arXiv subjects

Jun Xu

Publications and source records attributed to Jun Xu.

At least 73 records · Page 4Linked to original sources

arXiv2026

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.

cs.LG↗

arXiv2026

Learning to Retrieve from Agent Trajectories

Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human interaction logs such as clicks and dwell time. With the rapid emergence of large language model (LLM) powered search agents, however, retrieval is increasingly consumed by agents rather than human beings, and is embedded as a core component within multi-turn reasoning and action loops. In this setting, retrieval models trained under human-centric assumptions exhibit a fundamental mismatch with the way agents issue queries and consume results. In this work, we argue that retrieval models for agentic search should be trained directly from agent interaction data. We introduce learning to retrieve from agent trajectories as a new training paradigm, where supervision is derived from multi-step agent interactions. Through a systematic analysis of search agent trajectories, we identify key behavioral signals that reveal document utility, including browsing actions, unbrowsed rejections, and post-browse reasoning traces. Guided by these insights, we propose LRAT, a simple yet effective framework that mines high-quality retrieval supervision from agent trajectories and incorporates relevance intensity through weighted optimization. Extensive experiments on both in-domain and out-of-domain deep research benchmarks demonstrate that retrievers trained with LRAT consistently improve evidence recall, end-to-end task success, and execution efficiency across diverse agent architectures and scales. Our results highlight agent trajectories as a practical and scalable supervision source, pointing to a promising direction for retrieval in the era of agentic search.

cs.IR↗

arXiv2026

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios

The rapid evolution of embodied agents has accelerated the deployment of household robots in real-world environments. However, unlike structured industrial settings, household spaces introduce unpredictable safety risks, where system limitations such as perception latency and lack of common sense knowledge can lead to dangerous errors. Current safety evaluations, often restricted to static images, text, or general hazards, fail to adequately benchmark dynamic unsafe action detection in these specific contexts. To bridge this gap, we introduce HomeSafe-Bench, a challenging benchmark designed to evaluate Vision-Language Models (VLMs) on unsafe action detection in household scenarios. HomeSafe-Bench is contrusted via a hybrid pipeline combining physical simulation with advanced video generation and features 438 diverse cases across six functional areas with fine-grained multidimensional annotations. Beyond benchmarking, we propose Hierarchical Dual-Brain Guard for Household Safety (HD-Guard), a hierarchical streaming architecture for real-time safety monitoring. HD-Guard coordinates a lightweight FastBrain for continuous high-frequency screening with an asynchronous large-scale SlowBrain for deep multimodal reasoning, effectively balancing inference efficiency with detection accuracy. Evaluations demonstrate that HD-Guard achieves a superior trade-off between latency and performance, while our analysis identifies critical bottlenecks in current VLM-based safety detection.

cs.CV↗

arXiv2026

CbLDM: A Diffusion Model for recovering nanostructure from atomic pair distribution function

The nanostructure inverse problem is an attractive problem that helps researchers to understand the relationship between the properties and the structure of nanomaterials. This study focuses on the problem of recovering the model system of monometallic nanoparticles (MMNPs) from their pair distribution function (PDF) and regards it as a highly ill-posed conditional generation task. This study proposes a Condition-based Latent Diffusion Model (CbLDM) as a feasible solution to this problem. This model demonstrates an acceleration approach within the framework of a latent diffusion model by using conditional priors to estimate the conditional posterior distribution, which is an approximate distribution of p(z|x). In addition, this study uses Laplacian matrix instead of distance matrix to recover the nanostructure, which helps to improve stability. Our study demonstrates that a latent diffusion model with a conditional prior can generate nanostructures that are consistent with PDF observations and physically meaningful, thereby laying the groundwork for subsequent more complex inverse problems.

cs.LG↗

arXiv2026

Silence the Judge: Reinforcement Learning with Self-Verifier via Latent Geometric Clustering

Group Relative Policy Optimization (GRPO) significantly enhances the reasoning performance of Large Language Models (LLMs). However, this success heavily relies on expensive external verifiers or human rules. Such dependency not only leads to significant computational costs and training latency, but also yields sparse rewards that hinder optimization efficiency. To address these challenges, we propose Latent-GRPO, a framework that derives intrinsic rewards directly from latent space geometry. Crucially, our empirical analysis reveals a compelling geometric property: terminal token representations of correct reasoning trajectories form dense clusters with high intra-class similarity, whereas incorrect trajectories remain scattered as outliers. In light of this discovery, we introduce the Iterative Robust Centroid Estimation (IRCE) algorithm, which generates dense, continuous rewards by mitigating magnitude fluctuations via spherical projection and estimating a robust ``truth centroid'' through iterative aggregation. Experimental results on multiple datasets show that our method maintains model performance while achieving a training speedup of over 2x compared to baselines. Furthermore, extensive results demonstrate strong generalization ability and robustness. The code will be released soon.

cs.CL↗

arXiv2026

Angular momentum conservation and pion production in intermediate-energy heavy-ion collisions

We have studied the effect of rigorous angular momentum conservation (AMC) in elastic, inelastic, and decay channels on pion production in intermediate-energy heavy-ion collisions based on the framework of an isospin-dependent Boltzmann-Uehling-Uhlenbeck (IBUU) transport model. We found that the constraint of AMC suppresses the absorption of both $Δ$ resonances and pions, thus considerably enhances pion production and meanwhile reduces the charged pion yield ratio. The AMC effect on the charged pion yield ratio can not be simply compensated by a density-dependent in-medium $Δ$ production cross section. Therefore, incorporating the constraint of AMC is important in obtaining the correct pion multiplicity and charged pion yield ratio by transport simulations, relevant for the extraction of the nuclear symmetry energy at high densities.

nucl-th↗

arXiv2026

Enhancing Long-Term Welfare in Recommender Systems: An Information Revelation Approach

Improving the long-term user welfare (e.g., sustained user engagement) has become a central objective of recommender systems (RS). In real-world platforms, the creation behaviors of content creators plays a crucial role in shaping long-term welfare beyond short-term recommendation accuracy, making the effective steering of creator behavior essential to foster a healthier RS ecosystem. Existing works typically rely on re-ranking algorithms that heuristically adjust item exposure to steer creators' behavior. However, when embedded within recommendation pipelines, such a strategy often conflicts with the short-term objective of improving recommendation accuracy, leading to performance degradation and suboptimal long-term welfare. The well-established economics studies offer us valuable insights for an alternative approach without relying on recommendation algorithmic design: revealing information from an information-rich party (sender) to a less-informed party (receiver) can effectively change the receiver's beliefs and steer their behavior. Inspired by this idea, we propose an information-revealing framework, named Long-term Welfare Optimization via Information Revelation (LoRe). In this framework, we utilize a classical information revelation method (i.e., Bayesian persuasion) to map the stakeholders in RS, treating the platform as the sender and creators as the receivers. To address the challenge posed by the unrealistic assumption of traditional economic methods, we formulate the process of information revelation as a Markov Decision Process (MDP) and propose a learning algorithm trained and inferred in environments with boundedly rational creators. Extensive experiments on two real-world RS datasets demonstrate that our method can effectively outperform existing fair re-ranking methods and information revealing strategies in improving long-term user welfare.

cs.IR↗

arXiv2026

Cosmic-ray electron propagation in NGC 3044 from radio continuum observations

Star-forming edge-on galaxies often exhibit extended halo radiation in multiple bands, providing ideal laboratories for studying the transfer of matter from the disk to the halo. We investigate the transport of cosmic-ray electrons (CREs) and the associated galactic wind, and assess their impact on the surrounding medium in NGC 3044. We obtained the NGC 3044 total intensity image at 943 MHz from the Australian SKA Pathfinder (ASKAP) observations with a resolution of 16 arcsec and an rms noise of 20 $μ$Jy beam$^{-1}$. The sensitivity is higher than the previous observations at similar frequencies. We find that the ASKAP intensity profiles perpendicular to the disk can be fit with two exponential components. The scale heights of the thin and thick disks are $0.43 \pm 0.13$ kpc and $1.91 \pm 0.26$ kpc, respectively. By jointly fitting total intensity and spectral index profiles with one-dimensional advection and diffusion models, we find that CREs are advected outward from the disk with the velocity increasing with height in a power law. Beyond $\sim3$ kpc, the velocity exceeds the escape speed of $\sim400$ km s$^{-1}$, indicating a strong wind. We further identify a possible superbubble of radius $\sim3$ kpc filled with soft X-ray emitting hot gas and surrounded by an HI shell and a bright H$α$ rim. These results demonstrate that radio continuum observations provide a powerful probe of cosmic-ray-driven winds in normal star-forming spiral galaxies.

astro-ph.GA↗

arXiv2026

Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations

In real-world streaming recommender systems, user preferences evolve dynamically over time. Existing bandit-based methods treat time merely as a timestamp, neglecting its explicit relationship with user preferences and leading to suboptimal performance. Moreover, online learning methods often suffer from inefficient exploration-exploitation during the early online phase. To address these issues, we propose HyperBandit+, a novel contextual bandit policy that integrates a time-aware hypernetwork to adapt to time-varying user preferences and employs a large language model-assisted warm-start mechanism (LLM Start) to enhance exploration-exploitation efficiency in the early online phase. Specifically, HyperBandit+ leverages a neural network that takes time features as input and generates parameters for estimating time-varying rewards by capturing the correlation between time and user preferences. Additionally, the LLM Start mechanism employs multi-step data augmentation to simulate realistic interaction data for effective offline learning, providing warm-start parameters for the bandit policy in the early online phase. To meet real-time streaming recommendation demands, we adopt low-rank factorization to reduce hypernetwork training complexity. Theoretically, we rigorously establish a sublinear regret upper bound that accounts for both the hypernetwork and the LLM warm-start mechanism. Extensive experiments on real-world datasets demonstrate that HyperBandit+ consistently outperforms state-of-the-art baselines in terms of accumulated rewards.

cs.LG↗

arXiv2026

Distributed Model Predictive Control for Energy and Comfort Optimization in Large Buildings Using Piecewise Affine Approximation

The control of large buildings encounters challenges in computational efficiency due to their size and nonlinear components. To address these issues, this paper proposes a Piecewise Affine (PWA)-based distributed scheme for Model Predictive Control (MPC) that optimizes energy and comfort through PWA-based quadratic programming. We utilize the Alternating Direction Method of Multipliers (ADMM) for effective decomposition and apply the PWA technique to handle the nonlinear components. To solve the resulting large-scale nonconvex problems, the paper introduces a convex ADMM algorithm that transforms the nonconvex problem into a series of smaller convex problems, significantly enhancing computational efficiency. Furthermore, we demonstrate that the convex ADMM algorithm converges to a local optimum of the original problem. A case study involving 36 zones validates the effectiveness of the proposed method. Our proposed method reduces execution time by 86\% compared to the centralized version.

math.OC↗

arXiv2026

MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetings

Enterprise meeting environments require AI assistants that handle diverse operational tasks, from rapid fact checking during live discussions to cross meeting analysis for strategic planning, under strict latency, cost, and privacy constraints. Existing meeting benchmarks mainly focus on simplified question answering and fail to reflect real world enterprise workflows, where queries arise organically from multi stakeholder collaboration, span long temporal contexts, and require tool augmented reasoning. We address this gap through a grounded dataset and a learned agent framework. First, we introduce MeetAll, a bilingual and multimodal corpus derived from 231 enterprise meetings totaling 140 hours. Questions are injected using an enterprise informed protocol validated by domain expert review and human discriminability studies. Unlike purely synthetic benchmarks, this protocol is grounded in four enterprise critical dimensions: cognitive load, temporal context span, domain expertise, and actionable task execution, calibrated through interviews with stakeholders across finance, healthcare, and technology sectors. Second, we propose MeetBench XL, a multi dimensional evaluation protocol aligned with human judgment that measures factual fidelity, intent alignment, response efficiency, structural clarity, and completeness. Third, we present MeetMaster XL, a learned dual policy agent that jointly optimizes query routing between fast and slow reasoning paths and tool invocation, including retrieval, cross meeting aggregation, and web search. A lightweight classifier enables accurate routing with minimal overhead, achieving a superior quality latency tradeoff over single model baselines. Experiments against commercial systems show consistent gains, supported by ablations, robustness tests, and a real world deployment case study.Resources: https://github.com/huyuelin/MeetBench.

cs.AI↗

arXiv2026

DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents

Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation paradigm. Meanwhile, despite the rapid advancement of Search Agents, their practical deployment is constrained by a fundamental limitation, termed as 1) Latency Challenge: the serial execution of multi-round reasoning, tool calling, and tool response waiting under the ReAct agent paradigm induces severe end-to-end latency. Intuitively, dLLMs can leverage their distinctive strengths to optimize the operational efficiency of agents under the ReAct agent paradigm. Practically, existing dLLM backbones face the 2) Agent Ability Challenge. That is, existing dLLMs exhibit remarkably weak reasoning and tool-calling capabilities, preventing these advantages from being effectively realized in practice. In this paper, we propose DLLM-Searcher, an optimization framework for dLLM-based Search Agents. To solve the Agent Ability Challenge, we design a two-stage post-training pipeline encompassing Agentic Supervised Fine-Tuning (Agentic SFT) and Agentic Variance-Reduced Preference Optimization Agentic VRPO, which enhances the backbone dLLM's information seeking and reasoning capabilities. To mitigate the Latency Challenge, we leverage the flexible generation mechanism of dLLMs and propose a novel agent paradigm termed Parallel-Reasoning and Acting P-ReAct. P-ReAct guides the model to prioritize decoding tool_call instructions, thereby allowing the model to keep thinking while waiting for the tool's return. Experimental results demonstrate that DLLM-Searcher achieves performance comparable to mainstream LLM-based search agents and P-ReAct delivers approximately 15% inference acceleration. Our code is available at https://anonymous.4open.science/r/DLLM-Searcher-553C

cs.AI↗

arXiv2026

State Rank Dynamics in Linear Attention LLMs

Linear Attention Large Language Models (LLMs) offer a compelling recurrent formulation that compresses context into a fixed-size state matrix, enabling constant-time inference. However, the internal dynamics of this compressed state remain largely opaque. In this work, we present a comprehensive study on the runtime state dynamics of state-of-the-art Linear Attention models. We uncover a fundamental phenomenon termed State Rank Stratification, characterized by a distinct spectral bifurcation among linear attention heads: while one group maintains an effective rank oscillating near zero, the other exhibits rapid growth that converges to an upper bound. Extensive experiments across diverse inference contexts reveal that these dynamics remain strikingly consistent, indicating that the identity of a head,whether low-rank or high-rank,is an intrinsic structural property acquired during pre-training, rather than a transient state dependent on the input data. Furthermore, our diagnostic probes reveal a surprising functional divergence: low-rank heads are indispensable for model reasoning, whereas high-rank heads exhibit significant redundancy. Leveraging this insight, we propose Joint Rank-Norm Pruning, a zero-shot strategy that achieves a 38.9\% reduction in KV-cache overhead while largely maintaining model accuracy.

cs.LG↗

arXiv2026

Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience

Deep search agents powered by large language models have demonstrated strong capabilities in multi-step retrieval, reasoning, and long-horizon task execution. However, their practical failures often stem from the lack of mechanisms to monitor and regulate reasoning and retrieval states as tasks evolve under uncertainty. Insights from cognitive neuroscience suggest that human metacognition is hierarchically organized, integrating fast anomaly detection with selectively triggered, experience-driven reflection. In this work, we propose Deep Search with Meta-Cognitive Monitoring (DS-MCM), a deep search framework augmented with an explicit hierarchical metacognitive monitoring mechanism. DS-MCM integrates a Fast Consistency Monitor, which performs lightweight checks on the alignment between external evidence and internal reasoning confidence, and a Slow Experience-Driven Monitor, which is selectively activated to guide corrective intervention based on experience memory from historical agent trajectories. By embedding monitoring directly into the reasoning-retrieval loop, DS-MCM determines both when intervention is warranted and how corrective actions should be informed by prior experience. Experiments across multiple deep search benchmarks and backbone models demonstrate that DS-MCM consistently improves performance and robustness.

cs.CL↗

arXiv2026

Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference

The demand for immersive and interactive communication has driven advancements in 3D video conferencing, yet achieving high-fidelity 3D talking face representation at low bitrates remains a challenge. Traditional 2D video compression techniques fail to preserve fine-grained geometric and appearance details, while implicit neural rendering methods like NeRF suffer from prohibitive computational costs. To address these challenges, we propose a lightweight, high-fidelity, low-bitrate 3D talking face compression framework that integrates FLAME-based parametric modeling with 3DGS neural rendering. Our approach transmits only essential facial metadata in real time, enabling efficient reconstruction with a Gaussian-based head model. Additionally, we introduce a compact representation and compression scheme, including Gaussian attribute compression and MLP optimization, to enhance transmission efficiency. Experimental results demonstrate that our method achieves superior rate-distortion performance, delivering high-quality facial rendering at extremely low bitrates, making it well-suited for real-time 3D video conferencing applications.

cs.CV↗

arXiv2026

Convolutional Model Trees

A method for creating a forest of model trees to fit samples of a function defined on images is described in several steps: down-sampling the images, determining a tree's hyperplanes, applying convolutions to the hyperplanes to handle small distortions of training images, and creating forests of model trees to increase accuracy and achieve a smooth fit. A 1-to-1 correspondence among pixels of images, coefficients of hyperplanes and coefficients of leaf functions offers the possibility of dealing with larger distortions such as arbitrary rotations or changes of perspective. A theoretical method for smoothing forest outputs to produce a continuously differentiable approximation is described. Within that framework, a training procedure is proved to converge.

cs.LG↗

arXiv2026

LTS-VoiceAgent: A Listen-Think-Speak Framework for Efficient Streaming Voice Interaction via Semantic Triggering and Incremental Reasoning

Real-time voice agents face a dilemma: end-to-end models often lack deep reasoning, while cascaded pipelines incur high latency by executing ASR, LLM reasoning, and TTS strictly in sequence, unlike human conversation where listeners often start thinking before the speaker finishes. Since cascaded architectures remain the dominant choice for complex tasks, existing cascaded streaming strategies attempt to reduce this latency via mechanical segmentation (e.g., fixed chunks, VAD-based splitting) or speculative generation, but they frequently either break semantic units or waste computation on predictions that must be rolled back. To address these challenges, we propose LTS-VoiceAgent, a Listen-Think-Speak framework that explicitly separates when to think from how to reason incrementally. It features a Dynamic Semantic Trigger to detect meaningful prefixes, and a Dual-Role Stream Orchestrator that coordinates a background Thinker (for state maintenance) and a foreground Speaker (for speculative solving). This parallel design enables "thinking while speaking" without blocking responses. We also introduce a Pause-and-Repair benchmark containing natural disfluencies to stress-test streaming robustness. Experiments across VERA, Spoken-MQA, BigBenchAudio, and our benchmark show that LTS-VoiceAgent achieves a stronger accuracy-latency-efficiency trade-off than serial cascaded baselines and existing streaming strategies.

cs.SD↗

arXiv2026

Unveiling and Simulating Short-Video Addiction Behaviors via Economic Addiction Theory

Short-video applications have attracted substantial user traffic. However, these platforms also foster problematic usage patterns, commonly referred to as short-video addiction, which pose risks to both user health and the sustainable development of platforms. Prior studies on this issue have primarily relied on questionnaires or volunteer-based data collection, which are often limited by small sample sizes and population biases. In contrast, short-video platforms have large-scale behavioral data, offering a valuable foundation for analyzing addictive behaviors. To examine addiction-aware behavior patterns, we combine economic addiction theory with users' implicit behavior captured by recommendation systems. Our analysis shows that short-video addiction follows functional patterns similar to traditional forms of addictive behavior (e.g., substance abuse) and that its intensity is consistent with findings from previous social science studies. To develop a simulator that can learn and model these patterns, we introduce a novel training framework, AddictSim. To consider the personalized addiction patterns, AddictSim uses a mean-to-adapted strategy with group relative policy optimization training. Experiments on two large-scale datasets show that AddictSim consistently outperforms existing training strategies. Our simulation results show that integrating diversity-aware algorithms can mitigate addictive behaviors well.

cs.IR↗