Searcharxiv⌕ Search

arXiv subjects

Shaobo Wang

Publications and source records attributed to Shaobo Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Precise $^{136}$Xe Double Beta Decay Measurement in PandaX-4T with Implications on the Nuclear Matrix Elements and Majorons

The continuous spectrum of double beta decay ($ββ$) provides a sensitive probe to test the predictions of the standard model and to search for signatures of new physics beyond it. We present a comprehensive analysis of the $^{136}$Xe $ββ$ spectrum utilizing $39.1 \pm 0.7~\textrm{kg}\cdot\textrm{yr}$ of $^{136}$Xe exposure from the PandaX-4T experiment. The analysis yields the most precise measurement to date of the $^{136}$Xe two-neutrino double beta decay ($2νββ$) half-life, $(2.14 \pm 0.05) \times 10^{21}$ years, the uncertainty of which is reduced by a factor of 2 compared to our previous result. We measure the parameter $ξ_{31}^{2ν}$, defined as the ratio between the subleading and leading components of the $^{136}$Xe $2νββ$ nuclear matrix element, to be $0.59^{+0.41}_{-0.38}$, which is consistent with theoretical predictions. We also search for Majoron-emitting modes of $^{136}$Xe $ββ$, establishing the most stringent limit for the spectral index $n=7$.

nucl-ex↗
arXiv2026

IndustryCode: A Benchmark for Industry Code Generation

Code generation and comprehension by Large Language Models (LLMs) have emerged as core drivers of industrial intelligence and decision optimization, finding widespread application in fields such as finance, automation, and aerospace. Although recent advancements have demonstrated the remarkable potential of LLMs in general code generation, existing benchmarks are mainly confined to single domains and languages. Consequently, they fail to effectively evaluate the generalization capabilities required for real-world industrial applications or to reflect the coding proficiency demanded by complex industrial scenarios. To bridge this gap, we introduce IndustryCode, the first comprehensive benchmark designed to span multiple industrial domains and programming languages. IndustryCode comprises 579 sub-problems derived from 125 primary industrial challenges, accompanied by rigorous problem descriptions and test cases. It covers a wide range of fields, including finance, automation, aerospace, and remote sensing-and incorporates diverse programming languages such as MATLAB, Python, C++, and Stata. In our evaluation, the top-performing model, Claude 4.5 Opus, achieved an overall accuracy of 68.1% on sub-problems and 42.5% main problems. The benchmark dataset and automated evaluation code will be made publicly available upon acceptance.

cs.SE↗
arXiv2026

Do Phone-Use Agents Respect Your Privacy?

We study whether phone-use agents respect privacy while completing benign mobile tasks. This question has remained hard to answer because privacy-compliant behavior is not operationalized for phone-use agents, and ordinary apps do not reveal exactly what data agents type into which form entries during execution. To make this question measurable, we introduce MyPhoneBench, a verifiable evaluation framework for privacy behavior in mobile agents. We operationalize privacy-respecting phone use as permissioned access, minimal disclosure, and user-controlled memory through a minimal privacy contract, iMy, and pair it with instrumented mock apps plus rule-based auditing that make unnecessary permission requests, deceptive re-disclosure, and unnecessary form filling observable and reproducible. Across five frontier models on 10 mobile apps and 300 tasks, we find that task success, privacy-compliant task completion, and later-session use of saved preferences are distinct capabilities, and no single model dominates all three. Evaluating success and privacy jointly reshuffles the model ordering relative to either metric alone. The most persistent failure mode across models is simple data minimization: agents still fill optional personal entries that the task does not require. These results show that privacy failures arise from over-helpful execution of benign tasks, and that success-only evaluation overestimates the deployment readiness of current phone-use agents. All code, mock apps, and agent trajectories are publicly available at~ https://github.com/FreedomIntelligence/MyPhoneBench.

cs.CR↗
arXiv2026

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models

Reinforcement Learning from Verifiable Rewards (RLVR) has substantially enhanced the reasoning capabilities of large language models in abstract reasoning tasks. However, its application to Large Vision-Language Models (LVLMs) remains constrained by a structural representational bottleneck. Existing approaches generally lack explicit modeling and effective utilization of visual information, preventing visual representations from being tightly coupled with the reinforcement learning optimization process and thereby limiting further improvements in multimodal reasoning performance. To address this limitation, we propose KAWHI (Key-Region Aligned Weighted Harmonic Incentive), a plug-and-play reward reweighting mechanism that explicitly incorporates structured visual information into uniform reward policy optimization methods (e.g., GRPO and GSPO). The method adaptively localizes semantically salient regions through hierarchical geometric aggregation, identifies vision-critical attention heads via structured attribution, and performs paragraph-level credit reallocation to align spatial visual evidence with semantically decisive reasoning steps. Extensive empirical evaluations on diverse reasoning benchmarks substantiate KAWHI as a general-purpose enhancement module, consistently improving the performance of various uniform reward optimization methods. Project page: KAWHI (https://kawhiiiileo.github.io/KAWHI_PAGE/)

cs.CV↗
arXiv2026

Hierarchical Control Framework Integrating LLMs with RL for Decarbonized HVAC Operation

Heating, ventilation, and air conditioning (HVAC) systems account for a substantial share of building energy consumption. Environmental uncertainty and dynamic occupancy behavior bring challenges in decarbonized HVAC control. Reinforcement learning (RL) can optimize long-horizon comfort-energy trade-offs but suffers from exponential action-space growth and inefficient exploration in multi-zone buildings. Large language models (LLMs) can encode semantic context and operational knowledge, yet when used alone they lack reliable closed-loop numerical optimization and may result in less reliable comfort-energy trade-offs. To address these limitations, we propose a hierarchical control framework in which a fine-tuned LLM, trained on historical building operation data, generates state-dependent feasible action masks that prune the combinatorial joint action space into operationally plausible subsets. A masked value-based RL agent then performs constrained optimization within this reduced space, improving exploration efficiency and training stability. Evaluated in a high-fidelity simulator calibrated with real-world sensor and occupancy data from a 7-zone office building, the proposed method achieves a mean PPD of 7.30%, corresponding to reductions of 39.1% relative to DQN, the best vanilla RL baseline in comfort, and 53.1% relative to the best vanilla LLM baseline, while reducing daily HVAC energy use to 140.90~kWh, lower than all vanilla RL baselines. The results suggest that LLM-guided action masking is a promising pathway toward efficient multi-zone HVAC control.

eess.SY↗
arXiv2026

Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models

Native unified multimodal models, which integrate both generative and understanding capabilities, face substantial computational overhead that hinders their real-world deployment. Existing acceleration techniques typically employ a static, monolithic strategy, ignoring the fundamental divergence in computational profiles between iterative generation tasks (e.g., image generation) and single-pass understanding tasks (e.g., VQA). In this work, we present the first systematic analysis of unified models, revealing pronounced parameter specialization, where distinct neuron sets are critical for each task. This implies that, at the parameter level, unified models have implicitly internalized separate inference pathways for generation and understanding within a single architecture. Based on these insights, we introduce a training-free and task-aware acceleration framework, FlashU, that tailors optimization to each task's demands. Across both tasks, we introduce Task-Specific Network Pruning and Dynamic Layer Skipping, aiming to eliminate inter-layer and task-specific redundancy. For visual generation, we implement a time-varying control signal for the guidance scale and a temporal approximation for the diffusion head via Diffusion Head Cache. For multimodal understanding, building upon the pruned model, we introduce Dynamic Token Pruning via a V-Norm Proxy to exploit the spatial redundancy of visual inputs. Extensive experiments on Show-o2 demonstrate that FlashU achieves 1.78$\times$ to 2.01$\times$ inference acceleration across both understanding and generation tasks while maintaining SOTA performance, outperforming competing unified models and validating our task-aware acceleration paradigm. Our code is publicly available at https://github.com/Rirayh/FlashU.

cs.CV↗
arXiv2026

FreeFly-Thinking : Aligning Chain-of-Thought Reasoning with Continuous UAV Navigation

Vision-Language Navigation aims to enable agents to understand natural language instructions and carry out appropriate navigation actions in real-world environments. Most work focuses on indoor settings, with little research in complex outdoor scenes. Current UAV Vision-and-Language Navigation models typically act as black boxes without explicit reasoning. We introduce FreeFly-thinking, an end-to-end VLN framework that converts the UAV agent's egocentric images and language instructions into a series of actions, inspired by environment of urban architecture proposed by OpenFly. We first construct a UAV dataset for navigation task, and then performing natural language chain of thought. We adopt a two-stage training strategy: Supervised fine-tuning and Reinforcement fine-tuning. Experiments on unseen test demonstrate a strong performance, presenting robustness and efficiency in UAV navigation issue.

cs.CV↗
arXiv2026

DRUPI: Dataset Reduction Using Privileged Information

Dataset Condensation (DC) seeks to select or distill samples from large datasets into smaller subsets while preserving performance on target tasks. Existing methods primarily focus on pruning or synthesizing data in the same format as the original dataset, typically being the input data and corresponding labels. However, in DC settings, we find it is possible to synthesize more information beyond the data-label pair as an additional learning target to facilitate model training. In this paper, we introduce Dataset Condensation using Privileged Information (DCPI), which enriches DC by synthesizing privileged information alongside the reduced dataset. This privileged information can take the form of feature labels or attention labels, providing auxiliary supervision to improve model learning. Our findings reveal that effective feature labels must balance between being overly discriminative and excessively diverse, with a moderate level proves optimal for improving the reduced dataset's efficacy. Extensive experiments on ImageNet-1K, CIFAR-10/100 and Tiny ImageNet demonstrate that DCPI integrates seamlessly with existing dataset condensation methods, offering significant performance gains.

cs.CV↗
arXiv2026

Towards Principled Dataset Distillation: A Spectral Distribution Perspective

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic counterparts for efficient model training. However, existing DD methods exhibit substantial performance degradation on long-tailed datasets. We identify two fundamental challenges: heuristic design choices for distribution discrepancy measure and uniform treatment of imbalanced classes. To address these limitations, we propose Class-Aware Spectral Distribution Matching (CSDM), which reformulates distribution alignment via the spectrum of a well-behaved kernel function. This technique maps the original samples into frequency space, resulting in the Spectral Distribution Distance (SDD). To mitigate class imbalance, we exploit the unified form of SDD to perform amplitude-phase decomposition, which adaptively prioritizes the realism in tail classes. On CIFAR-10-LT, with 10 images per class, CSDM achieves a 14.0% improvement over state-of-the-art DD methods, with only a 5.7% performance drop when the number of images in tail classes decreases from 500 to 25, demonstrating strong stability on long-tailed data.

cs.CV↗
arXiv2026

Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet how visual evidence is integrated during reasoning remains poorly understood. We explore multimodal RLVR through the lens of cross-modal attention connectivity and find that only a small fraction of tokens (approximately 15%) exhibit strong visual-textual coupling. These high-connectivity tokens act as anchors that ground reasoning in the image, while the majority follow linguistic patterns. During RLVR training, credit assignment naturally concentrates on these anchors, sharpening their visual grounding over time. Building on this insight, we propose Anchor-Token Reinforcement Learning (AT-RL), a lightweight framework that selectively reinforces high-connectivity tokens via graph-based clustering of attention topology. Evaluated across the series (3B-32B), AT-RL introduces only 1.2% overhead yet enables the 32B model to surpass the 72B-Instruct baseline on MathVista (80.2), with consistent gains observed across STEM, video and general tasks. Conversely, training solely on low-connectivity tokens causes severe degradation, confirming that effective multimodal RL hinges on precise credit assignment to visual anchors. Our work reveals that reasoning quality is governed not by token quantity but by the fidelity of cross-modal anchoring.

cs.AI↗
arXiv2026

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall, pre-training is shifting from more tokens to better tokens. However, existing methods either rely on heuristic static filters that ignore training dynamics, or use dynamic yet optimizer-agnostic criteria based on raw gradients. We propose OPUS (Optimizer-induced Projected Utility Selection), a dynamic data selection framework that defines utility in the optimizer-induced update space. OPUS scores candidates by projecting their effective updates, shaped by modern optimizers, onto a target direction derived from a stable, in-distribution proxy. To ensure scalability, we employ Ghost technique with CountSketch for computational efficiency, and Boltzmann sampling for data diversity, incurring only 4.7\% additional compute overhead. OPUS achieves remarkable results across diverse corpora, quality tiers, optimizers, and model scales. In pre-training of GPT-2 Large/XL on FineWeb and FineWeb-Edu with 30B tokens, OPUS outperforms industrial-level baselines and even full 200B-token training. Moreover, when combined with industrial-level static filters, OPUS further improves pre-training efficiency, even with lower-quality data. Furthermore, in continued pre-training of Qwen3-8B-Base on SciencePedia, OPUS achieves superior performance using only 0.5B tokens compared to full training with 3B tokens, demonstrating significant data efficiency gains in specialized domains.

cs.CL↗
arXiv2026

Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning

As supervised fine-tuning (SFT) evolves from a lightweight post-training step into a compute-intensive phase rivaling mid-training in scale, data efficiency has become critical for aligning large language models (LLMs) under tight budgets. Existing data pruning methods suffer from a fragmented design: they operate either at the sample level or the token level in isolation, failing to jointly optimize both dimensions. This disconnect leads to significant inefficiencies--high-value samples may still contain redundant tokens, while token-level pruning often discards crucial instructional or corrective signals embedded in individual examples. To address this bottleneck, we introduce the Error-Uncertainty (EU) Plane, a diagnostic framework that jointly characterizes the heterogeneous utility of training data across samples and tokens. Guided by this insight, we propose Quadrant-based Tuning (Q-Tuning), a unified framework that strategically coordinates sample pruning and token pruning. Q-Tuning employs a two-stage strategy: first, it performs sample-level triage to retain examples rich in informative misconceptions or calibration signals; second, it applies an asymmetric token-pruning policy, using a context-aware scoring mechanism to trim less salient tokens exclusively from misconception samples while preserving calibration samples in their entirety. Our method sets a new state of the art across five diverse benchmarks. Remarkably, on SmolLM2-1.7B, Q-Tuning achieves a +38\% average improvement over the full-data SFT baseline using only 12.5\% of the original training data. As the first dynamic pruning approach to consistently outperform full-data training, Q-Tuning provides a practical and scalable blueprint for maximizing data utilization in budget-constrained LLM SFT.

cs.CL↗
arXiv2026

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis

Advancing complex reasoning in large language models relies on high-quality, verifiable datasets, yet human annotation remains cost-prohibitive and difficult to scale. Current synthesis paradigms often face a recurring trade-off: maintaining structural validity typically restricts problem complexity, while relaxing constraints to increase difficulty frequently leads to inconsistent or unsolvable instances. To address this, we propose Agentic Proposing, a framework that models problem synthesis as a goal-driven sequential decision process where a specialized agent dynamically selects and composes modular reasoning skills. Through an iterative workflow of internal reflection and tool-use, we develop the Agentic-Proposer-4B using Multi-Granularity Policy Optimization (MGPO) to generate high-precision, verifiable training trajectories across mathematics, coding, and science. Empirical results demonstrate that downstream solvers trained on agent-synthesized data significantly outperform leading baselines and exhibit robust cross-domain generalization. Notably, a 30B solver trained on only 11,000 synthesized trajectories achieves a state-of-the-art 91.6% accuracy on AIME25, rivaling frontier-scale proprietary models such as GPT-5 and proving that a small volume of high-quality synthetic signals can effectively substitute for massive human-curated datasets.

cs.AI↗
arXiv2026

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction

Multimodal Large Language Models (MLLMs) have significantly advanced vision-language understanding. However, even state-of-the-art models struggle with geometric reasoning, revealing a critical bottleneck: the extreme scarcity of high-quality image-text pairs. Human annotation is prohibitively expensive, while automated methods fail to ensure fidelity and training effectiveness. Existing approaches either passively adapt to available images or employ inefficient random exploration with filtering, decoupling generation from learning needs. We propose Socratic-Geo, a fully autonomous framework that dynamically couples data synthesis with model learning through multi-agent interaction. The Teacher agent generates parameterized Python scripts with reflective feedback (Reflect for solvability, RePI for visual validity), ensuring image-text pair purity. The Solver agent optimizes reasoning through preference learning, with failure paths guiding Teacher's targeted augmentation. Independently, the Generator learns image generation capabilities on accumulated "image-code-instruction" triplets, distilling programmatic drawing intelligence into visual generation. Starting from only 108 seed problems, Socratic-Solver achieves 49.11 on six benchmarks using one-quarter of baseline data, surpassing strong baselines by 2.43 points. Socratic-Generator achieves 42.4% on GenExam, establishing new state-of-the-art for open-source models, surpassing Seedream-4.0 (39.8%) and approaching Gemini-2.5-Flash-Image (43.1%).

cs.CV↗
arXiv2026

Grounding and Enhancing Informativeness and Utility in Dataset Distillation

Dataset Distillation (DD) seeks to create a compact dataset from a large, real-world dataset. While recent methods often rely on heuristic approaches to balance efficiency and quality, the fundamental relationship between original and synthetic data remains underexplored. This paper revisits knowledge distillation-based dataset distillation within a solid theoretical framework. We introduce the concepts of Informativeness and Utility, capturing crucial information within a sample and essential samples in the training set, respectively. Building on these principles, we define optimal dataset distillation mathematically. We then present InfoUtil, a framework that balances informativeness and utility in synthesizing the distilled dataset. InfoUtil incorporates two key components: (1) game-theoretic informativeness maximization using Shapley Value attribution to extract key information from samples, and (2) principled utility maximization by selecting globally influential samples based on Gradient Norm. These components ensure that the distilled dataset is both informative and utility-optimized. Experiments demonstrate that our method achieves a 6.1\% performance improvement over the previous state-of-the-art approach on ImageNet-1K dataset using ResNet-18.

cs.LG↗
arXiv2026

Performance Test and Circuit Simulation for R12699-406-M4 Photomultiplier Tube Base

The next-generation liquid xenon experiments like PandaX-xT target an energy range from sub-keV to multi-MeV to address the requirement of multiple physics searches. The Hamamatsu R12699-406-M4 photomultiplier tubes (PMTs) were developed and selected as photon sensors for PandaX-xT. Their voltage-divider base is optimized for a broad dynamic range, from single-photoelectron (SPE) sensitivity to 30~nC collected charge (matching the 2.5~MeV Q-value of $^{136}$Xe neutrinoless double beta decay~(NLDBD)). Using a dedicated test bench, we characterize the saturation and suppression responses of R12699-406-M4 PMTs with this base design. Based on measured PMT-base responses, we develop a circuit simulation model that accurately reproduces the physical mechanisms underlying these effects with key parameters tuned via experimental data. The combined simulation and bench-test approach guides base design and optimization, enabling improved detector dynamic range and supporting future saturation and suppression correction studies in data analysis.

physics.ins-det↗
arXiv2026

GPS-Synchronized Monitoring of Core-collapse Supernova Bursts with PandaX-4T via Coherent Elastic Neutrino Nuclear Scattering

The landmark detection of neutrinos from SN1987A marked the dawn of neutrino astrophysics. The neutrino burst provided essential insights into fundamental properties of neutrinos, and served as key probes of stellar evolution and supernova dynamics. The recent advancement in coherent elastic neutrino-nucleus scattering enables the detection of core-collapse supernova burst neutrinos using tonne-scale liquid xenon detectors originally designed for dark matter direct detection. Leveraging this capability, we developed and deployed an online supernova monitoring system for the PandaX-4T experiment. This system features a GPS module with millisecond-level timing precision, a low false-alarm rate, and high sensitivity to galactic core-collapse supernova explosion events. The methodology is robust, directly scalable, and planned for implementation in the next-generation PandaX-20T experiment.

hep-ex↗
arXiv2025

Search for Light Dark Matter with 259-day data in PandaX-4T

We present a search for light dark matter particles through their interactions with atomic electrons and nucleons, utilizing PandaX-4T data with an effective exposure of 1.04 tonne$\cdot$year for ionization-only data and 1.20 tonne$\cdot$year for paired data. Our analysis focuses on the energy range (efficiency$>$0.01) of approximately 0.33 to 3 keV for nuclear recoils, and from 0.04 to 0.39 keV for electronic recoils. We establish the most stringent constraints on spin-independent dark matter-nucleon interactions within a mass range of 2.5 to 5.0 GeV/$c^2$, spin-dependent neutron-only interactions within 2.0 to 5.3 GeV/$c^2$, and spin-dependent proton-only interactions within 2.0 to 3.8 GeV/$c^2$. Their corresponding limits at 3\,GeV/$c^2$ are $1.1 \times 10^{-43}$, $1.6 \times 10^{-38}$, and $5.6 \times 10^{-37}$\,cm$^2$, respectively. Additionally, our results improve the upper limits on the dark matter-electron scattering cross-section by a factor of 1.5 and 9.3 for heavy and light mediator scenarios respectively within 50 MeV/$c^2$ to 10 GeV/$c^2$, compared with previous best results.

hep-ex↗