensive LLM-driven multi-interest analysis. We formulate a max covering problem to ensure the compactness and representativeness of synthesized users' behaviors, and then conduct contrastive learning based on their LLM-driven multi-interests to disentangle item representations among different interests. Experiments on real-world datasets show the superiority of our approach against state-of-the-art methods.

cs.IR↗

arXiv2025

BMDetect: A Multimodal Deep Learning Framework for Comprehensive Biomedical Misconduct Detection

Academic misconduct detection in biomedical research remains challenging due to algorithmic narrowness in existing methods and fragmented analytical pipelines. We present BMDetect, a multimodal deep learning framework that integrates journal metadata (SJR, institutional data), semantic embeddings (PubMedBERT), and GPT-4o-mined textual attributes (methodological statistics, data anomalies) for holistic manuscript evaluation. Key innovations include: (1) multimodal fusion of domain-specific features to reduce detection bias; (2) quantitative evaluation of feature importance, identifying journal authority metrics (e.g., SJR-index) and textual anomalies (e.g., statistical outliers) as dominant predictors; and (3) the BioMCD dataset, a large-scale benchmark with 13,160 retracted articles and 53,411 controls. BMDetect achieves 74.33% AUC, outperforming single-modality baselines by 8.6%, and demonstrates transferability across biomedical subfields. This work advances scalable, interpretable tools for safeguarding research integrity.

cs.LG↗

arXiv2025

BURN: Backdoor Unlearning via Adversarial Boundary Analysis

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic labels of poison samples. This limitation prevents them from fully eliminating the false correlation between the trigger pattern and the target label. To address this, we leverage boundary adversarial attack techniques, revealing two key observations. First, poison samples exhibit significantly greater distances from decision boundaries compared to clean samples, indicating they require larger adversarial perturbations to change their predictions. Second, while adversarial predicted labels for clean samples are uniformly distributed, those for poison samples tend to revert to their original correct labels. Moreover, the features of poison samples restore to closely resemble those of corresponding clean samples after adding adversarial perturbations. Building upon these insights, we propose Backdoor Unlearning via adversaRial bouNdary analysis (BURN), a novel defense framework that integrates false correlation decoupling, progressive data refinement, and model purification. In the first phase, BURN employs adversarial boundary analysis to detect poisoned samples based on their abnormal adversarial boundary distances, then restores their correct semantic labels for fine-tuning. In the second phase, it employs a feedback mechanism that tracks prediction discrepancies between the original backdoored model and progressively sanitized models, guiding both dataset refinement and model purification. Extensive evaluations across multiple datasets, architectures, and seven diverse backdoor attack types confirm that BURN effectively removes backdoor threats while maintaining the model's original performance.

cs.CR↗

arXiv2025

A sharp and conservative method for modeling interfacial flows with insoluble surfactants in the framework of a geometric volume-of-fluid approach

Insoluble surfactants adsorbed at liquid-liquid or gas-liquid interfaces alter interfacial tension, leading to variations in the normal stress jump and generating tangential Marangoni stresses that can dramatically affect the flow dynamics. We develop a three-dimensional, sharp and conservative numerical method for modeling insoluble surfactant-laden interfacial flows within a volume-of-fluid framework. This method contrasts with diffusive transport algorithms commonly employed in the Eulerian framework. The proposed method preserves the zero-thickness property of the interface, ensures accurate calculation of the surfactant concentration, and robustly handles complex topological changes. The interface evolution is captured using a geometrical volume-of-fluid method, with surfactant mass sharply stored at the reconstructed interface. The advection term in the surfactant transport equation is discretized implicitly in conjunction with the geometrical advection of the volume fraction of one of the fluids, thereby eliminating numerical inconsistencies arising from discrepancies between the actual and computed interface areas. Additionally, the diffusion term is discretized along the reconstructed interface, preventing artificial diffusion normal to the zero-thickness interface. Benchmark tests demonstrate that the proposed method achieves higher accuracy and faster convergence compared to existing diffusive approaches. Finally, we apply the method to investigate the interaction of a surfactant-laden rising bubble with a vertical wall, revealing a transition from near-wall bouncing to migration away from the wall as the surfactant concentration increases.

physics.flu-dyn↗

arXiv2025

Efficient Long Context Fine-tuning with Chunk Flow

Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail distribution and employ training strategies designed specifically for long sequences. Moreover, these approaches also fail to address the challenges posed by variable sequence lengths during distributed training, such as load imbalance in data parallelism and severe pipeline bubbles in pipeline parallelism. These issues lead to suboptimal training performance and poor GPU resource utilization. To tackle these problems, we propose a chunk-centric training method named ChunkFlow. ChunkFlow reorganizes input sequences into uniformly sized chunks by consolidating short sequences and splitting longer ones. This approach achieves optimal computational efficiency and balance among training inputs. Additionally, ChunkFlow incorporates a state-aware chunk scheduling mechanism to ensure that the peak memory usage during training is primarily determined by the chunk size rather than the maximum sequence length in the dataset. Integrating this scheduling mechanism with existing pipeline scheduling algorithms further enhances the performance of distributed training. Experimental results demonstrate that, compared with Megatron-LM, ChunkFlow can be up to 4.53x faster in the long context fine-tuning of LLMs. Furthermore, we believe that ChunkFlow serves as an effective solution for a broader range of scenarios, such as long context continual pre-training, where datasets contain variable-length sequences.

cs.DC↗

arXiv2025

Learning-aided Bigraph Matching Approach to Multi-Crew Restoration of Damaged Power Networks Coupled with Road Transportation Networks

The resilience of critical infrastructure networks (CINs) after disruptions, such as those caused by natural hazards, depends on both the speed of restoration and the extent to which operational functionality can be regained. Allocating resources for restoration is a combinatorial optimal planning problem that involves determining which crews will repair specific network nodes and in what order. This paper presents a novel graph-based formulation that merges two interconnected graphs, representing crew and transportation nodes and power grid nodes, into a single heterogeneous graph. To enable efficient planning, graph reinforcement learning (GRL) is integrated with bigraph matching. GRL is utilized to design the incentive function for assigning crews to repair tasks based on the graph-abstracted state of the environment, ensuring generalization across damage scenarios. Two learning techniques are employed: a graph neural network trained using Proximal Policy Optimization and another trained via Neuroevolution. The learned incentive functions inform a bipartite graph that links crews to repair tasks, enabling weighted maximum matching for crew-to-task allocations. An efficient simulation environment that pre-computes optimal node-to-node path plans is used to train the proposed restoration planning methods. An IEEE 8500-bus power distribution test network coupled with a 21 square km transportation network is used as the case study, with scenarios varying in terms of numbers of damaged nodes, depots, and crews. Results demonstrate the approach's generalizability and scalability across scenarios, with learned policies providing 3-fold better performance than random policies, while also outperforming optimization-based solutions in both computation time (by several orders of magnitude) and power restored.

cs.LG↗

arXiv2025

Sparse Autoencoders Reveal Interpretable Structure in Small Gene Language Models

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the internal representations of large language models (LLMs), revealing latent latent features with semantical meaning. This interpretability has also proven valuable in biological domains: applying SAEs to protein language models uncovered meaningful features related to protein structure and function. More recently, SAEs have been used to analyze genomics-focused models such as Evo 2, identifying interpretable features in gene sequences. However, it remains unclear whether SAEs can extract meaningful representations from small gene language models, which have fewer parameters and potentially less expressive capacity. To address it, we propose applying SAEs to the activations of a small gene language model. We demonstrate that even small-scale models encode biologically relevant genomic features, such as transcription factor binding motifs, that SAEs can effectively uncover. Our findings suggest that compact gene language models are capable of learning structured genomic representations, and that SAEs offer a scalable approach for interpreting gene models across various model sizes.

q-bio.OT↗

arXiv2025

TableReasoner: Advancing Table Reasoning Framework with Large Language Models

The paper presents our system developed for table question answering (TQA). TQA tasks face challenges due to the characteristics of real-world tabular data, such as large size, incomplete column semantics, and entity ambiguity. To address these issues, we propose a large language model (LLM)-powered and programming-based table reasoning framework, named TableReasoner. It models a table using the schema that combines structural and semantic representations, enabling holistic understanding and efficient processing of large tables. We design a multi-step schema linking plan to derive a focused table schema that retains only query-relevant information, eliminating ambiguity and alleviating hallucinations. This focused table schema provides precise and sufficient table details for query refinement and programming. Furthermore, we integrate the reasoning workflow into an iterative thinking architecture, allowing incremental cycles of thinking, reasoning and reflection. Our system achieves first place in both subtasks of SemEval-2025 Task 8.

cs.AI↗

arXiv2025

Ultrafast and reliable domain-wall and skyrmion logic in a chirally coupled ferrimagnet

Unlocking the spin degree of freedom in addition to the electron's charge, spin-based logic offers an in-memory computing architecture beyond-CMOS technology. Here, we encode information into chiral spin textures (e.g., chiral domain-wall and skyrmion) and achieve an ultrafast and reliable all-electrical logic by exploiting the Dzyaloshinskii-Moriya interaction-induced chiral coupling. Taking advantage of fast spin dynamics in antiferromagnetically coupled systems, we achieved a fast domain-wall motion passing through the logic gate, exceeding 1 kilometre per second, yielding an operation time of 50 picoseconds for a 50 nanometres-long logic gate. Furthermore, we present a fast logic operation with skyrmion bubbles in a racetrack that exhibits a topologically protected computation scheme. Our work demonstrates a viable approach for advanced microchips with high operation frequency and ultralow power consumption, paving the way for next-generation computing technologies.

cond-mat.mes-hall↗

arXiv2025

CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs

Large reasoning models (LRMs) have demonstrated impressive capabilities in domains like mathematics and program synthesis. Despite their strong performance, LRMs often exhibit overthinking -- excessive and redundant reasoning steps that introduce inefficiencies during inference. This phenomenon raises an important question for LRM self-evaluation: How can a model autonomously assess the correctness of its own reasoning trajectory without external labels? To address this, we propose Chain-of-Reasoning Embedding (CoRE), a series of hidden states in latent space to enable label-free self-evaluation on intermediate reasoning steps of LRMs, so as to enhance metacognition abilities for improved reasoning efficiency. By analyzing the geometric properties of the CoRE trajectories, we reveal that redundant reasoning usually presents cyclical fluctuations, which correspond to repetitive and unconscious reflection/exploration. Leveraging this insight, we further introduce a training-free, label-free self-evaluation framework, CoRE-Eval, to detect such patterns and dynamically determine whether to terminate reasoning early. Extensive experiments on mathematical reasoning benchmarks (GSM8K, MATH-500, and AIME) and across model sizes from 7B to 32B demonstrate that CoRE-Eval reduces chain-of-thought length by 13.7% to 33.2% while improving answer accuracy by around 10%, achieving 70.0% accuracy on the challenging AIME benchmark with the 32B model.

cs.LG↗

arXiv2025

From Filamentation to Stratification: Instability Dynamics in Scissors-Shaped Relativistic Beam-Plasma System

Counter-streaming systems are a canonical model for beam-plasma instabilities, such as the filamentation instability, which is critical in high energy density physics. However, scenarios involving intersecting fast electron beams break the cylindrical symmetry inherent to such systems. Here, we introduce the scissors-shaped configuration, a fundamental multi-velocity-component system that captures this broken symmetry. Through theoretical analysis and particle-in-cell simulations, we reveal a dramatic shift in the instability dynamics: the system undergoes a stratification mode instead of filamentation. This mode is rapidly quenched by magnetic reconnection, leading to a quasi-stable state with magnetic energy two orders of magnitude lower than in the counter-streaming case. This discovery establishes a new principle of passive instability control via geometric configuration, offering a new perspective on beam-plasma interactions in astrophysics and inertial confinement fusion. The underlying physics is verifiable in upcoming multi-laser experiments.

physics.plasm-ph↗

arXiv2025

Ex-Ante Truthful Distribution-Reporting Mechanisms

This paper studies mechanism design for revenue maximization in a distribution-reporting setting, where the auctioneer does not know the buyers' true value distributions. Instead, each buyer reports and commits to a bid distribution in the ex-ante stage, which the auctioneer uses as input to the mechanism. Buyers strategically decide the reported distributions to maximize ex-ante utility, potentially deviating from their value distributions. As shown in previous work, classical prior-dependent mechanisms such as the Myerson auction fail to elicit truthful value distributions at the ex-ante stage, despite satisfying Bayesian incentive compatibility at the interim stage. We study the design of ex-ante incentive compatible mechanisms, and aim to maximize revenue in a prior-independent approximation framework. We introduce a family of threshold-augmented mechanisms, which ensures ex-ante incentive compatibility while boosting revenue through ex-ante thresholds. Based on these mechanisms, we construct the Peer-Max Mechanism, which achieves an either-or approximation guarantee for general non-identical distributions. Specifically, for any value distributions, its expected revenue either achieves a constant fraction of the optimal social welfare, or surpasses the second-price revenue by a constant fraction, where the constants depend on the number of buyers and a tunable parameter. We also provide an upper bound on the revenue achievable by any ex-ante incentive compatible mechanism, matching our lower bound up to a constant factor. Finally, we extend our approach to a setting where multiple units of identical items are sold to buyers with multi-unit demands.

cs.GT↗

arXiv2025

Topological defects govern plasticity and shear band formation in two-dimensional amorphous solids

Understanding the fundamental mechanisms behind plastic instabilities and shear band formation in amorphous media under applied deformation remains a long-standing challenge. Leveraging on the mathematical concept of topology, we revisit this problem using two-dimensional experimental amorphous granular packings subjected to pure shear. We demonstrate that topological defects (TDs) in the displacement vector field act as carriers of plasticity, enabling the prediction of both the onset of plastic flow and the global mechanical response of the system. At the microscopic level, we show that these TDs are responsible for the dynamical breakdown of local orientational order, thereby linking topological excitations to short-range structural changes. Finally, we establish that the spatial localization and cooperative alignment of TDs underlie the formation of macroscopic shear bands, which drive plastic flow under large shear loads. This process is mediated by the quasi-periodic annihilation of large defect clusters and their geometric transformation from an approximately isotropic to a strongly anisotropic shape. Our results provide a unified framework for understanding plastic deformation and shear band formation in two-dimensional amorphous systems by connecting topology, short-range order, and mechanical response.

cond-mat.soft↗