Searcharxiv⌕ Search

arXiv subjects

Haitao Wang

Publications and source records attributed to Haitao Wang.

At least 19 recordsLinked to original sources

Med-DisSeg: A Dispersion-Driven Framework for Fine-Grained Medical Image Segmentation

Accurate medical image segmentation is essential for quantitative image analysis and precision medicine. However, the visual similarity between target regions and surrounding tissues leads segmentation models to learn overly compact feature representations, limiting feature separability in the embedding space. This insufficient separability causes segmentation models to generate ambiguous activation maps and imprecise segmentation results. To address this issue, we propose Med-DisSeg, a dispersion-driven medical image segmentation framework that learns more separable feature representations, thereby enabling more accurate reconstruction of fine structures and boundaries. Within Med-DisSeg, a lightweight Dispersive Loss is introduced as an auxiliary regularizer to encourage more dispersed and separable feature representations. Building on these dispersion-regularized representations, the encoder strengthens structure-relevant responses through joint channel and spatial modeling, while the decoder performs multi-scale adaptive calibration to preserve complementary local details and contextual information. Together, these components improve the segmentation of small, deformable, and boundary-ambiguous targets. Extensive experiments on five public datasets covering three imaging modalities demonstrate the effectiveness and robustness of Med-DisSeg across diverse medical image segmentation tasks. The source code and pretrained models will be released upon acceptance.

cs.CV↗

Computing Independent Sets of Size Three in Disk Graphs

We study the problem of computing an independent set of size three in disk graphs, where vertices correspond to disks in the plane and two vertices are adjacent if their disks intersect. While computing a maximum independent set in disk graphs is NP-hard, the fixed-size case admits more efficient solutions. Given a set of $n$ disks, we present an algorithm to compute an independent set of size three in the disk graph and our algorithm runs in randomized expected $O^*(n^{5/3})$ time, where $O^*$ hides a factor of $n^ε$ for an arbitrarily small $ε> 0$. Our approach introduces a framework based on semi-algebraic range searching and tree-structured biclique partitions, which allows us to group pairs of disjoint disks into canonical subsets and avoid redundant computations. When the centers of the disks are in convex position, we solve the problem in $O(n \log^2 n)$ deterministic time. We also consider the case in which the disks themselves are in convex position, i.e., each disk contributes to the boundary of the convex hull of all disks, and obtain an $O(n \log^2 n)$ time algorithm for this setting as well. Our techniques for these cases are based on geometric properties of disk arrangements. In particular, they rely on new structural lemmas that reduce the problem to efficiently testing certain ordered configurations of disks. Our results improve upon the straightforward quadratic time approach and demonstrate how geometric structures and range searching techniques can be leveraged to solve fixed-size independent set problems in disk graphs more efficiently. To the best of our knowledge, this is the first systematic study of independent sets of size three in disk graphs. Our results show that even this smallest nontrivial case exhibits rich structural properties, especially under convexity assumptions.

cs.CG↗

FlowMAS: Learning Multi-Agent Workflow Topology via Information-guided Generative Flow Network

Automated multi-agent systems offer clear advantages over manually designed ones in scalability and adaptability, but existing workflow topology methods still face important limitations. Search-based methods are often computationally expensive, textual-gradient-based methods rely on coarse-grained feedback, and existing generation-based methods are not well suited to discrete workflow topologies with complex dependencies. To address these limitations, we propose FlowMAS, a multi-agent workflow topology method based on Generative Flow Networks (GFlowNets). FlowMAS models workflow generation as reward-guided flow over the topology space and introduces three components: a GFlowNet-based topology generation backbone, a curiosity-driven module for structure-aware exploration, and an information-guided optimization module for evaluating intermediate topologies. Concretely, the curiosity-driven module encourages exploration of structurally novel workflows, while the information-guided module measures both the information contribution and the communication efficiency of different operators to favor more informative and effective collaboration patterns. Experiments on six benchmark datasets with three LLM backbones show that FlowMAS consistently outperforms multiple baselines.

cs.MA↗

Implicit Additively Weighted Geodesic Voronoi Diagrams and Applications

Let $P$ be a simple polygon with $m$ vertices. After $O(m)$-time preprocessing of $P$, for any set $S$ of $n$ additively weighted point sites, we compute an implicit additively weighted geodesic Voronoi diagram in $O(n\log n+n\log^2 m)$ time, supporting nearest-neighbor queries in $O(\log(n+m))$ time. In contrast, explicitly constructing the diagram requires $Ω(m)$ time. Our algorithm introduces a new sweep-line paradigm that avoids explicitly constructing the diagram, together with a novel technique for point location in implicit subdivisions. As applications, we obtain new dynamic data structures for additively weighted geodesic nearest-neighbor searching and the first efficient algorithms for shortest paths in geodesic disk graphs. After the same $O(m)$-time preprocessing, single-source shortest paths in a geodesic disk graph of $n$ sites can be computed in $O(n\log n+n\log^2 m)$ time in the unweighted case and $O(n^{3/2}(\log n+\log^2 m))$ time in the weighted case. We also extend our techniques to implicit farthest geodesic Voronoi diagrams for unweighted sites, obtaining analogous bounds and dynamic farthest-neighbor data structures.

cs.CG↗

ATI-OPD: Adaptive Teacher Intervention for Stable Long-Sequence On-Policy Distillation

On-policy distillation (OPD) trains a student on its own responses using token-level feedback from a teacher. As responses grow longer, the student's prefix can depart from the teacher's own reasoning, weakening its feedback on later tokens. Updates based on this feedback can reinforce the same deviations in later responses and destabilize training. Prior approaches such as length control and loss reweighting limit learning from problematic responses but leave their prefixes unchanged. Fixed cutoffs can also discard later reasoning. We propose \textbf{Adaptive Teacher Intervention for On-Policy Distillation (ATI-OPD)} to improve subsequent teacher guidance by revising the student's reasoning prefix. ATI-OPD replaces the earliest high-disagreement segment with a short teacher segment, then lets the student resume its own reasoning from the revised text. To handle renewed disagreement, it excludes persistently divergent suffixes from the distillation loss while retaining useful student continuation. Training diagnostics show less teacher-student disagreement, fewer gradient spikes, and fewer extremely long responses. Across five mathematical reasoning benchmarks and two teacher-student pairs, ATI-OPD improves average student-only accuracy over standard OPD.

cs.CL↗

Time-asymptotic expansion and fluid approximation of the 1D Boltzmann equation with hard potentials

We establish a quantitative large-time comparison between the macroscopic Boltzmann solution and the full nonlinear compressible Navier-Stokes solution in one space dimension. For Maxwellian molecules and hard potentials with angular cutoff, we consider small, spatially compactly supported perturbations of a global Maxwellian with polynomial velocity decay, without assuming spatial differentiability. Nonlinear diffusion waves persist at leading order, making comparison through linearized equations alone insufficient. We construct a coupled system for the leading nonlinear fluid waves and derive cancellation identities from the exact kinetic spectral representation to control interactions between distinct characteristic families. Combined with a particle-fluid decomposition, these yield pointwise estimates separating the leading waves, their interactions, and a faster-decaying remainder.

math.AP↗

AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher agents can explore more hypotheses, but early evaluation scores might misrepresent their promise, shared findings could lose their applicability conditions, and useful procedures could remain confined to completed investigations. In this paper, we present AReaL-RSI, a framework for organizing a persistent research team of agents without updating backbone LLM weights. We formulate the scaling problem in terms of evaluated outcomes and whole-system resource expenditure. Concretely, a leader agent selects task-appropriate research orientations and guides ongoing investigations; conditional memory sharing distinguishes unresolved problems from supported findings and enables recipient adaptation. During recursive evolution, after each campaign, evidence-based review revises researcher orientation, knowledge, and skills for later campaigns. Experiments compare AReaL-RSI with Codex-Goal on downstream harness optimization, GPU kernel optimization, and AI research tasks using two backbones. Under the reported resource allocations, AReaL-RSI improves Terminal Bench performance by 2.2 percentage points for each backbone and increases mean KernelBench speedup by 32.2-36.8%; further scalability comparisons favor the design of AReaL-RSI over native scaling: combining experience sharing with specialized researcher roles yields 1.9-27.5% lower kernel latency than independent exploration and 1.3-33.9% lower latency than sharing alone across all seven comparable task-backbone pairs.

cs.AI↗

Deterministic Distance Selection in $O(n^{4/3})$ Time

Let $P$ be a set of $n$ points in the plane. Given an integer $K$ with $1\le K\le {n\choose 2}$, the distance selection problem asks for the $K$-th smallest distance among all pairwise distances of the points of $P$. The problem has been studied extensively over the past four decades. Recently, Chan and Zheng (2023) gave a randomized algorithm with $O(n^{4/3})$ expected running time, while the best known deterministic algorithm runs in $O(n^{4/3}\log n)$ time. In this paper, we present a deterministic $O(n^{4/3})$-time algorithm for the problem, matching the best known randomized complexity. We also consider the more general bichromatic version of the problem, where two point sets $A$ and $B$ are given, with $m=|A|$ and $n=|B|$, and the goal is to find the $K$-th smallest distance among the $mn$ distances between points of $A$ and points of $B$. For this problem, the best previously known algorithm runs in $O((m\log n+n\log m+m^{2/3}n^{2/3})\log(m+n))$ time. We present a new deterministic algorithm with running time $O(m\log^2 n+n\log^2 m+m^{2/3}n^{2/3})$.

cs.CG↗

Mechanistic transition between inter- and trans-granular creep cracking via a unified crystal plasticity-fracture framework

High-temperature creep in metals remains challenging due to the complex interplay of deformation and failure mechanisms across multiple length scales. The trade-off between inter- and trans-granular cracking governs the transition of creep rupture behaviour in metallic materials. However, the micromechanical basis of the transition and its linkage to the macroscopic brittle to ductile transition in creep rupture behaviour remain unresolved. Here, the stress-dependent competition between grain-boundary cavitation and slip-induced intragranular cracking is revealed via a unified crystal plasticity fracture framework. The framework incorporates crystal plasticity, grain-boundary cavitation, and crystallographic crack propagation within an explicit polycrystalline microstructure. The microscale computation reveals the transition from trans-granular-dominated cracking at high stress levels to mixed inter- and trans-granular cracking at intermediate stresses and inter-granular-dominated cracking at lower stresses, accompanied by distinct damage localization modes and the evolution of crack paths from grain boundary to grain-interior propagation. The results further quantify the linkage between microscopic fracture mechanisms and macroscopic creep rupture behaviour, including changes in rupture ductility and creep life. Under high-stress conditions, deformation-driven trans-granular damage localization promotes ductile rupture through extensive strain accumulation, whereas under lower-stress conditions, time-dependent grain-boundary damage accumulation leads to quasi-brittle rupture through localized inter-granular fracture.

cond-mat.mtrl-sci↗

D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Frequency and Pixel Spaces

Out-of-domain (OOD) robustness is challenging to achieve in real-world computer vision, especially in unsupervised domain adaptation scenarios, where shifts in image background, style, and acquisition instruments often degrade model performance. Generic augmentations show inconsistent gains under such shifts, whereas dataset-specific augmentations require expert knowledge and prior analysis. Moreover, prior studies show that neural networks adapt poorly to domain shifts because they exhibit a learning bias to domain-specific frequency components. Perturbing frequency values can mitigate such bias but overlooks pixel-level details, leading to suboptimal performance. To address these limitations, we propose D-GAP, a Dataset-agnostic and Gradient-guided augmentation method for the Amplitude spectrum (in frequency space) and the Pixel values. Unlike conventional handcrafted augmentations, D-GAP computes sensitivity maps in the frequency space from task gradients, which reflect how strongly the deep models respond to different frequency components, and uses the maps to adaptively interpolate amplitudes between source and target samples. We further propose a dual-space augmentation that jointly controls spectral bias and spatial fidelity by introducing a complementary pixel-space blending branch. This way, D-GAP turns augmentation from fixed, random, or manually designed perturbation into a model-response-adaptive intervention. Extensive experimental results show that the proposed method consistently outperforms both generic and dataset-specific domain adaptation methods, improving average OOD performance by +5.3% on four real-world datasets and +1.9% on three benchmark datasets. Code is available at https://github.com/RapidsAtHKUST/D-GAP.

cs.CV↗

OGPO: One-Step Generative Policy Optimization for Real-Time Robot Control

Real-time robot control demands fast action generation. Diffusion and flow matching policies for robot control require multi-step sampling, limiting their deployment in real-time scenarios. Natively reducing the sampling steps to one sacrifices representation quality and task performance, creating a trilemma among speed, fidelity, and performance. We present One-Step Generative Policy Optimization (OGPO), a systematic framework to resolve this trilemma. OGPO first pairs a lightweight architecture with the interval velocity principle for distillation-free one-step inference, while representation spreading prevents representation quality degradation. It then performs on-policy reinforcement learning (RL) fine-tuning on this fast, stable policy to break the imitation learning ceiling. Experiments on RoboMimic and OpenAI Gym benchmarks show that OGPO matches or exceeds multi-step baselines while achieving a 5-20 times inference speedup and over 120Hz control frequency. Physical deployment on a Franka-Emika-Panda robot validates real-world applicability. Project page: https://ogpo-project.github.io/

cs.RO↗

$L^1$ Behavior of the Stokes System and the Navier--Stokes System in the Half Space

In this paper, the detailed behavior of solutions of both the Stokes and the Navier--Stokes system in the half space is investigated when the initial data belongs to $L^1$. We first give a detailed asymptotic expansion of the solution to the Stokes system supplemented with $L^1$ initial data. With the aid of this expansion, we provide two sufficient conditions on the initial data so that the associated solutions of the Navier--Stokes system do not belong to $L^1$, corresponding to long time and short time behaviors, respectively. Moreover, for the $n$- dimensional Navier--Stokes system, a pointwise spatial lower bound of order $n$ is derived in a conic neighborhood of the $x_n$-axis, provided that the initial data decays faster than order $n$. One of the main difficulties to get precise form of leading order term is the non-commutativity of the Leray projection operator with the Laplacian. Our strategy is to employ the special structure of the Green tensor observed by Han and a cancellation property of the initial data. This also yields the sufficient conditions on the initial data to get precise asymptotic behavior via comparing the linear and nonlinear parts.

math.AP↗

MA-FPPO: Multi-Agent Flow-Pretrained Policy Optimization

Multi-agent flow policies learn cooperative behavior from fixed offline datasets, but often struggle to complete tasks in situations not covered by the offline data. In these situations, agents must both adapt to changes in the environment and coordinate with one another, yet action patterns learned offline are often insufficient for effective adaptation and coordination. To address this problem, we propose Multi-Agent Flow-Pretrained Policy Optimization (MA-FPPO), which uses online fine-tuning to improve the cooperative behavior of models pretrained with flow matching through new interactions with the environment. Building on the behavior learned during pretraining, we construct policies with explicit action likelihoods for discrete and continuous action spaces. We then update the pretrained model using shared team advantages to further improve coordination based on team performance. Our method achieves, on average, relative gains of 52.8% over the strongest listed offline baselines across 30 settings and 29.8% over purely online learning across 38 comparisons with matched online budgets and evaluation protocols.

cs.AI↗

MA-WAM: Multi-Agent World-Action Model for Test-Time Planning

Multi-agent cooperative tasks require different agents to execute a joint action simultaneously, and each agent's action affects both the observations and responses of the other agents. Hence, a world model is needed to predict the team return resulting from the joint actions of all agents. A naive extension directly applies a single-agent world model to each agent's action when predicting the team return step by step. However, such an extension fails to capture the dependencies among the simultaneous actions of multiple agents. We propose Multi-Agent World-Action Model (MA-WAM), a test-time planning framework that enables a frozen multi-agent flow policy to evaluate futures of candidate joint actions. To our knowledge, MA-WAM is the first test-time world-model planner for multi-agent flow policies. MA-WAM predicts the consequences of each joint action according to cross-agent dependencies and enables efficient candidate scoring. Across 30 offline multi-agent reinforcement learning (MARL) settings on MAMuJoCo, SMAC, and MPE, MA-WAM achieves mean relative gains of 22.0% over direct execution and 25.6% over uniform action selection. Under the standard evaluation protocol on an A100 GPU, MA-WAM adds 12.1 ms, accounting for 2.5% of the measured generation-and-scoring time.

cs.AI↗

G2MAF: Test-Time Gradient Guidance for Multi-Agent Flow Policies

Offline multi-agent reinforcement learning (MARL) learns cooperative policies from fixed datasets without further environment interaction and a learned policy is frozen at deployment. Such a frozen policy typically proposes a single joint action and executes it directly at deployment time. However, this one-shot deployment often commits to a suboptimal proposal, even when better nearby alternatives remain consistent with the behavior data. To address this issue, we propose Gradient Guided Multi Agent Flow (G2MAF), a refinement framework for optimizing joint policies at test-time. G2MAF applies one globally normalized, projected critic gradient to guide and coordinate all agents' corrections while keeping the action both feasible and close to the frozen policy proposal. Across 24 MPE and SMAC settings, its canonical variant improves 20 frozen settings, with mean relative gains of 9.2% on MPE and 8.9% on SMAC, with model inference latency increased by about 6% only.

cs.AI↗

CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making

How can generative offline multi-agent reinforcement learning achieve both fast joint trajectory generation and effective cooperation? Multi-agent diffusion models generate joint trajectories through iterative sampling but incur high inference latency. Distillation reduces sampling steps but may lose the teacher's cross-agent dependencies, reducing the success rate of cooperative tasks. A joint few-step generator can be trained directly to avoid losing these dependencies during distillation. However, insufficient modeling of cross-agent dependencies may still impair cooperation. In addition, its consistency training process introduces heavy computational and memory costs. Therefore, we propose Coordinated Few-Step Flow (CoFlow), which directly learns a joint averaged-velocity field for distillation-free one-step and few-step multi-agent trajectory generation. To support cooperation during generation, Coordinated Velocity Attention (CVA) incorporates teammate trajectory information into each agent's prediction. To reduce the consistency-training cost of this joint model, we approximate the correction term using finite differences. Across 48 configurations on MPE and SMAC, CoFlow supports centralized and decentralized execution. Under centralized execution, CoFlow outperforms our reproduced baseline by 11.2%, averaging relative gains equally across both benchmark suites, with a 12.93-fold model-sampling speedup. CVA improves normalized scores by 165.1% on average over the same model with cross-agent attention disabled. Compared with the exact-derivative implementation, finite-difference training achieves a 1.78-fold speedup and reduces peak GPU memory by 41.1%. Project page: https://github.com/Guowei-Zou/coflow.

cs.AI↗

UniPolicy: Unified Objective-Specific Policies for Generative Search Advertising

Search advertising connects user intent with commercial content and plays a critical role in platform monetization. Recent systems typically align pretrained generative models with a single business reward, such as eCPM, or use naive reward fusion for preliminary multi-objective alignment. However, an ideal search advertising system must jointly account for heterogeneous objectives, including relevance, click propensity, and commercial value, to balance user experience and business value while mitigating globally suboptimal performance caused by gradient competition. We propose UniPolicy, an objective-aware multi-policy alignment framework. UniPolicy combines objective-specific prefix tokens, sparse MoE-LoRA routing, and objective-specific residual FFNs to hierarchically decouple parameters within a shared backbone, providing differentiated parameter and policy-expression spaces for different business objectives. It further constructs pairwise preferences from multi-stage behavioral feedback, supplementing the relative preference information in exposed-but-unclicked samples and strengthening the relative advantage of clicked candidates in the generation distribution. At inference, UniPolicy supports parallel, business-customizable multi-policy beam search, flexibly allocating candidate quotas across objectives under a fixed retrieval budget. Large-scale offline experiments show that UniPolicy delivers balanced improvements across multiple metrics while preserving retrieval quality, outperforming single-objective reinforcement learning and naive reward-fusion baselines. In a 7-day online A/B test on a real search advertising system, UniPolicy improves CTR by 0.71%, RPS by 1.58%, and advertising revenue by 1.32%, while maintaining stable serving latency.

cs.CL↗

CMRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments

In obstacle avoidance navigation of unmanned aerial vehicles (UAVs), variations in obstacle scale have received less attention than obstacle number or density. Existing methods typically extract purely geometric features from single-frame depth observations. Such representations tend to neglect small obstacles and lose spatial context under occlusions caused by large obstacles, leading to noticeable degradation in environments with multi-scale obstacles. To address this issue, we propose CMRL, a Collision-aware and Memory-enhanced Reinforcement Learning framework for UAV navigation. The collision-aware latent representation encodes risk-sensitive depth cues to preserve fine-grained obstacle structures, thereby improving sensitivity to small obstacles. The temporal memory module integrates observations across frames, mitigating partial observability caused by large-obstacle occlusions. We evaluate CMRL with multi-scale obstacles, including ultra-small and extra-large obstacle settings. Results show that CMRL outperforms state-of-the-art baselines across all scales, with success rate gains of 0.47 and 0.29 in the ultra-small and extra-large settings, respectively. More importantly, CMRL achieves reliable navigation in cluttered outdoor environments. The code is available at https://honghongdev.github.io/camerl/

cs.RO↗