Searcharxiv⌕ Search

arXiv subjects

Bin Li

Publications and source records attributed to Bin Li.

At least 19 recordsLinked to original sources
arXiv2026

EP-LVMQA: Evidence-Preserving Coarse-to-Fine Localization for Low-Quality Long Video Moment Question Answering

Long instructional videos are increasingly used in medical education, industrial training, and procedural knowledge transfer, yet their evidence is often incomplete or unreliable: subtitles may be missing, ASR noisy, OCR sparse, and decisive actions briefly shown without narration. Existing VideoQA systems typically return labels or free-form text, making answer support difficult to inspect. We study Long Video Moment Question Answering (LVMQA), where a system returns timestamped answer-supporting evidence. We propose EP-LVMQA, an evidence-preserving coarse-to-fine framework comprising an Uncertainty-Aware Multimodal Evidence Timeline, a Coarse Evidence Planner, and an Evidence-Conditioned Fine Localizer. An evidence card transfers planner scores, matched cues, source-confidence proxies, modality-specific evidence, neighboring context, and a temporal prior between the latter two modules. On MedVidQA, EP-LVMQA achieves 26.1 R1@0.5 and 31.8 mIoU, improving the strongest non-ours results by 6.3 and 5.1 points. It raises Suff.@2 and Ver.@2 to 25.4 and 22.6, gains of 9.5 and 8.8 points. Under matched low-quality perturbations, average relative degradation is reduced from the strongest non-ours value of 14.6% to 11.1%. On Ego4D-NLQ and QVHighlights, EP-LVMQA remains broadly comparable to established task-specific localization methods.

cs.CV↗
arXiv2026

An Agentic Framework for Quality-Aware and Scenario-Adaptive Image Compression

Despite decades of progress, image codecs remain difficult to adapt to diverse real-world compression scenarios for two main reasons. First, most image codecs are optimized for a specific objective and require substantial redevelopment when the compression goal changes. Second, they typically assume clean inputs, whereas sensor-captured images often contain degradations that alter rate-quality behavior. To address these challenges, we propose Practical Image Coding Agents (PICA), a multi-agent framework that adapts existing codecs to diverse user requirements and potentially degraded inputs. PICA consists of four collaborative agents: a Perception agent that interprets user intent and analyzes image content, an Improvement agent that jointly considers bitrate and reconstruction quality to guide pre-coding restoration, a Coding agent that refines quality-control settings from global to regional levels, and an After-coding improvement agent that addresses residual degradations and compression-induced artifacts through restoration guided solely by image quality. To enable codec-agnostic regional adaptation, we introduce Agentic ROI Coding (AROIC), which treats the codec as a black box and allows the agent to automatically schedule, execute, evaluate, and reflect ROI coding plans without architectural modifications or codec-specific retraining. We integrate these four agents with a Scenario-Guided Quality-Rate (SGQR) evaluation strategy to enable more effective scenario-adaptive compression across heterogeneous codecs. Comprehensive experiments on clean, noisy, and blurred images across standard, perceptual, and machine-vision compression scenarios demonstrate that PICA consistently enhances the compression performance of both the conventional H.266/VVC codec and the neural Cheng2020 codec, outperforming competing compression methods on the Kodak, CLIC2020, and HEVC datasets.

cs.CV↗
arXiv2026

Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage

Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. Despite substantial progress, a unified anti-forgery foundation model covering such a broad threat spectrum remains absent. In this paper, we present Venus-DefakerOne2, which substantially extends the forensic capability boundary along both the forgery-form and media-type dimensions. Trained on tens of millions of open-source and in-house samples, it incorporates two key designs. Tide-Style-Tuning alternates LoRA and full-parameter fine-tuning to balance computational efficiency, generalization, and hard-sample fitting while mitigating catastrophic forgetting. Entropy-based Test Adaptation determines the optimal prediction modality by analyzing prediction entropy. Venus-DefakerOne2 achieves new state-of-the-art performance across a comprehensive suite of benchmarks, including DeepFake faces (96.7%), AI-generated images (93.3%), tampered documents (87.6%), manipulated natural images (89.6%), physical spoofs (93.1%), and AI-generated videos (96.0%). It significantly outperforms both specialized expert models and its predecessor, DefakerOne, establishing itself as a powerful and versatile foundation model for binary-decision forensic tasks.

cs.CV↗
arXiv2026

FiDeR: Denoising Astronomical Images at the Observational Resolution

We present Finite-iteration Deconvolution--Reconvolution Denoising (FiDeR), a method for reducing noise in astronomical images while retaining approximately the input point-spread function (PSF). We first apply a finite number of Richardson--Lucy (RL) iterations to the nonnegative source-plus-background image. We then measure the response of a calibration point source processed with the same settings and derive a reconvolution kernel matched to the observational PSF. The calibration includes the background-to-source flux ratio. We compare FiDeR with six denoisers using simulated point-source and mixed stellar--galaxy fields, and observations from the James Webb Space Telescope Near-Infrared Camera (NIRCam) and Mid-Infrared Instrument (MIRI). In the stellar tests, bright-source widths remain close to the input widths; faint sources show small residual offsets. For the mixed field, FiDeR reaches peak signal-to-noise ratios of 46.701 and 44.850 dB at backgrounds of 10 and 20 counts per pixel, with wing errors of 0.657 and 0.858 counts. It also gives small aperture-flux and shape errors, although block-matching and three-dimensional filtering (BM3D) gives higher structural similarity. The NIRCam data show lower core and combined-region errors, while the three-exposure MIRI test gives benefits mainly in the stellar aperture and photometry. These results support substantial noise reduction with little change in the measured PSF within the tested regimes. The denoised images can provide inputs for further reconstruction and measurement; their uncertainties must account for residual noise correlations.

astro-ph.IM↗
arXiv2026

Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents

Computer-use agents increasingly tackle tasks ranging from everyday desktop activities to long-horizon professional workflows. Yet interfaces centered on screenshots and mouse-and-keyboard actions can impose a human-interaction prior, requiring repeated screen interpretation while leaving the computer's semantic and programmatic capabilities underexposed. We argue for exposing these capabilities and letting models choose and combine them. We introduce Hybrid Computer Use (HCU), a unified interface for general agents that combines three complementary channels: programmatic interaction through code and command-line tools, semantic interaction through accessibility (AX), and visual interaction through graphical user interfaces (GUI). Our HCU supports efficient AX interaction and guards against stale-state actions during channel switching. A supplementary HCU skill guides agents in selecting and coordinating channels to use the unified interface effectively. Our designed AX tools return compact observations, execute actions in batches, and report their effects as AX diffs, so the model needs fewer round trips. On OSWorld 2.0, HCU achieves the highest Partial and Binary scores among the compared systems. Analyzing agent trajectories, we find that all evaluated models improve with HCU yet allocate work across the channels differently and consistently outperform compared baselines in terms of both efficiency and task success, highlighting the value of unified computer-use interfaces that allow flexible channel selection and combination.

cs.HC↗
arXiv2026

PALATE: Pretrained Autoregressive LATent Embeddings

Local-commerce and food-delivery marketplaces run large ads businesses: across hundreds of thousands of stores, merchants pay to be surfaced on browse and search surfaces, and a ranker decides which ads each consumer sees. Ranking well demands strong per-consumer personalization, yet a consumer's raw interaction history is sparse and high-cardinality. Our production ranker had personalized only through hand-engineered signals: aggregate engagement counts, categorical embeddings, and order-agnostic pooled history, with no learned per-consumer sequence representation. We learn one by training a GPT-style generative model of the consumer's engagement sequence to predict their next few engagements, and read its last-token hidden state as the consumer embedding. That single frozen vector becomes one shared personalization input for every ad surface: a daily job refreshes it, and each ranker consumes it as an ordinary dense feature. Offline it is the largest single-feature gain in our ranking-AUC ladder, a relative Eval-AUC gain of +0.59% on a browse-driven feed and +0.57% on a query-driven search surface. Online, it shipped as one component of bundled ranker retrains on both surfaces: Discovery (revenue +0.79%, conversion rate +1.17%) and Search (revenue +0.94%, conversion rate +1.50%). Three design choices adapt the generative objective to a repurchase-heavy marketplace, and are the core of our contribution: an exploration-weighted loss that up-weights businesses new to the consumer over ones already engaged; a two-stage curriculum: a click pretrain that keeps the representation broad and exploratory, then a conversion fine-tune that sharpens purchase intent; and a designed negative set that pairs a fixed popular-business pool and businesses shown but not ordered with random and in-batch negatives.

cs.IR↗
arXiv2026

Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses

Effective computer-use agents (CUAs) should seamlessly combine visual GUI interaction with code and terminal execution within a single policy. We present Mage-VL-Cowork, a 4B hybrid CUA trained from a general multimodally aligned checkpoint through an end-to-end, progressive five-stage curriculum across midtraining, SFT, and RL. To power this curriculum at scale, Mage-CUA-Forge replaces per-task agent construction with reusable, skill-conditioned generation workflows and application-specific preparers, synthesizing 293,806 desktop and web tasks across 6,915 skills while reducing recurring per-task expenditure by 82.6%. Rather than directly distilling a default teacher, we evolve the teacher harness and instantiate specialized CUA harnesses to yield high-quality trajectories alongside stage-specific supervision. Mage-VL-Cowork-4B finally climbs to 66.0% on OSWorld-Verified through different training stages with more efficient reasoning cost, achieving state-of-the-art performance at its parameter size and pushing forward the frontier of on-device intelligence.

cs.CL↗
arXiv2026

Too Hard, Too Easy, Just Right: Performance-Driven Challenge Adaptation in Virtual Reality Firefighter Training

Effective firefighter training requires practice under dynamic and stressful emergency conditions, yet real-world live-fire exercises are costly, risky, and difficult to scale. Virtual Reality (VR) offers a safe and controllable alternative, but many existing VR firefighter training systems rely on fixed scenarios or provide limited difficulty adaptation, making it difficult to maintain an appropriate level of challenge for skill development as trainees' performance changes over time. To address this limitation, we present ProACT, a performance-driven adaptive training system that regulates scenario difficulty through closed-loop interactions between trainee performance and simulated fire dynamics. Specifically, ProACT combines a global module that continuously adjusts scene-level fire spread dynamics in real time based on trainee performance with a local module that periodically updates object-level flammability across the environment. Our evaluation shows that ProACT improves both objective training performance and subjective user experience compared with existing adaptive and non-adaptive baselines. We further discuss how adaptive immersive environments can extend beyond firefighting to broader training domains.

cs.AI↗
arXiv2026

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety. We present Yuvion VL, a family of multimodal large language models purpose-built for content and AI safety, with both instruction-tuned and reasoning-oriented variants. Yuvion VL addresses this gap by treating safety as an inherently adversarial and multimodal problem and designing the entire pipeline around adversarial robustness. For data construction, we develop an automated pipeline integrating adversarial-aware data synthesis with multi-stage quality control, producing large-scale, high-quality multimodal samples augmented with domain knowledge and reasoning annotations. For training, we adopt a three-stage pipeline that includes continued pretraining for risk-concept cross-modal alignment, instruct post-training for production-grade safety tasks, and reasoning post-training for enhanced interpretability and performance in complex tasks. We further introduce Confuse-then-Contrast Fine-Tuning, a contrastive framework that mines model-specific confusions and constructs multi-image contrastive groups to enforce explicit discrimination of fine-grained visual-semantic elements, enabling the model to distinguish between visually similar cases with different safety implications in adversarial safety tasks. To support rigorous evaluation, we further introduce Yuvion VL RiskEval (YVRE), a collection of benchmarks covering diverse open and internal evaluations, with a focus on content and AI safety, adversarial robustness, and real-world capability requirements. Experiments show that Yuvion VL-32B achieves industry-leading safety performance, surpassing comparably sized open-source models and best closed-source commercial models, while maintaining comparable general capabilities.

cs.CV↗
arXiv2026

CAESAR: Mixed Reality Search-and-Rescue Platform for Cognitive Attack Evaluation

Mixed Reality (MR) enables immersive training by tightly coupling virtual content with the physical environment and supporting embodied interaction. In safety-critical collaborative tasks such as search-and-rescue, however, users rely heavily on virtual elements for perception, coordination, and decision-making, making them vulnerable to cognitive attacks that subtly distort visual feedback, virtual content, or system synchronization. While prior MR security research has examined individual attack mechanisms, evaluations are typically conducted in isolated or single-user settings, and there is a lack of standardized collaborative testbeds for systematic adversarial experimentation. In this paper, we develop CAESAR, an end-to-end multi-user MR framework for systematic evaluation of cognitive attacks in collaborative search-and-rescue training. CAESAR features a modular architecture that integrates four classes of cognitive attacks within a synchronized collaborative scenario and incorporates a multimodal data collection pipeline that captures behavioral, performance, and subjective measures under adversarial conditions. We conduct a controlled user study with an in-depth analysis of the latency-based attack, demonstrating measurable effects on task performance and user behavior while characterizing users' subjective experience under adversarial conditions.

cs.HC↗
arXiv2026

Offset Dual Microcombs in a Single Microresonator: Kerr-Raman Interleaved Combs

Integrated Kerr microcombs have emerged as a central platform for chip-scale nonlinear photonics. One of their most compelling applications is dual-comb technology, which enables fast, high-resolution, coherent optical spectroscopy, precision metrology, ranging, and ultrasensitive sensing by interfering two frequency combs with slightly different repetition rates. However, no effective strategy yet exists to synergistically excite multiple spatial mode families, manage mode competition and energy partitioning, and precisely engineer dispersion, leaving offset co-propagating dual-microcombs in a single resonator elusive. Here we demonstrate a new mechanism for offset dual microcombs formation via Kerr-Raman interleaving for the first time, by leveraging single Raman-active thin-film lithium niobate microrings. Two spatial mode families with high loaded Q factors up to 5 million are dispersion engineered to have nearly identical free-spectral-ranges but a designed relative frequency offset. Stimulated Raman scattering efficiently generates a Raman comb in one family alongside a Kerr comb in the other. The two combs interleave with a fractional offset to form a broadband, densely interleaved spectrum. Pumping the microring at only 320 mW yields Kerr-Raman interleaved dual combs both featuring nearly identical repetition rates around 102 GHz with a small difference of 675 MHz, a relatively flat envelope exceeding 29 nm and an intrinsic comb-line linewidth of 410 Hz. Our results establish offset dual-comb generation in a single microresonator, enabling compact dual-comb sources for chip-scale precision spectroscopy, Vernier-enhanced sensing, and advanced quantum photonics.

physics.optics↗
arXiv2026

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents independently and aggregating via nDCG, ignoring inter-document interactions (redundancy, conflict, complementarity) and unable to answer what makes one document set better than another. To address these issues, we propose a complete evaluate-diagnose-optimize framework. We design SetwiseEvalKit, a three-level, nine-dimension document set evaluation benchmark covering both short-form and long-form scenarios, comprising approximately 28K high-quality evaluation rubrics. We systematically evaluate 12 rerankers: even the best method achieves no more than 45% coverage, cross-document coordination dimensions are universally weak, and no single method maintains top performance across both settings. Building on this, we propose Rubric4Setwise, a training-free method that converts rubric-based evaluation criteria into document set selection signals, achieving the best downstream generation performance with fewer documents and search rounds. It is the only method that maintains state-of-the-art results across both scenarios, validating the effectiveness of closing the loop from evaluation to optimization.

cs.CL↗
arXiv2026

Clock-Free Stochastic Scheduling for Real-Time Synchronized Content Delivery

Real-time synchronized content delivery is critical for applications such as cloud gaming, collaborative mixed reality, and live streaming, where a server must ensure that a group of users perceives the same content simultaneously for each delivery. Due to heterogeneous and unpredictable network delays, ensuring synchronization is highly challenging. We propose a clock-free scheduling framework that introduces latency compensation to control the server's delivery time for each user, aiming to maximize synchronization performance (i.e., minimizing the gap between the maximum and minimum latencies) while maintaining a low overall latency cost. Unlike prior work requiring synchronized clocks or client-side timestamps, our approach uses only acknowledgment feedback, enabling flexible deployment across diverse environments. We formulate the problem as a convex stochastic optimization with a non-smooth objective. To solve the problem, we employ the stochastic proximal point (SPP) algorithm that updates the delay compensation, using only the previous latency samples, rather than the latency distribution. By exploiting the subproblem structure, we apply ADMM to enable efficient updates with per-iteration complexity of at most $\mathcal{O}(N\log N)$, where $N$ is the number of users. We establish a convergence rate of $\mathcal{O}(1/\sqrt{K})$, where $K$ is the number of content deliveries for transmission. The framework is further extended to handle transmission failures, where packet loss results in successful delivery to only a subset of users. Finally, simulations using both synthetic and real-world latency traces demonstrate the consistent superiority of our algorithm against baseline methods.

cs.NI↗
arXiv2026

Heterogeneous Services in Multi-UAV Networks with No-Fly Zone and User Mobility

In this paper, we investigate a wireless communication network supported by multiple uncrewed aerial vehicles (UAVs). To ensure reliable connectivity, UAVs are desired to approach the boundaries of designated no-fly zones (NFZs) without violating them when mobile users (MUs) enter NFZs. To support heterogeneous communication services, MUs are assigned different priority levels based on their individual communication types. Considering the practical constraints arising from user mobility, heterogeneous communication requirements, and NFZs, the objective is to maximize the weighted sum of MU communication rates, where weights correspond to MU priorities. This is achieved by jointly optimizing trajectory planning, UAV transmission power control, and the binary association factor between UAVs and MUs. To address this challenging optimization problem under dynamic constraints, we develop a soft actor-critic algorithm with prioritized experience replay, which learns an adaptive control policy. Numerical results show that the proposed algorithm outperforms benchmark schemes in terms of convergence speed and stability. Moreover, it effectively meets diverse communication requirements, satisfies UAV energy constraints, and ensures reliable operation under NFZ constraints.

eess.SY↗
arXiv2026

MotionAnimator: Semantic-to-Motion Reasoning for Animating Part-Structured 3D Assets in XR

3D digital assets are increasingly used in education, simulation, design, and immersive content creation, yet most remain behaviorally inert: they provide geometry and component structure but lack the semantic annotations, motion constraints, and executable behaviors needed to function as dynamic objects in Extended Reality (XR). Animating such assets therefore still requires manual rigging, object-specific templates, or substantial programming expertise. We introduce MotionAnimator, an intent-driven, part-aware XR animation authoring system that transforms semantically unlabeled, part-structured 3D assets into executable animations from natural-language instructions. Rather than generating code directly from text, MotionAnimator externalizes object understanding and motion reasoning into explicit semantic and motion representations. It grounds object identity, semantic parts, and functional directions, constructs a structured plan that coordinates object- and part-level motion, and translates the plan into executable Unity behavior. On a benchmark of 90 prompts across 30 objects, MotionAnimator demonstrated reliable semantic grounding and coordinated animation generation across diverse objects and animation intents. An exploratory user study further provided insights into users' experiences with MotionAnimator and highlighted its potential for part-aware XR animation authoring. These findings demonstrate how explicit semantic and motion representations can bridge high-level user intent and executable behavior, enabling existing part-structured assets to support coordinated XR animations beyond object-level transformations and predefined behaviors.

cs.HC↗
arXiv2026

Room-temperature ferroelectric p-wave magnet

P -wave magnets exhibit odd-parity spin polarization in momentum space while retaining zero net magnetization, offering a promising route toward nonrelativistic spintronics. Previously reported p-wave magnets based on combined time-reversal and lattice-translation symmetry, Tt, have thus far exhibited ordering temperatures below the liquid-nitrogen range. Here, we demonstrate a distinct route to a pristine p-wave magnetism that does not require T t symmetry, and instead is based on incommensurate spin-spiral order. Specifically, the cycloidal magnetic structure of the multiferroic BiFeO3 (BFO) intrinsically realizes p-wave magnetism coexisting with ferroelectric polarization at room temperature. Combining symmetry analysis, density-functional-theory calculations, and circular photogalvanic-effect (CPGE) measurements, we find a large nonrelativistic spin splitting of approximately 100 meV associated with the cycloidal order. The resulting p-wave spin polarization gives rise to a characteristic CPGE response whose sign can be reversibly switched by electrically controlling the cycloid chirality. Our results establish ferroelectric BiFeO3 as a room-temperature platform for electrically switchable p-wave magnetism and provide a route toward voltage-controlled spintronic devices based on parity-breaking magnetic order.

cond-mat.mtrl-sci↗
arXiv2026

A Star's Death by a Thousand Cuts: The Runaway Periodic Eruptions of AT2023uqm

Stars on bound orbits around a supermassive black hole may undergo repeated partial tidal disruption events (rpTDEs), producing periodic flares. While several candidates have been suggested, definitive confirmation of these events remains elusive. We report the discovery of AT2023uqm, a nuclear transient that has exhibited at least five periodic optical flares, making it only the second confirmed case of periodicity after ASASSN-14ko. Uniquely, the flares from AT2023uqm show a nearly exponential increase in energy--a "runaway" phenomenon signaling the star's progressive destruction. This behavior is consistent with rpTDEs of low-mass, main-sequence stars or evolved giant stars. Multiwavelength observations and spectroscopic analysis of the two most recent flares reinforce its interpretation as an rpTDE. Intriguingly, each flare displays a similar double-peaked structure, potentially originating from a double-peaked mass fallback rate or two discrete collisions per orbit. The extreme ratio of peak separation to orbital period draws attention to the possibility of a giant star being disrupted, which could be distinguished from a low-mass main-sequence star by its future mass-loss evolution. Our analysis demonstrates the power of rpTDEs to probe the properties of disrupted stars and the physical processes of tidal disruption, though it is currently limited by our knowledge of these events. AT2023uqm emerges as the most compelling rpTDE thus far, serving as a crucial framework for modeling and understanding these phenomena.

astro-ph.HE↗
arXiv2026

Anchor and Adapt: Asymmetric Prompt Adaptation for Few-Shot Industrial Anomaly Detection

In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to learn from these samples alone. Some vision-language methods therefore use manually specified descriptions to supply explicit anomaly semantics. However, constructing these descriptions requires product-specific effort, and their effectiveness depends on prompt selection. We propose Anchor and Adapt, a two-stage prompt learning framework that separates the acquisition of anomaly semantics from adaptation to target normal appearance. Stage I learns transferable normal and abnormal anchors from annotated auxiliary data. Stage II keeps these anchors fixed and adapts an additional normal branch using the few target normal samples. The inherited and adapted normal branches jointly characterize target normality, with text-anchor regularization encouraging consistency with the generic normal prior and separation from the abnormal anchors. This design retains learned anomaly knowledge while reducing dependence on category-specific anomaly templates, without requiring synthetic anomaly generation. Cross-dataset experiments between MVTec-AD and VisA under 1-, 2-, and 4-shot settings demonstrate competitive detection and localization performance. Controlled ablations assess the roles of transferred anchors, asymmetric adaptation, dual-normal representations, and anchor regularization.

cs.CV↗