arXiv subjects

Ming Zhang

Publications and source records attributed to Ming Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Comprehensive Analysis of Optical brightness and Color Variability of Blazars in the ZTF Survey DR22

This study conducts a comprehensive analysis of brightness and color variability in blazars, utilizing over six years of quasi-simultaneous g-band and r-band data from 1149 sources in the ZTF Data Release 22 (DR22), including 589 BL Lacs and 560 FSRQs. We quantify the amplitude of variability and the fractional root mean square (rms) variability for each source and statistically assess the overall and short-term color behaviors across different subclasses; examine the distribution of brightness variability characteristics across different blazar types and investigate how the extent of variability correlates with color trends. We found BL Lacs tend to exhibit a BWB (bluer when brighter) trend, while FSRQs display a RWB (redder when brighter) trend; BL Lacs with negligible host-galaxy contamination exhibit a BWB trend fraction of 14.7% (68/462) compared to 2.3% (11/462) for RWB trend, while FSRQs show 8.8% (49/560) BWB trend versus 14.1% (79/560) RWB trend. By statistically investigating how color behavior depends on brightness state across different timescales, we find that brighter states in both BL Lacs and FSRQs are more likely to exhibit BWB trend. Our results also show that BL Lacs with a BWB trend exhibit higher variability than those with a RWB trend, whereas FSRQs with a RWB trend display significantly greater variability than those with a BWB trend. These results suggest that blazar color variability depends jointly on source type, brightness state, and variability amplitude, highlighting the complexity of color evolution in blazars.

astro-ph.CO↗

arXiv2026

Testing Cosmic Distance Duality Relation and Transparency with DESI DR2

The Cosmic Distance Duality Relation (CDDR) is a fundamental principle of standard cosmology, linking luminosity (LD) and angular diameter distances (ADD). This work investigates the validity of the CDDR and cosmic transparency by combining the latest Baryon Acoustic Oscillations (BAO) data from DESI DR2, Type Ia Supernovae from Pantheon+, and cosmic chronometers. To address the redshift mismatch between datasets, two distinct reconstruction techniques are employed: Gaussian Process Regression (GPR) and the Free-Knots Method (FKM). The analysis performs null tests on the CDDR under different cosmological priors, finding that the null hypothesis holds and the CDDR is valid within statistical uncertainties. Although mild deviations are observed from the local distance ladder prior, internal consistency calibration indicates that these discrepancies and the Hubble tension may share a common origin, possibly related to systematic effects or new physics. Using multiple phenomenological parameterizations, the deviation parameter is also found to be statistically consistent with zero (e.g., $η_1 = 0.023 \pm 0.027$ for the linear model under Planck priors). Furthermore, the study finds no statistically significant evidence for cosmic opacity. The average of the opacity derivative is compatible with zero ($\langle dτ/dz \rangle = 0.0409 \pm 0.1024$ for GPR and $0.0730 \pm 0.1607$ for FKM). Based on these null results, stringent constraints are placed on the parameter space of Axion-Like Particles (ALPs) and Mini-Charged Particles (MCPs).

astro-ph.CO↗

arXiv2026

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents

Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orchestrate tools for such rigorous workflows. To bridge this gap, we introduce SciAgentGym, a scalable interactive environment featuring 1,780 domain-specific tools across four natural science disciplines, supported by a robust execution infrastructure. Complementing this, we present SciAgentBench, a tiered evaluation suite designed to stress-test agentic capabilities from elementary actions to long-horizon workflows. Our evaluation identifies a critical bottleneck: state-of-the-art models still struggle with complex scientific tool-use, and their performance degrades substantially as interaction horizons extend. To address this, we propose SciForge, a data synthesis method that models the tool action space as a dependency graph to generate logic-aware training trajectories. By fine-tuning on these trajectories, our SciAgent-8B outperforms the significantly larger Qwen3-VL-235B-Instruct while exhibiting positive cross-domain transfer of scientific tool-use capabilities. These results underscore the promising potential of next-generation autonomous scientific agents.

cs.CL↗

arXiv2026

Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR

Multimodal large language models (MLLMs) excel at high-level reasoning yet fail on OCR tasks where fine-grained visual details are compromised or misaligned. We identify an overlooked optimization issue in multi-layer feature fusion. Skip pathways introduce direct back-propagation paths from high-level semantic objectives to early visual layers. This mechanism overwrites low-level signals and destabilizes training. To mitigate this gradient interference, we propose Detached Skip-Links, a minimal modification that reuses shallow features in the forward pass while stopping gradients through the skip branch during joint training. This asymmetric design reduces gradient interference, improving stability and convergence without adding learnable parameters. To diagnose whether fine-grained information is preserved and usable by an LLM, we introduce $R$-Probe, which measures pixel-level reconstructability of projected visual tokens using a shallow decoder initialized from the first quarter of the LLM layers. Across multiple ViT backbones and multimodal benchmarks, and at scales up to 7M training samples, our approach consistently improves OCR-centric benchmarks and delivers clear gains on general multimodal tasks.

cs.CV↗

arXiv2026

Generative structure search for efficient and diverse discovery of molecular and crystal structures

Predicting stable and metastable structures is central to molecular and materials discovery, but remains limited by the cost of searching high-dimensional energy landscapes. Deep generative models offer efficient structure sampling, yet their outputs remain shaped by training data and can underexplore minima that are rare but physically relevant. We introduce generative structure search (GSS), a unified framework that formulates diffusion-based generation and random structure search (RSS) as limiting regimes of a common sampling process driven by learned score fields and physical forces. Coupling these drivers lets GSS use data priors to accelerate sampling while retaining energy-guided exploration of local minima. Across molecular and crystalline systems, GSS recovers diverse metastable structures with more than tenfold lower sampling cost than RSS for broad coverage and remains effective for compositions outside the training distribution. The results establish a physically grounded generative search strategy for discovering structures beyond the reach of data-driven sampling alone.

cs.AI↗

arXiv2026

UniSpike: Accelerating Spiking Neural Networks on Neuromorphic Systems via Eliminating Address Redundancy

Many-core neuromorphic systems accelerate Spiking Neural Networks (SNNs), yet their packet-based spike communication can spend substantial traffic and energy repeatedly transmitting destination addresses. This overhead is amplified by the small payload of spike packets: in representative workloads, duplicate address transmissions account for up to 49% of the total traffic. This paper presents UniSpike, a hardware-software co-design that removes address redundancy by aggregating spikes destined for the same core into compact packets. UniSpike combines destination-centric spike scheduling, lightweight runtime packet assembly hardware, and destination-aware SNN partitioning. Across diverse SNN workloads, UniSpike reduces traffic by 1.93$\times$ on average, delivering 1.77$\times$ speedup and 1.50$\times$ energy efficiency improvement over state-of-the-art designs.

cs.NE↗

arXiv2026

MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis

Although LLMs have made substantial progress in reasoning, systematically producing frontier-level reasoning data remains difficult. Existing synthesis methods often have limited visibility into the structural factors that govern problem difficulty, which can result in narrow diversity and unstable difficulty control. In this work, we view the difficulty of a reasoning problem as arising from the accumulation of atomic knowledge-reasoning transformations, which we term thought modes. Building on this perspective, we propose MindLoom, a framework for synthesizing frontier-level reasoning data through compositional thought mode engineering. Given a collection of hard problems with verified solutions, MindLoom first decomposes those solutions into thought mode chains that reveal each problem's construction logic. It then trains a retrieval model that matches problem states to compatible thought modes, providing guidance on which reasoning challenges to introduce during synthesis. New problems are composed by iteratively applying retrieved thought modes to seed questions, with distribution-aligned sampling to encourage diverse reasoning coverage. Finally, a rollout-based judging stage labels generated questions by difficulty and supplies judged-correct responses for supervised fine-tuning. We evaluate MindLoom on nine benchmarks covering five STEM disciplines and four mathematical reasoning tasks across multiple model families and sizes. Models fine-tuned on MindLoom-generated data achieves favorable performances over base models, distillation, and external-data baselines across the reported benchmarks. Ablation studies indicate the contribution of each component, and further analysis suggests that MindLoom covers a broad range of reasoning patterns while maintaining useful difficulty control. We have open-sourced our implementation at https://github.com/EachSheep/MindLoom.

cs.AI↗

arXiv2026

AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration

The automated mining of predictive signals, or alphas, is a central challenge in quantitative finance. While Reinforcement Learning (RL) has emerged as a promising paradigm for generating formulaic alphas, existing frameworks are fundamentally hampered by a triad of interconnected issues. First, they suffer from reward sparsity, where meaningful feedback is only available upon the completion of a full formula, leading to inefficient and unstable exploration. Second, they rely on semantically inadequate sequential representations of mathematical expressions, failing to capture the structure that determine an alpha's behavior. Third, the standard RL objective of maximizing expected returns inherently drives policies towards a single optimal mode, directly contradicting the practical need for a diverse portfolio of non-correlated alphas. To overcome these challenges, we introduce AlphaSAGE (Structure-Aware Alpha Mining via Generative Flow Networks for Robust Exploration), a novel framework is built upon three cornerstone innovations: (1) a structure-aware encoder based on Relational Graph Convolutional Network (RGCN); (2) a new framework with Generative Flow Networks (GFlowNets); and (3) a dense, multi-faceted reward structure. Empirical results demonstrate that AlphaSAGE outperforms existing baselines in mining a more diverse, novel, and highly predictive portfolio of alphas, thereby proposing a new paradigm for automated alpha mining. Our code is available at https://github.com/BerkinChen/AlphaSAGE.

q-fin.CP↗

arXiv2026

Quasinormal modes of massless scalar and electromagnetic perturbations for Euler-Heisenberg black holes surrounded by perfect fluid dark matter

We investigate the quasinormal modes of massless scalar and electromagnetic perturbations in charged Euler--Heisenberg black holes surrounded by perfect fluid dark matter. The quasinormal frequencies are calculated using the asymptotic iteration method and the sixth-order WKB approximation, and the relative deviation between the two methods is quantitatively analyzed to verify the reliability of results. The greybody factors for both perturbations are also evaluated within the sixth-order WKB framework. We systematically examine the effects of the black hole charge $Q$, nonlinear electrodynamic parameter $a$, dark matter parameter $λ$, and angular quantum number $l$ on the quasinormal frequencies and greybody factors. We find that these parameters significantly modify the structure of the effective potential barriers, and thus affect the oscillation frequencies, damping rates, and wave transmission and reflection properties of the perturbed fields.

gr-qc↗

arXiv2026

SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models

Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabilities required in practice. Most benchmarks are manually curated or domain-generic, limiting scalability and alignment with real scientific use cases. In this paper, we propose a new framework named SciCustom to address the problem. It enables the custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs. SciCustom first organizes scientific knowledge into ontology-grounded knowledge units with controlled granularity and trains a tagger to map large-scale data instances into this knowledge space. Given a custom requirement, relevant knowledge units are identified via voting-based multi-model consensus. These units enable relevance-aware benchmark retrieval via binary search, followed by proxy subset selection and data-grounded benchmark generation for efficient evaluation. Experiments in chemistry and healthcare demonstrate that SciCustom reveals fine-grained differences in LLM scientific capabilities that standard benchmarks overlook, while requiring neither expert annotation nor synthetic question generation. This work provides a scalable and application-aware foundation for benchmarking scientific capabilities in LLMs. The source code is available at https://github.com/yjwtheonly/SciCustom.

cs.CL↗

arXiv2026

ADR: An Agentic Detection System for Enterprise Agentic AI Security

We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol (MCP). We identify three persistent challenges in this domain: (1) limited observability -- existing Endpoint Detection and Response (EDR) tools see file writes but not the agent reasoning, prompts, or causal chains linking intent to execution; (2) insufficient robustness -- static defenses constrained by pre-defined rules fail to generalize across diverse attack techniques and enterprise contexts; and (3) high detection costs -- LLM-based inference is prohibitively expensive at scale. ADR addresses these challenges via three components: the ADR Sensor for high-fidelity agentic telemetry, the ADR Explorer for systematic pre-deployment red teaming and hard-example generation, and the ADR Detector for scalable, two-tier online detection combining fast triage with context-aware reasoning. Deployed at Uber for over ten months, ADR has sustained reliable detection in production with growing adoption reaching over 7,200 unique hosts and processing over 10,000 agent sessions daily, uncovering hundreds of credential exposures across 26 categories and enabling a shift-left prevention layer (97.2% precision, 206 detected credentials). To validate the approach and enable community adoption, we introduce ADR-Bench (302 tasks, 17 techniques, 133 MCP servers), where ADR achieves zero false positives while detecting 67% of attacks -- outperforming three state-of-the-art baselines (ALRPHFS, GuardAgent, LlamaFirewall) by 2--4x in F1-score. On AgentDojo (public prompt injection benchmark), ADR detects all attacks with only three false alarms out of 93 tasks.

cs.AI↗

arXiv2026

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training

Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex and unreliable supervision signals can destabilize training and harm generalization. While existing approaches such as worst-case optimization (e.g., RFQI, CQL) and mean-based methods (e.g., PPO, GRPO) can improve stability, they often overlook generalization and may produce overly conservative policies, leading to uneven performance across diverse real scenarios. To this end, we introduce DVPO (Distributional Value Modeling with Risk-aware Policy Optimization), a new RL framework that combines conditional risk theory with distributional value modeling to better balance robustness and generalization. DVPO learns token-level value distributions to provide fine-grained supervision, and applies an asymmetric risk regularization to shape the distribution tails: it contracts the lower tail to dampen noisy negative deviations, while expanding the upper tail to preserve exploratory diversity. Across extensive experiments and analysis in multi-turn dialogue, math reasoning, and scientific QA, DVPO consistently outperforms PPO, GRPO, and robust Bellman-based PPO under noisy supervision, showing its potential for LLM post-training in the real-world.

cs.LG↗

arXiv2026

DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training

Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM post-training. Recent distributional RL methods improve robustness by modeling values with multiple quantile points, but they still learn each quantile independently as a scalar. This results in rough-grained value representations that lack fine-grained conditioning on state information, struggling under complex and OOD conditions. We propose DFPO (Distributional Value Flow Policy Optimization with Conditional Risk and Consistency Control), a robust distributional RL framework that models values as continuous flows across time steps. By scaling value modeling through learning of a value flow field instead of isolated quantile predictions, DFPO captures richer state information for more accurate advantage estimation. To stabilize training under noisy feedback, DFPO further integrates conditional risk control and consistency constraints along value flow trajectories. Experiments on dialogue, math reasoning, and scientific tasks show that DFPO outperforms PPO, FlowRL, and other robust baselines under noisy supervision, achieving improved training stability and generalization.

cs.LG↗

arXiv2026

Interests Burn-down Diffusion Process for Personalized Collaborative Filtering

Generative methods have gained widespread attention in Collaborative Filtering (CF) tasks for their ability to produce high-quality personalized samples aligned with users' interests. Among them, diffusion generative models have raised increasing attention in recommendation field. Despite that the pioneering efforts have applied the conventional diffusion process to model diffusive user interests, the incongruity between the Gaussian noise and the subtle nature of user's personalized interaction behavior has led to sub-optimal results. To this end, we introduce a specifically-tailored diffusion scheme for interaction systems, namely the interests burn-down process. The interests burn-down process delineates the decay of user interests towards candidate items, complemented by its reverse burn-up process that yields personalized recommendation for users. The inherent burn-down nature of this process adeptly models the diffusive user interests, aligning seamlessly with the requirements of CF tasks. We present a novel recommendation method StageCF to illustrate the superiority of this newly proposed diffusion process. Experimental results have demonstrated the effectiveness of StageCF against existing generative and diffusion-based baseline methods. Furthermore, comprehensive studies validate the functionality of interests burn-down process, shedding light on its capacity to generate personalized interactions.

cs.IR↗

arXiv2026

CL-bench Life: Can Language Models Learn from Real-Life Context?

Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life.

cs.CL↗

arXiv2026

Dual-Polarized Massive MIMO Based on Precoding for Vehicle-To-Ground Communication in Urban Rail Transit

The development of intelligent and diversified ser vices in urban rail transit (URT) has resulted in an increasing de mand for high-rate communication between vehicles and ground equipment. However, existing URT communication systems strug gle to handle the massive data exchange required for vehicle-to ground (V2G) communication. To address this issue, we propose a distributed dual-polarized MIMO architecture suitable for URT tunnel scenarios. Specifically, the channel model is based on spatial three-dimensional (3D) non-stationary geometry-based stochastic model (GBSM), which takes into account the geometric distribution of URT tunnels and the cross-polarization effects between dual-polarized antennas. For dual-polarized MIMO systems, the polarized-aware sparse channel estimation (PASCE) method is proposed for effective channel estimation. Additionally, we derive closed-form expressions for the MMSE and MR precoding schemes. The polarized-aware dynamic interference cancellation (PADIC) algorithm is developed to eliminate in terference between different polarization modes and multiple users. The simulation results demonstrate that the proposed dual-polarized precoding algorithm can withstand high cross polarization correlation (XPC) and improve the efficiency of V2G communication to achieve high rates.

eess.SY↗

arXiv2026

Vision-Braille: A Curriculum Learning Toolkit and Braille-Chinese Corpus for Braille Translation

We present Vision-Braille, the first publicly available end-to-end system for translating Chinese Braille extracted from images into written Chinese. This system addresses the unique challenges of limited annotated resources and tone omission. It integrates a robust Braille OCR pipeline with an LLM fine-tuned for sequence-to-sequence translation. We construct a synthetic Braille-Chinese corpus, including tone-omission variants that mimic authentic Braille writing habits. We fine-tune the model using a four-stage curriculum: starting with sentence-level data with full tone markers, progressing to passage-level data, then applying a tone-omission schedule of decreasing retention, and finally consolidating on passages with heavy tone omission. On passage-level translation with 10\% tone retention, \methodname{} achieves 83.28 BLEU. Vision-Braille offers an inclusive NLP solution that empowers students with visual impairments to participate in mainstream education by enabling teachers to grade Braille homework without extensive training. Our code and data are available at https://anonymous.4open.science/r/EMNLP_2026_Supp_Code_Data-2F6D.

cs.CL↗

arXiv2026

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions

Reinforcement learning (RL) has emerged as a powerful post-training paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, reinforcement learning for LLMs faces substantial data scarcity challenges, including the limited availability of high-quality external supervision and the constrained volume of model-generated experience. These limitations make data-efficient reinforcement learning a critical research direction. In this survey, we present the first systematic review of reinforcement learning for LLMs under data scarcity. We propose a bottom-up hierarchical framework built around three complementary perspectives: the data-centric perspective, the training-centric perspective, and the framework-centric perspective. We develop a taxonomy of existing methods, summarize representative approaches in each category, and analyze their strengths and limitations. Our taxonomy aims to provide a clear conceptual foundation for understanding the design space of data-efficient RL for LLMs and to guide researchers working in this emerging area. We hope this survey offers a comprehensive roadmap for future research and inspires new directions toward more efficient and scalable reinforcement learning post-training for LLMs.

cs.LG↗