arXiv subjects

Han Li

Publications and source records attributed to Han Li.

At least 253 records · Page 14Linked to original sources

arXiv2025

Orthogonal Geometry of Magneto-Optical Kerr Effect Enabled by Magnetization Multipole of Berry Curvature

The Magneto-Optical Kerr Effect (MOKE) is a fundamental tool in magnetometry, pivotal for advancing research in optics, magnetism, and spintronics as a direct probe of magnetization. Traditional MOKE measurements primarily detect the magnetization components parallel to the Poynting vector, which can only access the magnitude but not the direction of the orthogonal component. In this study, we introduce an orthogonal MOKE geometry in which the Kerr signal detects both the magnitude and direction of the magnetization component perpendicular to the Poynting vector. We demonstrate the broad applicability of this orthogonal geometry through the MOKE measurements in cubic ferromagnets and van der Waals ferromagnet. We theoretically show that the orthogonal MOKE geometry is enabled by the multipolar structure of Berry curvature in the magnetization space, which generally induces a Voigt vector orthogonal to the magnetization, thereby accounting for the unique magnetization angle dependence distinct from conventional MOKE. The establishment of the orthogonal MOKE geometry not only introduces a new paradigm for magneto-optical measurements but also provides a framework for exploring the magnetization multipoles of Berry curvature across the electromagnetic spectrum.

physics.optics↗

arXiv2025

ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding

Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought reasoning or test-time search using Process Reward Models (PRMs), these approaches encounter challenges such as a lack of explanations, bias in PRM training data, early-step bias in PRM scores, and insufficient post-training optimization of reasoning potential. To address these issues, we propose Retrieval-Augmented Reasoning through Trustworthy Process Rewarding (ReARTeR), a framework that enhances RAG systems' reasoning capabilities through post-training and test-time scaling. At test time, ReARTeR introduces Trustworthy Process Rewarding via a Process Reward Model for accurate scalar scoring and a Process Explanation Model (PEM) for generating natural language explanations, enabling step refinement. During post-training, it utilizes Monte Carlo Tree Search guided by Trustworthy Process Rewarding to collect high-quality step-level preference data, optimized through Iterative Preference Optimization. ReARTeR addresses three core challenges: (1) misalignment between PRM and PEM, tackled through off-policy preference learning; (2) bias in PRM training data, mitigated by balanced annotation methods and stronger annotations for challenging examples; and (3) early-step bias in PRM, resolved through a temporal-difference-based look-ahead search strategy. Experimental results on multi-step reasoning benchmarks demonstrate significant improvements, underscoring ReARTeR's potential to advance the reasoning capabilities of RAG systems.

cs.CL↗

arXiv2024

LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application

Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items. However, this approach overlooks the wealth of semantic information embedded within textual descriptions of items, leading to suboptimal performance and poor generalizations. Leveraging the capability of large language models to comprehend and reason about textual content presents a promising avenue for advancing recommendation systems. To achieve this, we propose an Llm-driven knowlEdge Adaptive RecommeNdation (LEARN) framework that synergizes open-world knowledge with collaborative knowledge. We address computational complexity concerns by utilizing pretrained LLMs as item encoders and freezing LLM parameters to avoid catastrophic forgetting and preserve open-world knowledge. To bridge the gap between the open-world and collaborative domains, we design a twin-tower structure supervised by the recommendation task and tailored for practical industrial application. Through experiments on the real large-scale industrial dataset and online A/B tests, we demonstrate the efficacy of our approach in industry application. We also achieve state-of-the-art performance on six Amazon Review datasets to verify the superiority of our method.

cs.IR↗

arXiv2024

Frequency-Aware Transformer for Learned Image Compression

Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing anisotropic frequency components and preserving directional details. To overcome these challenges, we propose a novel frequency-aware transformer (FAT) block that for the first time achieves multiscale directional ananlysis for LIC. The FAT block comprises frequency-decomposition window attention (FDWA) modules to capture multiscale and directional frequency components of natural images. Additionally, we introduce frequency-modulation feed-forward network (FMFFN) to adaptively modulate different frequency components, improving rate-distortion performance. Furthermore, we present a transformer-based channel-wise autoregressive (T-CA) model that effectively exploits channel dependencies. Experiments show that our method achieves state-of-the-art rate-distortion performance compared to existing LIC methods, and evidently outperforms latest standardized codec VTM-12.1 by 14.5%, 15.1%, 13.0% in BD-rate on the Kodak, Tecnick, and CLIC datasets.

eess.IV↗

arXiv2024

CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention

Vehicle Routing Problems (VRPs) are significant Combinatorial Optimization (CO) problems holding substantial practical importance. Recently, Neural Combinatorial Optimization (NCO), which involves training deep learning models on extensive data to learn vehicle routing heuristics, has emerged as a promising approach due to its efficiency and the reduced need for manual algorithm design. However, applying NCO across diverse real-world scenarios with various constraints necessitates cross-problem capabilities. Current NCO methods typically employ a unified model lacking a constraint-specific structure, thereby restricting their cross-problem performance. Current multi-task methods for VRPs typically employ a constraint-unaware model, limiting their cross-problem performance. Furthermore, they rely solely on global connectivity, which fails to focus on key nodes and leads to inefficient representation learning. This paper introduces a Constraint-Aware Dual-Attention Model (CaDA), designed to address these limitations. CaDA incorporates a constraint prompt that efficiently represents different problem variants. Additionally, it features a dual-attention mechanism with a global branch for capturing broader graph-wide information and a sparse branch that selectively focuses on the most relevant nodes. We comprehensively evaluate our model on 16 different VRPs and compare its performance against existing cross-problem VRP solvers. CaDA achieves state-of-the-art results across all the VRPs. Our ablation study further confirms that each component of CaDA contributes positively to its cross-problem learning performance.

cs.AI↗

arXiv2024

How to Recognize Clustering of Luminescent Defects in Single-Wall Carbon Nanotubes

Semiconducting single-wall carbon nanotubes (SWCNTs) are a promising material platform for near-infrared in-vivo imaging, optical sensing, and single-photon emission at telecommunication wavelengths. The functionalization of SWCNTs with luminescent defects can lead to significantly enhanced photoluminescence (PL) properties due to efficient trapping of highly mobile excitons and red-shifted emission from these trap states. Among the most studied luminescent defect types are oxygen and aryl defects that have largely similar optical properties. So far, no direct comparison between SWCNTs functionalized with oxygen and aryl defects under identical conditions has been performed. Here, we employ a combination of spectroscopic techniques to quantify the number of defects, their distribution along the nanotubes and thus their exciton trapping efficiencies. The different slopes of Raman D/G+ ratios versus calculated defect densities from PL quantum yield measurements indicate substantial dissimilarities between oxygen and aryl defects. Supported by statistical analysis of single-nanotube PL spectra at cryogenic temperatures it reveals clustering of oxygen defects. The clustering of 2-3 oxygen defects, which act as a single exciton trap, occurs irrespective of the functionalization method and thus enables the use of simple equations to determine the density of oxygen defects and oxygen defect clusters in SWCNTs based on standard Raman spectroscopy. The presented analytical approach is a versatile and sensitive tool to study defect distribution and clustering in SWCNTs and can be applied to any new functionalization method.

cond-mat.mtrl-sci↗

arXiv2024

Multimodal Instruction Tuning with Hybrid State Space Models

Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in image resolution and frame rate substantially increases computational demands due to the increased number of input tokens. This challenge is further exacerbated by the quadratic complexity with respect to sequence length of the self-attention mechanism. Most prior works either pre-train models with long contexts, overlooking the efficiency problem, or attempt to reduce the context length via downsampling (e.g., identify the key image patches or frames) to decrease the context length, which may result in information loss. To circumvent this issue while keeping the remarkable effectiveness of MLLMs, we propose a novel approach using a hybrid transformer-MAMBA model to efficiently handle long contexts in multimodal applications. Our multimodal model can effectively process long context input exceeding 100k tokens, outperforming existing models across various benchmarks. Remarkably, our model enhances inference efficiency for high-resolution images and high-frame-rate videos by about 4 times compared to current models, with efficiency gains increasing as image resolution or video frames rise. Furthermore, our model is the first to be trained on low-resolution images or low-frame-rate videos while being capable of inference on high-resolution images and high-frame-rate videos, offering flexibility for inference in diverse scenarios.

cs.CV↗

arXiv2024

RecFlow: An Industrial Full Flow Recommendation Dataset

Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users. Existing RS benchmark datasets primarily focus on the exposure space, where novel RS algorithms are trained and evaluated. However, when these algorithms transition to real world industrial RS, they face a critical challenge of handling unexposed items which are a significantly larger space than the exposed one. This discrepancy profoundly impacts their practical performance. Additionally, these algorithms often overlook the intricate interplay between multiple RS stages, resulting in suboptimal overall system performance. To address this issue, we introduce RecFlow, an industrial full flow recommendation dataset designed to bridge the gap between offline RS benchmarks and the real online environment. Unlike existing datasets, RecFlow includes samples not only from the exposure space but also unexposed items filtered at each stage of the RS funnel. Our dataset comprises 38M interactions from 42K users across nearly 9M items with additional 1.9B stage samples collected from 9.3M online requests over 37 days and spanning 6 stages. Leveraging the RecFlow dataset, we conduct courageous exploration experiments, showcasing its potential in designing new algorithms to enhance effectiveness by incorporating stage-specific samples. Some of these algorithms have already been deployed online, consistently yielding significant gains. We propose RecFlow as the first comprehensive benchmark dataset for the RS community, supporting research on designing algorithms at any stage, study of selection bias, debiased algorithms, multi-stage consistency and optimality, multi-task recommendation, and user behavior modeling. The RecFlow dataset, along with the corresponding source code, is available at https://github.com/RecFlow-ICLR/RecFlow.

cs.IR↗

arXiv2024

Longitudinal Causal Image Synthesis

Clinical decision-making relies heavily on causal reasoning and longitudinal analysis. For example, for a patient with Alzheimer's disease (AD), how will the brain grey matter atrophy in a year if intervened on the A-beta level in cerebrospinal fluid? The answer is fundamental to diagnosis and follow-up treatment. However, this kind of inquiry involves counterfactual medical images which can not be acquired by instrumental or correlation-based image synthesis models. Yet, such queries require counterfactual medical images, not obtainable through standard image synthesis models. Hence, a causal longitudinal image synthesis (CLIS) method, enabling the synthesis of such images, is highly valuable. However, building a CLIS model confronts three primary yet unmet challenges: mismatched dimensionality between high-dimensional images and low-dimensional tabular variables, inconsistent collection intervals of follow-up data, and inadequate causal modeling capability of existing causal graph methods for image data. In this paper, we established a tabular-visual causal graph (TVCG) for CLIS overcoming these challenges through a novel integration of generative imaging, continuous-time modeling, and structural causal models combined with a neural network. We train our CLIS based on the ADNI dataset and evaluate it on two other AD datasets, which illustrate the outstanding yet controllable quality of the synthesized images and the contributions of synthesized MRI to the characterization of AD progression, substantiating the reliability and utility in clinics.

eess.IV↗

arXiv2024

Coarse-to-fine Dynamic Uplift Modeling for Real-time Video Recommendation

With the rise of short video platforms, video recommendation technology faces more complex challenges. Currently, there are multiple non-personalized modules in the video recommendation pipeline that urgently need personalized modeling techniques for improvement. Inspired by the success of uplift modeling in online marketing, we attempt to implement uplift modeling in the video recommendation scenario. However, we face two main challenges: 1) Design and utilization of treatments, and 2) Capture of user real-time interest. To address them, we design adjusting the distribution of videos with varying durations as the treatment and propose Coarse-to-fine Dynamic Uplift Modeling (CDUM) for real-time video recommendation. CDUM consists of two modules, CPM and FIC. The former module fully utilizes the offline features of users to model their long-term preferences, while the latter module leverages online real-time contextual features and request-level candidates to model users' real-time interests. These two modules work together to dynamically identify and targeting specific user groups and applying treatments effectively. Further, we conduct comprehensive experiments on the offline public and industrial datasets and online A/B test, demonstrating the superiority and effectiveness of our proposed CDUM. Our proposed CDUM is eventually fully deployed on the Kuaishou platform, serving hundreds of millions of users every day. The source code will be provided after the paper is accepted.

cs.IR↗

arXiv2024

Variable Aperture Bokeh Rendering via Customized Focal Plane Guidance

Bokeh rendering is one of the most popular techniques in photography. It can make photographs visually appealing, forcing users to focus their attentions on particular area of image. However, achieving satisfactory bokeh effect usually presents significant challenge, since mobile cameras with restricted optical systems are constrained, while expensive high-end DSLR lens with large aperture should be needed. Therefore, many deep learning-based computational photography methods have been developed to mimic the bokeh effect in recent years. Nevertheless, most of these methods were limited to rendering bokeh effect in certain single aperture. There lacks user-friendly bokeh rendering method that can provide precise focal plane control and customised bokeh generation. There as well lacks authentic realistic bokeh dataset that can potentially promote bokeh learning on variable apertures. To address these two issues, in this paper, we have proposed an effective controllable bokeh rendering method, and contributed a Variable Aperture Bokeh Dataset (VABD). In the proposed method, user can customize focal plane to accurately locate concerned subjects and select target aperture information for bokeh rendering. Experimental results on public EBB! benchmark dataset and our constructed dataset VABD have demonstrated that the customized focal plane together aperture prompt can bootstrap model to simulate realistic bokeh effect. The proposed method has achieved competitive state-of-the-art performance with only 4.4M parameters, which is much lighter than mainstream computational bokeh models. The contributed dataset and source codes will be released on github https://github.com/MoTong-AI-studio/VABM.

cs.CV↗

arXiv2024

The existence of a bounded linear extension operator for $L^{s,p}(\mathbb{R}^n)$ when $\frac{n}{p}<\{s\}$

Let $L^{s,p}(\mathbb{R}^n)$ denote the homogeneous Sobolev-Slobodeckij space. In this paper, we demonstrate the existence of a bounded linear extension operator from the jet space $J^{\lfloor s \rfloor}_E L^{s,p}(\mathbb{R}^n)$ to $L^{s,p}(\mathbb{R}^n)$ for any $E \subseteq \mathbb{R}^n$, $p \in [1, \infty)$, and $s \in (0, \infty)$ satisfying $\frac{n}{p} < \{s\}$, where $\{s\}$ represents the fractional part of $s$. Our approach builds upon the classical Whitney extension operator and uses the method of exponentially decreasing paths.

math.CA↗

arXiv2024

Predicting macroscopic properties of amorphous monolayer carbon via pair correlation function

Establishing the structure-property relationship in amorphous materials has been a long-term grand challenge due to the lack of a unified description of the degree of disorder. In this work, we develop SPRamNet, a neural network based machine-learning pipeline that effectively predicts structure-property relationship of amorphous material via global descriptors. Applying SPRamNet on the recently discovered amorphous monolayer carbon, we successfully predict the thermal and electronic properties. More importantly, we reveal that a short range of pair correlation function can readily encode sufficiently rich information of the structure of amorphous material. Utilizing powerful machine learning architectures, the encoded information can be decoded to reconstruct macroscopic properties involving many-body and long-range interactions. Establishing this hidden relationship offers a unified description of the degree of disorder and eliminates the heavy burden of measuring atomic structure, opening a new avenue in studying amorphous materials.

cond-mat.mtrl-sci↗

arXiv2024

Constructing hierarchical time series through clustering: Is there an optimal way for forecasting?

Forecast reconciliation has attracted significant research interest in recent years, with most studies taking the hierarchy of time series as given. We extend existing work that uses time series clustering to construct hierarchies, with the goal of improving forecast accuracy, in three ways. First, we investigate multiple approaches to clustering, including not only different clustering algorithms, but also the way time series are represented and how distance between time series is defined. We find that cluster-based hierarchies lead to improvements in forecast accuracy relative to two-level hierarchies. Second, we devise an approach based on random permutation of hierarchies, keeping the structure of the hierarchy fixed, while time series are randomly allocated to clusters. In doing so, we find that improvements in forecast accuracy that accrue from using clustering do not arise from grouping together similar series but from the structure of the hierarchy. Third, we propose an approach based on averaging forecasts across hierarchies constructed using different clustering methods, that is shown to outperform any single clustering method. All analysis is carried out on two benchmark datasets and a simulated dataset. Our findings provide new insights into the role of hierarchy construction in forecast reconciliation and offer valuable guidance on forecasting practice.

stat.ME↗

arXiv2024

From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph-Based Deep Learning

Accurate prediction of protein-ligand binding affinities is an essential challenge in structure-based drug design. Despite recent advances in data-driven methods for affinity prediction, their accuracy is still limited, partially because they only take advantage of static crystal structures while the actual binding affinities are generally determined by the thermodynamic ensembles between proteins and ligands. One effective way to approximate such a thermodynamic ensemble is to use molecular dynamics (MD) simulation. Here, an MD dataset containing 3,218 different protein-ligand complexes is curated, and Dynaformer, a graph-based deep learning model is further developed to predict the binding affinities by learning the geometric characteristics of the protein-ligand interactions from the MD trajectories. In silico experiments demonstrated that the model exhibits state-of-the-art scoring and ranking power on the CASF-2016 benchmark dataset, outperforming the methods hitherto reported. Moreover, in a virtual screening on heat shock protein 90 (HSP90) using Dynaformer, 20 candidates are identified and their binding affinities are further experimentally validated. Dynaformer displayed promising results in virtual drug screening, revealing 12 hit compounds (two are in the submicromolar range), including several novel scaffolds. Overall, these results demonstrated that the approach offer a promising avenue for accelerating the early drug discovery process.

q-bio.BM↗

arXiv2024

Easy Access to Bright Oxygen Defects in Biocompatible Single-Walled Carbon Nanotubes via a Fenton-Like Reaction

The covalent functionalization of single-walled carbon nanotubes (SWNTs) with luminescent oxygen defects increases their brightness and enables their application as optical biosensors or fluorescent probes for in-vivo imaging in the second-biological window (NIR-II). However, obtaining luminescent defects with high brightness is challenging with the current functionalization methods due to a restricted window of reaction conditions or the necessity for controlled irradiation with ultraviolet light. Here we report a method for introducing luminescent oxygen defects via a Fenton-like reaction that uses benign and inexpensive chemicals without light irradiation. (6,5) SWNTs in aqueous dispersion functionalized with this method show bright $E_{11}$* emission (1105 nm) with 3.2-times higher peak intensities than the pristine $E_{11}$ emission and a reproducible photoluminescence quantum yield of 3%. The functionalization can be performed within a wide range of reaction parameters and even with unsorted nanotube raw material at high concentrations (100 mg/L), giving access to large amounts of brightly luminescent SWNTs. We further find that the introduced oxygen defects rearrange under light irradiation, which gives additional insights into the structure and dynamics of oxygen defects. Finally, the functionalization of ultra-short SWNTs with oxygen defects also enables high photoluminescence quantum yields and their excellent emission properties are retained after surfactant exchange with biocompatible pegylated phospholipids or single-stranded DNA to make them suitable for in-vivo NIR-II imaging and dopamine sensing.

cond-mat.mtrl-sci↗

arXiv2024

Spatiotemporal Graph Guided Multi-modal Network for Livestreaming Product Retrieval

With the rapid expansion of e-commerce, more consumers have become accustomed to making purchases via livestreaming. Accurately identifying the products being sold by salespeople, i.e., livestreaming product retrieval (LPR), poses a fundamental and daunting challenge. The LPR task encompasses three primary dilemmas in real-world scenarios: 1) the recognition of intended products from distractor products present in the background; 2) the video-image heterogeneity that the appearance of products showcased in live streams often deviates substantially from standardized product images in stores; 3) there are numerous confusing products with subtle visual nuances in the shop. To tackle these challenges, we propose the Spatiotemporal Graphing Multi-modal Network (SGMN). First, we employ a text-guided attention mechanism that leverages the spoken content of salespeople to guide the model to focus toward intended products, emphasizing their salience over cluttered background products. Second, a long-range spatiotemporal graph network is further designed to achieve both instance-level interaction and frame-level matching, solving the misalignment caused by video-image heterogeneity. Third, we propose a multi-modal hard example mining, assisting the model in distinguishing highly similar products with fine-grained features across the video-image-text domain. Through extensive quantitative and qualitative experiments, we demonstrate the superior performance of our proposed SGMN model, surpassing the state-of-the-art methods by a substantial margin. The code is available at https://github.com/Huxiaowan/SGMN.

cs.CV↗

arXiv2024

Magnetocaloric Effect of Topological Excitations in Kitaev Magnets

Traditional magnetic sub-Kelvin cooling relies on the nearly free local moments in hydrate paramagnetic salts, whose utility is hampered by the dilute magnetic ions and low thermal conductivity. Here we propose to use instead fractional excitations inherent to quantum spin liquids (QSLs) as an alternative, which are sensitive to external fields and can induce a very distinctive magnetocaloric effect. With state-of-the-art tensor-network approach, we compute low-temperature properties of Kitaev honeycomb model. For the ferromagnetic case, strong demagnetization cooling effect is observed due to the nearly free $Z_2$ vortices via spin fractionalization, described by a paramagnetic equation of state with a renormalized Curie constant. For the antiferromagnetic Kitaev case, we uncover an intermediate-field gapless QSL phase with very large spin entropy, possibly due to the emergence of spinon Fermi surface. Potential realization of topological excitation cooling in Kitaev materials is also discussed, which may offer a promising pathway to circumvent existing limitations in the paramagnetic hydrates.

cond-mat.str-el↗