arXiv subjects

Jiaxin Xu

Publications and source records attributed to Jiaxin Xu.

At least 19 recordsLinked to original sources

arXiv2026

LMEB: Long-horizon Memory Embedding Benchmark

Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage retrieval and fail to assess models' ability to handle long-horizon memory retrieval tasks involving fragmented, context-dependent, and temporally distant information. To address this gap, we introduce the Long-horizon Memory Embedding Benchmark (LMEB), a comprehensive framework for evaluating embedding models on complex, long-horizon memory retrieval. LMEB comprises 22 datasets and 193 zero-shot retrieval tasks spanning four memory types: episodic, dialogue, semantic, and procedural. These memory types differ in terms of level of abstraction and temporal dependency, capturing distinct aspects of memory retrieval that reflect the diverse challenges of the real world. We evaluate 15 widely used embedding models, ranging from hundreds of millions to ten billion parameters. The results reveal that (1) LMEB provides a reasonable level of difficulty; (2) Larger models do not always perform better; (3) LMEB and MTEB measure orthogonal capabilities. This suggests that the field has yet to converge on a universal model capable of excelling across all memory retrieval tasks, and that strong performance on traditional passage retrieval does not necessarily transfer to long-horizon memory retrieval. LMEB provides a standardized and reproducible framework that fills a key gap in memory embedding evaluation and supports future advances in long-term, context-dependent retrieval.

cs.CL↗

arXiv2026

KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking

As retrieval systems scale, high-quality reranking becomes increasingly important. However, most existing rerankers, whether encoder-based or decoder-based, jointly encode the query and passage, tightly coupling their computation and limiting deployment efficiency as well as flexibility. We present KaLM-Reranker-V1, a fast but not late-interaction (FBNL) reranker that decouples query and passage computation while retaining expressive relevance modeling. Built on an encoder-decoder architecture, KaLM-Reranker-V1 uses the encoder to pre-encode passages with Matryoshka embedding pooling, while the decoder models the system instruction, user instruction, and query intent; cross-attention then captures relevance between the query context and passage representations. This design makes KaLM-Reranker-V1 efficient through decoupled passage encoding, yet not late interaction, by preserving rich relevance modeling through cross-attention. We instantiate KaLM-Reranker-V1 in three sizes, Nano, Small, and Large, with 0.27B, 1B, and 4B activated parameters, respectively. Extensive experiments on BEIR, MIRACL, and LMEB demonstrate that KaLM-Reranker-V1 achieves strong reranking performance with superior efficiency. On BEIR, KaLM-Reranker-V1 achieves state-of-the-art performance, on par with strong industrial models such as the Qwen3-Reranker series; on MIRACL, despite not being extensively trained on multilingual data, KaLM-Reranker-V1 still shows excellent reranking performance. Moreover, on LMEB, reranking models demonstrate a clear advantage, with even the 0.27B Nano model remaining competitive with 7-12B embedding models.

cs.CL↗

arXiv2026

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

cs.CL↗

arXiv2026

ADEPT-PolyGraphMT: Automated Molecular Simulation and Multi-Task Multi-Fidelity Machine Learning for Polymer Property Generation and Prediction

The discovery of polymers with targeted properties is challenged by the vast chemical design space and the limited availability of consistent, high-quality data across multiple properties. In this work, an integrated polymer informatics framework is presented that combines the Automated molecular Dynamics Engine for Polymer simulaTions (ADEPT) workflow with multi-task and multi-fidelity machine learning (PolyGraphMT). Polymer repeat units are represented as molecular graphs and processed using a graph neural network to learn structure-property relationships. Starting from SMILES representations for monomers, ADEPT automates the construction of atomistic models and the evaluation of their properties using molecular dynamics simulations and density functional theory calculations. The simulation data are combined with curated experimental data and group contribution theory estimates to construct a unified dataset of approximately 62,000 polymer property values spanning 28 properties. Using this dataset, inter-property correlations are analyzed, and multi-task learning strategies are evaluated for joint property prediction. The results show that multi-task models achieve performance comparable to single-task models in data-rich regimes and exhibit superior accuracy as training data become limited. In addition, fidelity-aware training improves predictive accuracy when combining experimental and computational data sources. The trained models are further applied to large-scale property prediction for polymers in the PolyInfo database and the PI1M virtual polymer library, producing physically consistent property distributions across a broad chemical space. Overall, the proposed framework provides a structured approach for scalable prediction and screening of polymer properties across multiple property types and data fidelity levels.

physics.chem-ph↗

arXiv2026

Active learning-enabled multi-objective design of thermally conductive and mechanically compliant polymers

Polymers are attractive in applications like flexible electronics and thermal interface materials due to their mechanical compliance and processability. However, conventional polymers have low thermal conductivity (TC), limiting their heat dissipation performance. Identifying polymers that simultaneously achieve high intrinsic TC and mechanical flexibility (i.e., low modulus) remains a challenge. Here, we develop an active learning (AL) framework based on multi-objective Bayesian optimization (MOBO) to discover polymers exhibiting both high TC and low bulk modulus. Initially, a high-throughput molecular dynamics (MD) pipeline generated an initial dataset, and independent Deep Kernel Learning (DKL) surrogate models were trained for TC and bulk modulus to predict properties and uncertainties. Using the parallel noisy expected hypervolume improvement (qNEHVI) acquisition function, the framework iteratively screens a larger unlabeled polymer database, systematically recommends new polymer candidates for MD evaluation, and updates the DKL models with newly acquired data. Ultimately, six candidates were identified on the Pareto front, representing optimal trade-offs between TC and modulus. Interpretability analysis further revealed molecular features associated with these trade-offs, and synthesizability assessment supported the practical relevance of the selected candidates. By combining MD simulations with AL-enabled MOBO, our workflow mitigates data scarcity, reduces development time, and provides actionable guidance for designing multifunctional polymers tailored for different applications.

cond-mat.mtrl-sci↗

arXiv2026

Robust quantized transport from topological quasienergy winding in long-range-coupling synthetic quantum walks

Quantized transport is a prominent feature in topological physics, with canonical examples being the quantum Hall effect and adiabatic Thouless pump, which are based on the Chern number, a topological invariant of 2D systems. Going beyond the Chern-number-based paradigms, quantized transports can also arise from k-direction quasienergy winding unique to periodically driven (Floquet) systems, which are free of dimensionality and adiabaticity limitations. However, lattices displaying winding of their quasienergy bands require asymmetric long-range couplings that are difficult to achieve in lattices of real-space coupled sites. Here, by leveraging photonic synthetic dimensions we construct asymmetric long-range-couplings in a one-dimensional temporal quantum walk based on three coupled fiber loops. We demonstrate quantized transport arising from the winding of quasienergy bands in k direction. We show that the average group velocity of an initial wave packet is proportional to the winding number, which leads to a quantized transport displacement. To better visualize this quantized displacement, we cascade two regions with flipped nearest/long-range couplings and observe a focusing effect with a quantized spatial shift in the focusing point. We also probe the robust properties of quantized transport against obstacles and disorders. The study initiates quasienergy-winding-based topological transports, which can feature applications in precise and robust imaging and information processing.

physics.optics↗

arXiv2026

Designing Persuasive Social Robots for Health Behavior Change: A Systematic Review of Behavior Change Strategies and Evaluation Methods

Social robots are increasingly applied as health behavior change interventions, yet actionable knowledge to guide their design and evaluation remains limited. This systematic review synthesizes (1) the behavior change strategies used in existing HRI studies employing social robots to promote health behavior change, and (2) the evaluation methods applied to assess behavior change outcomes. Relevant literature was identified through systematic database searches and hand searches. Analysis of 39 studies revealed four overarching categories of behavior change strategies: coaching strategies, counseling strategies, social influence strategies, and persuasion-enhancing strategies. These strategies highlight the unique affordances of social robots as behavior change interventions and offer valuable design heuristics. The review also identified key characteristics of current evaluation practices, including study designs, settings, durations, and outcome measures, on the basis of which we propose several directions for future HRI research.

cs.RO↗

arXiv2025

Open Polymer Challenge: Post-Competition Report

Machine learning (ML) offers a powerful path toward discovering sustainable polymer materials, but progress has been limited by the lack of large, high-quality, and openly accessible polymer datasets. The Open Polymer Challenge (OPC) addresses this gap by releasing the first community-developed benchmark for polymer informatics, featuring a dataset with 10K polymers and 5 properties: thermal conductivity, radius of gyration, density, fractional free volume, and glass transition temperature. The challenge centers on multi-task polymer property prediction, a core step in virtual screening pipelines for materials discovery. Participants developed models under realistic constraints that include small data, label imbalance, and heterogeneous simulation sources, using techniques such as feature-based augmentation, transfer learning, self-supervised pretraining, and targeted ensemble strategies. The competition also revealed important lessons about data preparation, distribution shifts, and cross-group simulation consistency, informing best practices for future large-scale polymer datasets. The resulting models, analysis, and released data create a new foundation for molecular AI in polymer science and are expected to accelerate the development of sustainable and energy-efficient materials. Along with the competition, we release the test dataset at https://www.kaggle.com/datasets/alexliu99/neurips-open-polymer-prediction-2025-test-data. We also release the data generation pipeline at https://github.com/sobinalosious/ADEPT, which simulates more than 25 properties, including thermal conductivity, radius of gyration, and density.

cs.LG↗

arXiv2025

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) DeepSeek Sparse Attention (DSA): We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance in long-context scenarios. (2) Scalable Reinforcement Learning Framework: By implementing a robust reinforcement learning protocol and scaling post-training compute, DeepSeek-V3.2 performs comparably to GPT-5. Notably, our high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and exhibits reasoning proficiency on par with Gemini-3.0-Pro, achieving gold-medal performance in both the 2025 International Mathematical Olympiad (IMO) and the International Olympiad in Informatics (IOI). (3) Large-Scale Agentic Task Synthesis Pipeline: To integrate reasoning into tool-use scenarios, we developed a novel synthesis pipeline that systematically generates training data at scale. This methodology facilitates scalable agentic post-training, yielding substantial improvements in generalization and instruction-following robustness within complex, interactive environments.

cs.CL↗

arXiv2025

Research progress of artificial intelligence empowered quantum communication and quantum sensing systems

Quantum communication and quantum sensing, which leverage the unique characteristics of quantum systems, enable information-theoretically secure communication and high-precision measurement of physical quantities. However, they both face numerous challenges on the path to practical application. Artificial intelligence (AI), as a major technological advancement in current scientific landscape, offers powerful data processing and analytical capabilities, providing new ideas and methods for optimizing and enhancing quantum communication and sensing systems. In quantum communication, AI techniques have greatly improved the performance and security of quantum key distribution, quantum memory, and quantum networks through parameter optimization, real-time feedback control, and attack detection. In quantum sensing, quantum sensing technology enables ultra-high sensitivity detection of physical quantities such as time and magnetic fields. The introduction of AI has opened up new avenues for achieving high-precision and high-sensitivity quantum measurements. With AI, sensor performance is optimized, and measurement accuracy is further enhanced through data analysis. This paper also analyzes the current challenges in using AI to empower quantum communication and sensing systems, such as implementing efficient algorithm deployment and system feedback control under limited computational resources, and addressing complex task environments, dynamically changing scenarios, and multi-task coordination requirements. Finally, this paper discusses and envisions future development prospects in this field.

quant-ph↗

arXiv2025

Assessing Risk Heterogeneity through Heavy-Tailed Frequency and Severity Mixtures

The analysis of risk typically involves dividing a random damage-generation process into separate frequency (event-count) and severity (damage-magnitude) components. In the present article, we construct canonical families of mixture distributions for each of these components, based on a Negative Binomial kernel for frequencies and a Gamma kernel for severities. These mixtures are employed to assess the heterogeneity of risk factors underlying an empirical distribution through the shape of the implied mixing distribution. From the duality of the Negative Binomial and Gamma distributions, we first derive necessary and sufficient conditions for heavy-tailed (i.e., inverse power-law) canonical mixtures. We then formulate flexible 4-parameter families of mixing distributions for Geometric and Exponential kernels to generate heavy-tailed 4-parameter mixture models, and extend these mixtures to arbitrary Negative Binomial and Gamma kernels, respectively, yielding 5-parameter mixtures for detecting and measuring risk heterogeneity. To check the robustness of such heterogeneity inferences, we show how a fitted 5-parameter model may be re-expressed in terms of alternative Negative Binomial or Gamma kernels whose associated mixing distributions form a "calibrated" family.

stat.ME↗

arXiv2025

User Concerns Regarding Social Robots for Mood Regulation: A Case Study on the "Sunday Blues"

While recent research highlights the potential of social robots to support mood regulation, little is known about how prospective users view their integration into everyday life. To explore this, we conducted an exploratory case study that used a speculative robot concept "Mora" to provoke reflection and facilitate meaningful discussion about using social robots to manage subtle, day-to-day emotional experiences. We focused on the "Sunday Blues," a common dip in mood that occurs at the end of the weekend, as a relatable context in which to explore individuals' insights. Using a video prototype and a co-constructing stories method, we engaged 15 participants in imagining interactions with Mora and discussing their expectations, doubts, and concerns. The study surfaced a range of nuanced reflections around the attributes of social robots like empathy, intervention effectiveness, and ethical boundaries, which we translated into design considerations for future research and development in human-robot interaction.

cs.HC↗

arXiv2025

A Criterion for Extending Continuous-Mixture Identifiability Results

Mixture distributions provide a versatile and widely used framework for modeling random phenomena, and are particularly well-suited to the analysis of geoscientific processes and their attendant risks to society. For continuous mixtures of random variables, we specify a simple criterion - generating-function accessibility - to extend previously known kernel-based identifiability (or unidentifiability) results to new kernel distributions. This criterion, based on functional relationships between the relevant kernels' moment-generating functions or Laplace transforms, may be applied to continuous mixtures of both discrete and continuous random variables. To illustrate the proposed approach, we present results for several specific kernels, in each case briefly noting its relevance to research in the geosciences and/or related risk analysis.

stat.ML↗

arXiv2025

A Versatility Measure for Parametric Risk Models

Parametric statistical methods play a central role in analyzing risk through its underlying frequency and severity components. Given the wide availability of numerical algorithms and high-speed computers, researchers and practitioners often model these separate (although possibly statistically dependent) random variables by fitting a large number of parametric probability distributions to historical data and then comparing goodness-of-fit statistics. However, this approach is highly susceptible to problems of overfitting because it gives insufficient weight to fundamental considerations of functional simplicity and adaptability. To address this shortcoming, we propose a formal mathematical measure for assessing the versatility of frequency and severity distributions prior to their application. We then illustrate this approach by computing and comparing values of the versatility measure for a variety of probability distributions commonly used in risk analysis.

stat.AP↗

arXiv2025

POINT$^{2}$: A Polymer Informatics Training and Testing Database

The advancement of polymer informatics has been significantly propelled by the integration of machine learning (ML) techniques, enabling the rapid prediction of polymer properties and expediting the discovery of high-performance polymeric materials. However, the field lacks a standardized workflow that encompasses prediction accuracy, uncertainty quantification, ML interpretability, and polymer synthesizability. In this study, we introduce POINT$^{2}$ (POlymer INformatics Training and Testing), a comprehensive benchmark database and protocol designed to address these critical challenges. Leveraging the existing labeled datasets and the unlabeled PI1M dataset, a collection of approximately one million virtual polymers generated via a recurrent neural network trained on the realistic polymers, we develop an ensemble of ML models, including Quantile Random Forests, Multilayer Perceptrons with dropout, Graph Neural Networks, and pretrained large language models. These models are coupled with diverse polymer representations such as Morgan, MACCS, RDKit, Topological, Atom Pair fingerprints, and graph-based descriptors to achieve property predictions, uncertainty estimations, model interpretability, and template-based polymerization synthesizability across a spectrum of properties, including gas permeability, thermal conductivity, glass transition temperature, melting temperature, fractional free volume, and density. The POINT$^{2}$ database can serve as a valuable resource for the polymer informatics community for polymer discovery and optimization.

cond-mat.mtrl-sci↗

arXiv2025

Hybrid Implementation for Untrusted-node-based Quantum Key Distribution Network

Quantum key distribution (QKD) serves as a cornerstone of secure quantum communication, providing unconditional security grounded in quantum mechanics. While trusted-node networks have facilitated early QKD deployment, their vulnerability to node compromise underscores the need for untrusted-node architectures. Measurement-device-independent QKD (MDI-QKD) and twin-field QKD (TF-QKD) have emerged as leading candidates, addressing security vulnerabilities and extending transmission distances. Despite the wide adoptions in various fiber scaling, no integrated implementation of these two protocols has been demonstrated to date. Here, we present a hybrid system that seamlessly integrates TF-QKD and MDI-QKD into one untrusted-node-based architecture. Utilizing an efficient phase estimation method based on asymmetric interferometers, we convert twin-field global phase tracking to relative phase calibration, allowing near continuous running of both protocols. Experiments demonstrate secure finite-size key rates for sending-or-not-sending QKD and MDI-QKD over fiber distances of 150 to 431 km. The results align with theoretical simulations and show the ability to surpass the absolute repeaterless key capacity. Our work offers an unified framework for deploying multi-protocol QKD networks, laying the foundation for adaptable and scalable quantum infrastructures that can meet a wide range of security and performance needs.

quant-ph↗

arXiv2025

From Abstract to Actionable: Pairwise Shapley Values for Explainable AI

Explainable AI (XAI) is critical for ensuring transparency, accountability, and trust in machine learning systems as black-box models are increasingly deployed within high-stakes domains. Among XAI methods, Shapley values are widely used for their fairness and consistency axioms. However, prevalent Shapley value approximation methods commonly rely on abstract baselines or computationally intensive calculations, which can limit their interpretability and scalability. To address such challenges, we propose Pairwise Shapley Values, a novel framework that grounds feature attributions in explicit, human-relatable comparisons between pairs of data instances proximal in feature space. Our method introduces pairwise reference selection combined with single-value imputation to deliver intuitive, model-agnostic explanations while significantly reducing computational overhead. Here, we demonstrate that Pairwise Shapley Values enhance interpretability across diverse regression and classification scenarios--including real estate pricing, polymer property prediction, and drug discovery datasets. We conclude that the proposed methods enable more transparent AI systems and advance the real-world applicability of XAI.

cs.LG↗

arXiv2025

Robot-Initiated Social Control of Sedentary Behavior: Comparing the Impact of Relationship- and Target-Focused Strategies

To design social robots to effectively promote health behavior change, it is essential to understand how people respond to various health communication strategies employed by these robots. This study examines the effectiveness of two types of social control strategies from a social robot, relationship-focused strategies (emphasizing relational consequences) and target-focused strategies (emphasizing health consequences), in encouraging people to reduce sedentary behavior. A two-session lab experiment was conducted (n = 135), where participants first played a game with a robot, followed by the robot persuading them to stand up and move using one of the strategies. Half of the participants joined a second session to have a repeated interaction with the robot. Results showed that relationship-focused strategies motivated participants to stay active longer. Repeated sessions did not strengthen participants' relationship with the robot, but those who felt more attached to the robot responded more actively to the target-focused strategies. These findings offer valuable insights for designing persuasive strategies for social robots in health communication contexts.

cs.HC↗