arXiv subjects

Ruiyang Zhang

Publications and source records attributed to Ruiyang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Why Formal Monitors Fail: Attack Distribution Entropy as a Coverage Bound for LTL-Based LLM Agent Safety

Runtime safety monitors based on Linear Temporal Logic (LTL) and finite automata (FSA) are increasingly deployed to intercept unsafe tool-call sequences in LLM agents. Yet the same monitor achieves 68-75% attack coverage on some model architectures and near-zero on others, with no explanation from capability scores, training data, or prompt design. We provide the missing theory. We prove that the recall of any fixed-invariant FSA monitor is bounded above by the concentration of the attack distribution: the fraction of attacks covered by the k most frequent trigger-completion patterns. When attacks concentrate (low Shannon entropy), a small fixed invariant set achieves high recall; when they disperse across many structurally distinct patterns (high entropy), no fixed invariant set of tractable size can, regardless of how the invariants were derived. We validate this entropy-coverage bound across eight frontier LLM architectures. GPT-class and DeepSeek backends yield highly concentrated attacks (H ~ 0.24 bits; one pattern covers 96%), explaining 68-75% recall; Gemini variants yield high-entropy distributions (H ~ 2.81 bits; 7 clusters each <= 7%), explaining near-zero recall (6-13%), invariant to architecture-matched retraining. Entropy accounts for 76% of variance in coverage (Pearson r = -0.87, p = 0.005, 95% CI [-0.98, -0.78]), holding under leave-one-out (r in [-0.91, -0.82]). We introduce a pre-deployment entropy test that predicts monitor coverage from a small attack sample, enabling architecture-aware monitor selection before deployment. The bound and test are architecture-agnostic and apply to any FSA-based runtime monitor over discrete action sequences.

cs.CR↗

arXiv2026

Memdora: Designing Cognitively-Grounded Flashcard Interactions for AI-Powered Spaced Repetition

Spaced repetition systems (SRS) have demonstrated robust effects on long-term retention, yet existing tools reduce the flashcard interaction to a single binary gesture: flip and self-rate. This impoverished interaction model fails to leverage decades of cognitive science evidence on retrieval practice, and requires learners to context-switch out of their reading flow to create cards manually. We present Memdora, a cross-platform AI spaced repetition system that addresses these limitations through four contributions: (1) a taxonomy of 17 cognitively-grounded interaction types across three learning categories -- Language (6 types), By Heart (1 type with 3 retrieval modes), and Exam (10 types) -- each grounded in peer-reviewed cognitive science evidence, with per-type design rationale and citations documented in this paper; (2) a unified AI generation pipeline that collapses card creation to a single gesture at the point of reading across web, mobile, and three browser extensions (Chrome, Edge, Firefox); (3) a collaborative layer enabling users to publish decks with live synchronization: followers discover and follow decks via a public feed, and any edits the deck owner makes propagate instantly to all followers while each follower maintains independent FSRS-6 scheduling state; and (4) an effort-based behavioral reward system that incentivizes actual cognitive engagement rather than mere app presence. Memdora integrates FSRS-6, the current state-of-the-art spaced repetition algorithm, and is deployed publicly on iOS, Android, Web, and three browser extensions. We describe the design rationale for each interaction type, discuss how the system advances beyond prior AI flashcard systems including SmartFlash and KARL, and outline implications for educational technology design.

cs.HC↗

arXiv2026

Incentives and Market Structure in Intent-Based Exchanges: Evidence from a Solver-Reward Reform

Intent-based decentralized exchanges delegate execution to a competitive class of agents -- solvers -- whose behavior is shaped by protocol-designed reward rules. We measure how a change to those rules reshapes who captures value, using a governance-dated natural experiment: CoW Protocol CIP-74 (effective 8 December 2025), which replaced a fixed solver-reward cap with one tied to protocol revenue and introduced an ad-valorem volume fee. Using daily solver shares over 395 days, we find the reform reallocated trading value by order size. The robust signature is a monotone size gradient: concentration fell in small orders and rose in large ones across four order-value buckets (Spearman rho=1.00, exact permutation p=0.042) -- a pattern that survives dropping the single largest solver. Aggregate concentration also rose (volume-weighted HHI 0.176->0.241), substantially carried by the incumbent top solver. By trade count the market de-concentrated (count-HHI -0.060). A simple solver-economics model rationalizes the pattern: an ad-valorem fee is competitively neutral, while a revenue-linked reward cap raises the marginal payoff to inventory-rich solvers on large orders -- consistent with restricted-entry predictions (Chitra et al. 2024). A control venue (UniswapX) shows no matching break. We detect no change in average execution quality (~7 bps bound). A triple-difference exploiting a February 2026 fee cut is directionally consistent but underpowered. Reward design measurably reallocates who captures value in intent markets, without moving the average price users receive.

cs.CR↗

arXiv2026

Enhancing In-context Panoramic Generation via Geometric-aware Pretraining

In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality training data tailored to in-context panoramic tasks, we propose Canvas360Dataset, a collection of 1M high-quality paired panoramic samples for style transfer, inpainting, outpainting, and editing, enabling effective supervision across diverse in-context generation scenarios. On the modeling side, Canvas360 enhances text-to-panorama generation through parallel depth generation, velocity circular padding, and similarity loss regularization, enabling the model to learn geometry-aware representations, capture object distortion details, and improve geometric consistency and global coherence. Furthermore, empowered by strong panoramic priors, Canvas360 enables a unified in-context panoramic generation framework that supports diverse downstream tasks via token-level concatenation, surpassing prior methods in both task coverage and modeling flexibility. Extensive experiments show that Canvas360 improves panoramic image fidelity, achieving particularly strong performance on the panorama-specific FAED metric and competitive or leading results across the reported quantitative evaluations. More information can be found on our project page: https://zry000.github.io/Canvas360/

cs.CV↗

arXiv2026

TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation

Dexterous manipulation in everyday environments requires both anticipation and reaction: a robot must predict how contact should evolve while rapidly correcting local errors caused by slip, misalignment, unstable grasping, or force mismatch. Vision and language provide semantic and geometric guidance, but they cannot reliably reveal hidden contact states such as force, slip, and contact stability. Although tactile sensing exposes these physical cues, most existing policies treat touch as a low-frequency observation stream within a monolithic action model, coupling slow task reasoning, action generation, and fast contact feedback in a single loop. We introduce TouchWorld, a predictive-and-reactive tactile foundation model for dexterous manipulation. TouchWorld uses a hierarchical policy that separates vision-language subtask planning, tactile world-model prediction, visuo-tactile goal-conditioned action generation, and high-frequency tactile residual refinement. A High-Level Planning Layer produces executable subtasks and predicts tactile subgoals; a Visuo-Tactile Goal-Conditioned Policy generates nominal action chunks; and a Tactile-Conditioned Refinement Policy performs online residual correction using recent tactile and proprioceptive feedback. By using touch as both a predictive contact reference and a fast feedback signal, TouchWorld preserves the semantic generalization of vision-language-action policies while improving local contact adaptation. Across six long-horizon and contact-rich dexterous manipulation tasks, TouchWorld achieves 65.0% success in the clean setting and 53.7% success under human perturbations, outperforming the strongest baseline by 15.7 and 18.5 percentage points, respectively.

cs.RO↗

arXiv2026

The 1st PortraitCraft Challenge: A CVPR 2026 Workshop Competition on Portrait Composition Understanding and Generation

This paper presents an overview of the inaugural PortraitCraft Challenge, held as one of the official competitions at CVPR 2026. The challenge focuses on portrait composition understanding and generation, aiming to advance AI research in portrait aesthetics analysis and controllable image synthesis. Unlike existing datasets and tasks that primarily focus on global aesthetic scoring, PortraitCraft introduces a unified evaluation framework comprising two complementary tracks. Track 1 requires models to perform structured portrait composition understanding, and Track 2 requires models to generate portrait images from structured composition descriptions under explicit compositional constraints. To support the challenge, we constructed and publicly released a large-scale portrait composition dataset consisting of approximately 50,000 curated real portrait images, providing multi-level supervision. This report describes the challenge setup, evaluation protocols, dataset composition, and final results, along with an analysis of the technical characteristics of the submitted solutions. The PortraitCraft Challenge provides a standardized and reproducible platform for research on portrait composition understanding and generation, and is expected to foster further progress in the fields of portrait aesthetics and controllable image generation.

cs.CV↗

arXiv2026

UniSHARP: Universal Sharp Monocular View Synthesis

In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from conventional perspective cameras to wide-field-of-view, fisheye and omnidirectional panoramic settings. To overcome the pinhole-specific assumptions of SHARP, our key idea is to align various images in a unified omnidirectional latent space. Thus, we propose UniSHARP, which performs implicit alignment in both feature and Gaussian spaces. Specifically, Gaussian primitives are arranged along rays and radial distances in a ray-based universal representation, while 2D semantic and 3D spatial features extracted from UniK3D-inspired encoders are jointly decoded to generate the complete Gaussian cloud. To comprehensively evaluate our method, we construct a benchmark covering diverse imaging systems across various scenes. The benchmark is further stratified by field of view (FoV) to enable fine-grained assessment of the universal monocular rendering task. Extensive experiments on the proposed benchmark demonstrate the effectiveness of UniSHARP, outperforming alternative methods by a large margin. The project page can be found at: https://insta360-research-team.github.io/Unisharp-website/

cs.CV↗

arXiv2026

Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This paper presents a systematic empirical study using TravelPlanner, a challenging testbed requiring tool orchestration to satisfy multifaceted constraints. We decompose the agentic RL design space along 5 axes: reward shaping, model scaling, data composition, algorithm selection, and environmental stability. Our controlled experiments yield 7 key takeaways, e.g., (1) reward and algorithm choices are scale-dependent as smaller models benefit from staged rewards and enhanced exploration, whereas larger models converge efficiently with simpler dense rewards, (2) ~ 1K training samples with a balanced difficulty mixture mark a sweet spot for both in-domain and out-of-domain performance, and (3) environmental stability is critical to prevent policy degradation. Based on our distilled recipe, our RL-trained models achieve state-of-the-art performance on TravelPlanner, significantly outperforming leading LLMs.

cs.LG↗

arXiv2026

VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning

Large models are increasingly becoming autonomous agents that interact with real-world environments and use external tools to augment their static capabilities. However, most recent progress has focused on text-only large language models, which are limited to a single modality and therefore have narrower application scenarios. On the other hand, multimodal large models, while offering stronger perceptual capabilities, remain limited to static knowledge and lack the ability to access and leverage up-to-date web information. In this paper, we propose VSearcher, turning static multimodal model into multimodal search agent capable of long-horizon, multi-turn tool use in real-world web environments, including text search, image search, and web browsing, via reinforcement learning. Specifically, we introduce Iterative Injection Data Synthesis pipeline to generate large-scale, complex multimodal QA questions, which are further filtered with comprehensive metrics to ensure high quality and sufficient difficulty. We then adopt an SFT-then-RL training pipeline to turn base multimodal models to agent capable of multi-turn tool calling in real-world web environments. Besides, we propose a multimodal search benchmark MM-SearchExam dedicated to evaluating search capabilities of multimodal search agents, which proves highly challenging for recent proprietary models. Extensive evaluations across multiple multimodal search benchmarks reveal effectiveness of our method. VSearcher achieves superior performance compared to recent multimodal search agents and even surpasses several proprietary models on multimodal web search tasks.

cs.CV↗

arXiv2026

SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models

Despite the empirical success of extensive, step-by-step reasoning in large multimodal models, long reasoning processes inevitably incur substantial computational overhead, i.e., in terms of higher token costs and increased response time, which undermines inference efficiency. In contrast, humans often employ sketch-style reasoning: a concise, goal-directed cognitive process that prioritizes salient information and enables efficient problem-solving. Inspired by this cognitive efficiency, we propose SketchThinker-R1, which incentivizes sketch-style reasoning ability in large multimodal models. Our method consists of three primary stages. In the Sketch-Mode Cold Start stage, we convert standard long reasoning process into sketch-style reasoning and finetune base multimodal model, instilling initial sketch-style reasoning capability. Next, we train SketchJudge Reward Model, which explicitly evaluates thinking process of model and assigns higher scores to sketch-style reasoning. Finally, we conduct Sketch-Thinking Reinforcement Learning under supervision of SketchJudge to further generalize sketch-style reasoning ability. Experimental evaluation on four benchmarks reveals that our SketchThinker-R1 achieves over 64% reduction in reasoning token cost without compromising final answer accuracy. Qualitative analysis further shows that sketch-style reasoning focuses more on key cues during problem solving.

cs.CV↗

arXiv2025

A Low Background Beta Detection System using a Time Projection Chamber

In this paper, we present a Time Projection Chamber (TPC) system for low-background beta radiation measurements. The system consists of a TPC with two-dimensional-strip readout Micromegas and an anti-coincidence detector with readout pads for cosmic ray veto. The detector system utilize an AGET-based waveform sampling system for data acquisition. The beta detection capability of the system was verified through experimental test using $^{90}$Sr beta source. Additionally, a dedicated simulation program based on Geant4 was developed to model the entire detection process, including responses to both the beta source and background radiation. Simulation results were compared with experimental data for both beta and background samples, showing good agreements. The simulation samples were utilized to optimize and train classification models for beta and background discrimination. By applying the selected model into test data, the system achieved a background rate of 0.49 $\rm cpm/cm^2$ while retaining more than 55% of $^{90}$Sr beta signals within a 7 cm diameter detection region. Further analysis revealed that approximately 70% of the background originates from environmental gamma radiation, while the remaining contribution mainly comes from intrinsic radioactivity of detector materials, particularly the FR-4 based field cage and readout plane. Based on the knowledge gained from the experiments and simulations, an optimization of the TPC system has been proposed, with simulation predicting a potential reduction of the background rate to 0.0012 $\rm cpm/cm^2$.

physics.ins-det↗

arXiv2025

SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing

With the rapid advancement of text-to-image (T2I) models, ensuring their safety has become increasingly critical. Existing safety approaches can be categorized into training-time and inference-time methods. While inference-time methods are widely adopted due to their cost-effectiveness, they often suffer from limitations such as over-refusal and imbalance between safety and utility. To address these challenges, we propose a multi-round safety editing framework that functions as a model-agnostic, plug-and-play module, enabling efficient safety alignment for any text-to-image model. Central to this framework is MR-SafeEdit, a multi-round image-text interleaved dataset specifically constructed for safety editing in text-to-image generation. We introduce a post-hoc safety editing paradigm that mirrors the human cognitive process of identifying and refining unsafe content. To instantiate this paradigm, we develop SafeEditor, a unified MLLM capable of multi-round safety editing on generated images. Experimental results show that SafeEditor surpasses prior safety approaches by reducing over-refusal while achieving a more favorable safety-utility balance.

cs.CV↗

arXiv2025

Conceptual Design Report of Super Tau-Charm Facility: The Accelerator

Electron-positron colliders operating in the GeV region of center-of-mass energies or the Tau-Charm energy region, have been proven to enable competitive frontier research, due to its several unique features. With the progress of high energy physics in the last two decades, a new-generation Tau-Charm factory, Super Tau Charm Facility (STCF) has been actively promoting by the particle physics community in China. STCF holds great potential to address fundamental questions such as the essence of color confinement and the matter-antimatter asymmetry in the universe in the next decades. The main design goals of STCF are with a center-of-mass energy ranging from 2 to 7 GeV and a peak luminosity surpassing 5*10^34 cm^-2s^-1 that is optimized at a center-of-mass energy of 4 GeV, which is about 50 times that of the currently operating Tau-Charm factory - BEPCII. The STCF accelerator is composed of two main parts: a double-ring collider with the crab-waist collision scheme and an injector that provides top-up injections for both electron and positron beams. As a typical third-generation electron-positron circular collider, the STCF accelerator faces many challenges in both accelerator physics and technology. In this paper, the conceptual design of the STCF accelerator complex is presented, including the ongoing efforts and plans for technological R&D, as well as the required infrastructure. The STCF project aims to secure support from the Chinese central government for its construction during the 15th Five-Year Plan (2026-2030) in China.

physics.acc-ph↗

arXiv2025

MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval

Document Understanding is a foundational AI capability with broad applications, and Document Question Answering (DocQA) is a key evaluation task. Traditional methods convert the document into text for processing by Large Language Models (LLMs), but this process strips away critical multi-modal information like figures. While Large Vision-Language Models (LVLMs) address this limitation, their constrained input size makes multi-page document comprehension infeasible. Retrieval-augmented generation (RAG) methods mitigate this by selecting relevant pages, but they rely solely on semantic relevance, ignoring logical connections between pages and the query, which is essential for reasoning. To this end, we propose MoLoRAG, a logic-aware retrieval framework for multi-modal, multi-page document understanding. By constructing a page graph that captures contextual relationships between pages, a lightweight VLM performs graph traversal to retrieve relevant pages, including those with logical connections often overlooked. This approach combines semantic and logical relevance to deliver more accurate retrieval. After retrieval, the top-$K$ pages are fed into arbitrary LVLMs for question answering. To enhance flexibility, MoLoRAG offers two variants: a training-free solution for easy deployment and a fine-tuned version to improve logical relevance checking. Experiments on four DocQA datasets demonstrate average improvements of 9.68% in accuracy over LVLM direct inference and 7.44% in retrieval precision over baselines. Codes and datasets are released at https://github.com/WxxShirley/MoLoRAG.

cs.CL↗

arXiv2025

Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models

Large Multimodal Models (LMMs), harnessing the complementarity among diverse modalities, are often considered more robust than pure Language Large Models (LLMs); yet do LMMs know what they do not know? There are three key open questions remaining: (1) how to evaluate the uncertainty of diverse LMMs in a unified manner, (2) how to prompt LMMs to show its uncertainty, and (3) how to quantify uncertainty for downstream tasks. In an attempt to address these challenges, we introduce Uncertainty-o: (1) a model-agnostic framework designed to reveal uncertainty in LMMs regardless of their modalities, architectures, or capabilities, (2) an empirical exploration of multimodal prompt perturbations to uncover LMM uncertainty, offering insights and findings, and (3) derive the formulation of multimodal semantic uncertainty, which enables quantifying uncertainty from multimodal responses. Experiments across 18 benchmarks spanning various modalities and 10 LMMs (both open- and closed-source) demonstrate the effectiveness of Uncertainty-o in reliably estimating LMM uncertainty, thereby enhancing downstream tasks such as hallucination detection, hallucination mitigation, and uncertainty-aware Chain-of-Thought reasoning.

cs.CV↗

arXiv2025

Simulation of MAPS and a MAPS-based Inner Tracker for the Super Tau-Charm Facility

Monolithic Active Pixel Sensors (MAPS) are a promising detector candidate for the inner tracker of the Super Tau-Charm Facility (STCF). To evaluate the performance of MAPS and the MAPS-based inner tracker, a dedicated simulation workflow has been developed, offering essential insights for detector design and optimization. The intrinsic characteristics of MAPS, designed using several fabrication processes and pixel geometries, were investigated through a combination of Technology Computer Aided Design (TCAD) and Monte Carlo simulations. Simulations were conducted with both minimum ionizing particles and $^{55}$Fe X-rays to assess critical parameters such as detection efficiency, cluster size, spatial resolution, and charge collection efficiency. Based on these evaluations, a MAPS sensor featuring a strip-like pixel and a high-resistivity epitaxial layer is selected as the baseline sensor design for the STCF inner tracker due to its excellent performance. Using this optimized MAPS design, a three-layer MAPS-based inner tracker was modeled and simulated. The simulation demonstrated an average detection efficiency exceeding 99%, spatial resolutions of 44.8$\rm{\mu m}$ in the $z$ direction and 8.2$\rm{\mu m}$ in the $r-\phi$ direction, and an intrinsic sensor time resolution of 5.9ns for 1GeV/c $\mu^-$ particles originating from the interaction point. These promising results suggest that the MAPS-based inner tracker fulfills the performance requirements of the STCF experiment.

physics.ins-det↗

arXiv2025

A Low Power Monolithic Active Pixel Sensor Prototype for the STCF Inner Tracker

The Super Tau-Charm Facility (STCF) is a proposed $e^+e^-$ collider with a peak luminosity 100 times higher than that of the present tau-charm factory. The inner tracker (ITK) of STCF should feature a low material budget and high readout speed. Under these requirements, the monolithic active pixel sensor (MAPS) is considered as a promising candidate for the ITK. To minimize the power consumption of MAPS (for low material budget), larger-size sensors are proposed to reduce the scale of the readout circuitry while preserving the required position resolution. Multiple sensors with varying dimensions and structures were designed and integrated in several prototype chips for performance comparison, fabricated in a 180~nm CIS process. The in-pixel readout circuit can also provide time of arrival (ToA) and time-over-threshold (ToT) of the hit signal, with a least significant bit (LSB) of 50 ns. The peripheral readout circuit performs operations including timestamp correction, data aggregation, caching, framing, 8b/10b encoding, and serialization. According to simulation, the power consumption for a full-scale chip is about 55.7 mW/cm2. Preliminary measurements have been conducted on the prototype chips.

physics.ins-det↗

arXiv2025

Further Characterization of the JadePix-3 CMOS Pixel Sensor for the CEPC Vertex Detector: in Dependence of Substrate Reverse Bias

The Circular Electron-Positron Collider (CEPC), a proposed next-generation $e^+e^-$ collider to enable high-precision studies of the Higgs boson and potential new physics, imposes rigorous demands on detector technologies, particularly the vertex detector. JadePix-3 is a prototype Monolithic Active Pixel Sensor (MAPS) designed for the CEPC vertex detector. This paper presents a detailed laboratory-based characterization of the JadePix-3 sensor, focusing on the previously under-explored effects of substrate reverse bias voltage on key performance metrics: charge collection efficiency, average cluster size, and hit efficiency of laser. Systematic testing demonstrated that JadePix-3 operates reliably under reverse bias, exhibiting a reduced input capacitance, an expanded depletion region, enhanced charge collection efficiency, and a lower fake-hit rate. These findings confirm the sensor's potential for high-precision particle tracking and vertexing at the CEPC while offering valuable references for future iterational R\&D of the JadePix series.

physics.ins-det↗