Search arXiv⌕ Search

arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 19 recordsLinked to original sources
arXiv2026

GearUp: DAG-aware Acceleration for Serverless Inference Serving via Slack-guided Pre-loading

Serverless platforms increasingly host machine learning (ML) inference workflows, modeled as directed acyclic graphs (DAGs) of interdependent functions. Beyond container startup, each ML node must load libraries, model weights, and CUDA kernels before it can run. These costs accumulate along dependent DAG paths and place initialization on the end-to-end critical path. Existing systems optimize one half of this problem. DAG-agnostic pre-loading prepares nodes the request may never reach, wasting host and GPU memory. DAG-aware serving routes and scales whole functions, leaving the loading stages inside a node untouched. This paper presents GearUp, a serverless DAG inference serving system that removes ML-node loading from the end-to-end critical path at low resource cost. GearUp profiles the loading stages of each node and schedules them inside the slack time the DAG exposes, hiding initialization behind upstream execution. It reuses initialized instances within and across requests to avoid redundant cold starts. A probabilistic, traffic-adaptive keep-alive policy sets how long idle instances are retained, balancing memory cost against cold-start risk under bursty load. On the AMBER Alert and FINRA-ML workflows with NVIDIA L40S GPUs, GearUp reduces median end-to-end latency by 64.5% and 75.9% against SMIless, for median speedups of 3.1x and 10.0x over cold execution. Integrated GPU and host memory allocation fall by up to 83.9% and 94.6% against eager pre-loading in InstaInfer. GearUp achieves 4.2x strong scaling on four workers.

cs.DC↗
arXiv2026

Equivalence between rationality and modular invariance under $C_2$-cofiniteness

We prove that for a simple and $C_2$-cofinite vertex operator algebra, the rationality is equivalent to the modular invariance of the space of complete ordinary one-point trace functions of its irreducible modules. This proves a conjecture given by Dong-Ren in \cite{DongRen}, which is also the inverse theorem of Zhu's modular invariance theorem \cite{Zhu}.

math.QA↗
arXiv2026

Learning Graph Beliefs for Active Radio Mapping With Decision-Certified Multi-Step Sensing

Radio maps provide essential wireless propagation knowledge for network optimization and autonomous platforms. Acquiring dense measurements, however, is prohibitively costly, requiring active sampling to prioritize informative measurements. Existing active sampling methods typically rely on variances from prescribed spatial models or learned pointwise uncertainty, which may not fully capture the spatial correlation of different measurements. This paper proposes GraphBARC, a graph-structured active radio map construction framework that integrates learned spatial modeling with analytical Bayesian inference. A graph network learns correlated node and edge factors using only acquired measurements, inducing a joint full-map belief that supports analytical observation updates without retraining. Rather than immediate one-step acquisition, it adopts a nonmyopic sensing strategy that evaluates joint map-wide Bayes risk reduction over feasible multi-step routes, accounting for information redundancy among planned measurements. We reuse candidate responses and derive residual-based bounds directly on route-value differences, retaining shared response-error structure to avoid uniformly high-accuracy evaluation. An error-aware continuation bound screens unpromising prefixes, after which only responses needed for unresolved comparisons are refined. We further establish a computable decision-gap bound and show that certified exclusions remain valid during refinement. Experiments show that GraphBARC reduces mean root-mean-square error (RMSE) by over 16% relative to the evaluated baselines and core planning time by 56% compared with the fixed-accuracy, unpruned implementation.

cs.NI↗
arXiv2026

DUET4D: Self-Corrective Coupled Guidance for Sparse-View 4D Reconstruction

Sparse-view 4D reconstruction is highly under-constrained when only a few cameras are available. Generative priors can recover missing appearances, but video models are computationally impractical for iterative reconstruction, whereas single-view models produce temporally inconsistent pseudo-observations. Moreover, directly absorbing uncertain generative outputs into Gaussian optimization often creates redundant primitives and floating artifacts. To address these challenges, we propose DUET4D, a self-corrective coupled guidance framework for sparse-view 4D Gaussian splatting. The core of our approach is a self-corrective framework where the 4D representation guides generative prior for spatio-temporal consistent supervisions. We first construct sequential alignments from current Gaussian evidence to steer the latent restoration. Then we use Sequential Fidelity Resampling to lift generative supervisions into Gaussian space to selectively distinguish repeatedly supported primitives. The corrected representation then provides more reliable Gaussian evidence for the next restoration cycle. Extensive experiments demonstrate that DUET4D significantly improves rendering quality and rendering efficiency.

cs.CV↗
arXiv2026

HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction

Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace these failures to a fundamental mismatch. Streaming geometry is inherently temporally heterogeneous, with evidence ranging from short-lived correspondences to persistent global scale. However, current architectures impose uniform and pathological influence patterns. For example, sliding windows enforce hard cutoffs, while ungated recurrence and causal attention cause cache saturation and spike-like attention sinks. To resolve this, we formalize geometric propagation as an \emph{evidence influence kernel} and propose HorizonStream, a long-horizon Transformer that explicitly factorizes this kernel. For the long-range temporal factor, Geometric Linear Attention learns channel-wise decay rates to enable bounded, multi-timescale propagation of geometric evidence. For the short-range spatial factor, Geometric Local Attention with Spatiotemporal RoPE performs reliable 3D matching while suppressing attention sinks. Finally, Metric Readout Tokens recover stable scale and rigid pose directly from the persistent geometric state. Extensive experiments show that HorizonStream, trained on only 48-frame clips, generalizes stably to sequences exceeding 10,000\ frames with constant memory and linear time, achieving state-of-the-art streaming 3D reconstruction performance. Project Page: https://3dagentworld.github.io/horizonstream/

cs.CV↗
arXiv2026

Physics-Informed Graph-Based Safe RL with Constraint-Specific Critics for Community Battery Coordination in Distribution Network

High penetrations of distributed energy resources (DERs) and fast-varying electric vehicle (EV) charging intensify voltage and line-limit violations in distribution networks (DNs), making safe, low-cost operation increasingly challenging. This paper proposes a physics-informed safe deep reinforcement learning (DRL) framework for coordinating community battery energy storage systems to mitigate constraint violations while minimizing operating cost. To represent nonlocal spatiotemporal interactions, we develop a dual-level physics-informed graph representation in which line impedance and capacity shape spatial information propagation, while power-balance, voltage-profile, and flow-reconstruction losses regularize the latent state toward control-relevant physical consistency. Building on this representation, we develop Lagrangian Dedicated-Critic PPO (LDCPPO), which implements constraint-specific value decomposition: independent reward and cost critics preserve heterogeneous voltage- and line-loading-related learning signals and combine their advantages only during the Lagrangian policy update. Case studies on DNs with high rooftop photovoltaic penetration and EV charging demonstrate that the proposed method reduces the key voltage-violation degree by up to 80.5% compared with the tested baselines, while also achieving the lowest voltage-violation count and line-overload degree with competitive operating cost.

cs.AI↗
arXiv2026

Can discrete-time analyses be trusted for stepped wedge trials with continuous recruitment?

In stepped wedge cluster randomized trials (SW-CRTs), the intervention is rolled out to clusters sequentially over multiple periods. It is common practice to analyze data from SW-CRTs using linear mixed models that treat time as discrete. However, a recent systematic review found that 95.1\% of cross-sectional SW-CRTs recruit individuals continuously over time. Despite the prevalence of continuous recruitment, there has been limited guidance on how to draw model-robust inference for such designs. In this article, we conduct simulation studies to examine the performance of discrete-time linear mixed models in the case of continuous recruitment designs with a continuous outcome. Specifically, we generate outcomes under a continuous-time exponential decay correlation structure with either discrete or continuous fixed period effects. We consider constant and exposure-time-dependent intervention effects, with and without random intervention effects across clusters. We then analyze the simulated data using linear mixed models under three discrete-time working correlation structures: simple exchangeable, nested exchangeable, and discrete-time exponential decay, with robust sandwich variance estimation. Our results demonstrate that discrete-time analysis often yields negligible bias and that the robust variance estimator with the Mancl and DeRouen correction consistently achieves nominal coverage and type I error rate. However, when recruitment patterns vary systematically between control and intervention periods, discrete-time analyses give slightly biased intervention effect estimates. Finally, we illustrate these findings by reanalyzing a completed SW-CRT.

stat.ME↗
arXiv2026

RuleSmith: Multi-Agent LLMs for Automated Game Balancing

Game balancing is a longstanding challenge requiring repeated playtesting, expert intuition, and extensive manual tuning. We introduce RuleSmith, a framework that couples multi-agent LLM self-play with surrogate-based optimization over a parameterized rule space. As a proof of concept, we build CivMini, a simplified civilization-style game with two asymmetric factions governed by 12 tunable parameters. LLM agents interpret textual rulebooks and game states to propose actions that are validated by the game engine, yielding noisy estimates of faction win rates. Our primary implementation uses Gaussian-process Bayesian optimization with Expected-Improvement-based adaptive sampling to allocate more evaluation games to promising candidates. RuleSmith consistently finds near-balanced configurations: three independent optimization runs reach near-even empirical win rates in independent 200- and 300-game evaluations, and additional experiments with NTBEA and TPE show that the same self-play interface supports different search components. Cross-model evaluations and small human studies provide preliminary evidence of transfer across player populations. RuleSmith produces interpretable numerical rule adjustments without task-specific policy training. Project and code: https://adonis-galaxy.github.io/RuleSmith-website/

cs.LG↗
arXiv2026

FrontierCS 2: A Benchmark for Computer Science R&D

Can LLM agents make contributions to frontier computer science R&D? We introduce FrontierCS 2, a benchmark of 48 open-ended tasks. We take a paper and the code its authors released and delete the paper's contribution. The deleted code becomes the human reference that sets the bar. Earlier open-ended benchmarks give each agent a problem statement and grade one program after the run. FrontierCS 2 places the agent inside a research environment. The agent inherits a working repository and may submit a patch at any point. For each patch, a judge returns a development-suite score but keeps the evaluator, the held-out final suite and the reference private, and grades the final submission on that suite against the reference. The tasks span 13 domains, from machine-learning systems and high-performance computing to databases, security and robotics. Beyond these 48 tasks, FrontierCS 2 keeps a private set of more than 100 tasks, to be announced in the future. We evaluate 12 agents. The best one is Claude Opus 5.5, passing 58% of its runs. No run passes on 16 tasks. A higher score is not the same as a pass: most runs that beat the reference on the combined final score still fall short on some metric or workload. On a shared capability scale for agents and tasks, the median task is roughly as difficult as what the strongest agent can handle.

cs.LG↗
arXiv2026

Modelling Toxin-Induced Intraspecific Personality Variation in Predator-Prey Dynamics

Personality traits, such as boldness and shyness, can affect interspecific interactions through differences in individual behaviour. Environmental toxins may also alter these traits. However, few predator-prey models have considered animal personality. In this study, we extend a toxin-dependent predator-prey model by incorporating personality variation in both prey and predators. Prey personality affects birth and growth, whereas predator personality affects the predator functional response. The model is parameterized for rainbow trout and aquatic insect prey exposed to methylmercury. Numerical results show that prey and predator personality have different effects on population dynamics. Prey personality tends to reduce biomass fluctuations and promote stable coexistence. In contrast, predator personality can increase biomass fluctuations and lead to persistent population oscillations. These effects are mainly observed at low and intermediate toxin concentrations that are environmentally relevant to freshwater ecosystems. Using a quasi-steady-state approximation, we reduce the model to a two-dimensional system and study its positivity, boundedness, and the existence of equilibria. The equilibrium structure depends jointly on the toxin level and the prey and predator personality contrasts. Based on this existence classification, we numerically investigate the local stability of all feasible equilibria and identify parameter regions corresponding to locally stable extinction, prey-only persistence, coexistence, and bistability. Overall, toxin-induced personality variation can qualitatively change predator-prey dynamics.

q-bio.PE↗
arXiv2026

OPIS: An Input-Grounded Benchmark for Multi-Object Memory in Video World Models

Video world models must preserve the visual state of the world over time, but existing evaluation protocols often rely on generated histories, video reference, or selected revisit viewpoints that can confound the assessment of a model's true memory capability. To address this, we introduce OPIS, an input-grounded benchmark that strictly anchors the assessment to a fixed set of object instances from the initial observation for evaluating multi-object memory in video world models. The OPIS dataset comprises 500 cases across real-world, embodied-robotic, and game-world domains, providing dense object-level annotations for 12,672 rigid, articulated, and deformable instances. Our object-centric evaluator combines association and explicit visibility reasoning to hierarchically measure Object (O) Presence (P), Identity (I), and Structure (S), utilizing static or dynamic evaluation tracks based on object kinematics. Across eight image-to-video or camera-conditioned world models, our proposed OPIS scores range from 48.65 to 56.01. As the reference inventory grows from less than 20 to more than 40 objects, the Presence, Identity, and Structure scores show an overall decline, with the average Identity score falling from 40.22 to 23.11. The results demonstrate that preserving the particular object instances in the input is considerably harder than generating plausible visual elements.

cs.CV↗
arXiv2026

Baseline and Incremental: User, Item, and Request Debiasing in Instagram Feed Ranking

A feed ranker scores candidates with a value model, a weighted sum of engagement predictions. Each prediction conflates a baseline, what this viewer, item or request would produce anyway, with the incremental amount by which this candidate exceeds it. The literature mostly removes the baseline. We argue that a multi-signal value model should keep the raw prediction and add the incremental part as a separately weighted term. On Instagram Feed, three debiasing families deployed independently, for viewer habit, item popularity and request context, are one parameterised operator, and a design procedure picks a point in it. Media-type (format) bias goes instead to a debiased label chosen by the same procedure. In a controlled four-arm ablation of deployed Feed terms (neither term, each alone, both), the two-term arm beats both single-term arms at production weights on point estimates in 11 of 13 judged (term, metric) pairs. Of the 26 direct contrasts, 17 are significantly for it and only 1 against it, on impressions. The ablation also suggests that the offline diagnostic should screen signals, not rank them. Such terms have served Instagram Feed production for most of a year. Beyond Feed, Meta, whose apps serve billions of people, has adopted the operator across surfaces, apps and both ranking stages. Its launches there drive sessions and daily active users, the core visitation and retention metrics.

cs.IR↗
arXiv2026

SciDiagBench: A Type-Specific Benchmark for Human-Aligned Evaluation of Scientific Diagrams

Recent agents have demonstrated strong capabilities in generating images from textual prompts, motivating their utilization for scientific diagram generation. Scientific diagrams naturally span diverse types, each characterized by distinct visual structures and content organization. Consequently, during peer review and other scientific evaluation, human experts naturally consider type-specific criteria when assessing their quality. However, existing VLM-based evaluation benchmarks fail to reflect the above human evaluation practices for two main reasons: 1) benchmark datasets typically lack a systematic categorization of different diagram types and thus adopt the same generic criteria for all diagrams, and 2) their evaluation criteria are often designed heuristically, without explicit alignment to human evaluation preferences. Motivated by these limitations, we introduce SciDiagBench, which consists of a benchmark dataset that systematically categorizes scientific diagrams into 11 types and a human preference-guided evaluation method. Specifically, SciDiagBench contains 165 scientific diagrams across 10 broad domains, with types including graphical abstracts, technical roadmaps, and illustrative cases. Based on this dataset, SciDiagBench develops an evaluation method that leverages a preference-guided calibration process to incorporate human preferences into the generation of type-specific criteria. Ultimately, SciDiagBench enables more reliable automated evaluation that better aligns with human evaluation across diverse scientific diagrams.

cs.CL↗
arXiv2026

VeriCalib: Verifiable Target-Based LiDAR-Camera Calibration

Target-based extrinsic calibration estimates the rigid transform between sensors from a few observations of a known target, and its result is commonly assessed by the root-mean-square error of the fitted residuals. However, this scalar error is computed on the same observations and therefore cannot indicate whether to accept the result, re-extract, recollect or add observations. This paper presents VeriCalib, which formulates extrinsic calibration as a verifiable estimation problem and reports a calibration state. The key insight is a two-level extrinsic compensation mechanism, in which the extrinsic compensates the rigid part of each observation error at the residual level, and rotation and translation compensate each other at the parameter level. Consequently, the fitted residual can reveal neither an inconsistency between the observations and the model nor whether the estimated extrinsic is reliable in every direction. Accordingly, we assess the calibration through a structured covariance that jointly propagates the uncertainty of the camera and LiDAR board features with a known-geometry prior, and estimate its scale as a variance component from the residuals. On this covariance, we decouple rotation and translation to resolve the precision along each direction and guide data collection toward the weakest one. Since this precision presumes consistent observations, we further develop within-view and cross-view checks that examine the internal residual and the rigid discrepancy between observations, respectively, with thresholds that hold their significance level under an unknown noise level. We also extend the minimal detectable bias to the extrinsic to bound the smallest detectable fault along each direction. These criteria form a calibration state that indicates whether to accept the result or how to collect the data...

cs.RO↗
arXiv2026

When Seeing Is Not Believing -- A Benchmark for Search-Grounded Video Misinformation Detection

Video misinformation increasingly operates at the semantic and evidential level: authentic footage may be selectively edited, temporally reordered, spliced across sources, or augmented with AI-generated content to construct false narratives. Such evidence-dependent manipulations cannot be reliably verified from the input video alone, because the missing, reordered, replaced, or recontextualized evidence lies outside the video itself. We introduce \textbf{EVID-Bench}, a benchmark for search-grounded video misinformation detection, where a system must search the open web for related videos and identify what information is false through cross-video comparison. EVID-Bench comprises 222 videos spanning 9 manipulation types across 3 categories: AI generation, single-source editing, and multi-source editing. All samples are verified to be undetectable by frontier models through visual inspection alone. We evaluate nine frontier multimodal models using a retrieval-augmented verification baseline. The best system achieves only 61.43\% point-level accuracy and 43.24\% video-level accuracy, while AI-generated manipulations remain especially challenging. Error analysis reveals recurring challenges: models fixate on irrelevant anchors, misattribute synthetic content to editorial splicing, and terminate search prematurely before fully explaining the manipulation.

cs.CV↗
arXiv2026

Omni-RS: Unifying Multi-Task Understanding and Generation in Remote Sensing

Practical remote sensing applications often require both understanding and generation capabilities for the same geographic scene. However, most existing methods address either understanding or generation in isolation, while existing unified remote sensing models' generative ability is limited to text-to-image. To bridge this gap, we propose Omni-RS, a unified framework supporting four remote sensing understanding tasks and five generation tasks. Specifically, we introduce the "Scene-Guided Two-Stage Training" strategy, which first adapts a multimodal large language model to remote sensing understanding and then uses its hidden states to guide a diffusion transformer for image generation. To enable joint learning across diverse generation tasks, we construct UniGen, a unified multi-task generation dataset, by organizing heterogeneous remote sensing data into a unified format. Furthermore, we introduce "Detailed Visual Conditioning", which uses visual conditions encoded by a VAE to guide the generation process, thereby supporting additional generation tasks that require reference images. Extensive experiments demonstrate that Omni-RS performs exceptionally well in understanding tasks and has achieved outstanding results in a variety of generative tasks.

cs.CV↗
arXiv2026

CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat

AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in isolation against static targets. Real cyber operations, however, are dynamic and coupled: security postures constantly change as attackers and defenders adapt to each other in real time. Static benchmarks quickly saturate and miss an agent's ability to attack and defend simultaneously under live pressure. To address this gap, we present CyberArena, a dynamic, symmetric adversarial benchmark built around multi-round attack-and-defense combat. In isolated sandboxes, two agents compete under identical rules, acting concurrently as both attackers and defenders over continuously changing services. This converts static targets into evolving, semi-open challenges, directly testing an agent's speed and precision in discovering, exploiting, and patching vulnerabilities. To sustain the benchmark's longevity, an automated agentic pipeline continuously generates, reviews, and validates new environments. Furthermore, because pairwise contests are notoriously hard to quantify, we introduce a dynamical model that maps match dynamics into unified, multidimensional scores across offensive, defensive, and domain-specific capabilities. Evaluating 12 frontier LLM agents across 40 challenges in 466 matches, CyberArena separates model capabilities where single-agent baselines hit a ceiling. The trajectories read like a fight rather than an exam: defenders patch one hole and miss the next and certify repairs on stale evidence, while capable agents think a move ahead, planting backdoors for later rounds and, in one case, writing their own packet sniffer to watch the opponent. Beyond a benchmark, CyberArena serves as an adaptable, scalable experimental platform for future research on cybersecurity agents.

cs.CR↗
arXiv2026

VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents

Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruction and environment available for solving a task, an agent writes an executable verifier that must accept every valid solution and reject invalid ones. We introduce VerifierBench, a benchmark of 222 tasks from six agent benchmarks spanning tool-call, state-based, and code verification, with 4,993 hidden test cases that include alternative valid solutions and attacks; Verifier4Verifier (V4V), a six-check audit, screens its source verifiers and test suites. Across 19 models in a common agent harness, normalized balanced accuracy ranges from 10.6 to 62.1, with generated verifiers consistently rejecting invalid solutions more reliably than they accept valid ones. This apparent strength can mask overly restrictive verification: most false rejections in the analyzed records come from verifiers that accept no tested solution to a task. Case studies reveal unsupported assumptions about solution formats, tool use, and code changes that exclude valid solutions. These errors survive self-testing because agents test solutions that share the verifier's mistaken assumptions, or submit verifiers without confirming that any correct solution passes. These findings suggest testing both whether a verifier accepts a correct solution and whether it accepts other solutions permitted by the task. The project page and dataset are publicly available.

cs.SE↗