arXiv subjects

Hao Wu

Publications and source records attributed to Hao Wu.

At least 19 recordsLinked to original sources

arXiv2026

Gating and Learnable Temperature for Graph Attention Mechanisms

Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions and use fixed sharpness of attention coefficient distributions. This paper proposes gated graph attention and learnable temperature for common graph attention mechanisms. Gated graph attention filters feature or message responses to reduce the influence of unreliable dimensions, while learnable temperature dynamically adjusts the sharpness of the attention coefficient distribution. We conduct experiments on five standard node classification benchmarks and five heterophilic benchmarks. On most of these benchmarks, our two modifications improve upon the corresponding graph attention backbones, and combining them can yield further gains. Controlled noise experiments further verify the behavior of the proposed mechanisms under feature perturbations. Theoretical analysis explains these results by showing that gating improves robustness when only part of the feature coordinates are reliable, while temperature is beneficial when global noise weakens the discriminability of node features.

cs.LG↗

arXiv2026

Large Excursions of Reflected Lévy Processes: Local Asymptotics

This paper establishes uniform local large-deviation asymptotics for excursions of a Lévy process $X$ with negative drift $-β$ and $α$-locally regularly varying Lévy measure $ν$, reflected at its running infimum. Under the excursion measure $\underline n$, we first prove that the lifetime $ζ$ and height $\overlineε$ satisfy \begin{equation*} \underline{n}\big(ζ\in(t,t+δ] \big) \sim \underline{n}(\overlineε\in\big (βt,βt+βδ]\big) \sim\underline{n}(ζ)\cdotν\big((βt,βt+βδ]\big), \quad \mbox{as } t\to\infty, \end{equation*} uniformly in $δ\in[δ_0,\infty]$ for every $δ_0>0$. In contrast to the asymptotic equivalence of the corresponding tail events, fixed-width lifetime and height windows have asymptotically negligible relative overlap. Nevertheless, for any positive function $θ$ satisfying $|X_t+βt|/θ_t\to0$ in probability, \begin{equation*} \underline n\big( |\overlineε-βt| \leq θ_t \,\big|\, ζ\in (t,t+δ] \big) \sim \underline n\big( |ζ-t| \leq θ_t \,\big|\, \overlineε\in (βt,βt+βδ] \big) \to 1 . \end{equation*} For conditioning windows of sublinear width bounded away from zero, both conditional excursion laws converge under spatial rescaling to a single-jump process with deterministic jump size and random arrival time determined by the integrated excursion survival function. An additional time rescaling yields the same deterministic linear descent killed at zero. Finally, we identify the joint limiting distribution of the unscaled pre-terminal position and terminal overshoot, including continuous and discontinuous termination.

math.PR↗

arXiv2026

CLOSURE: Cross-Channel Closure for Multivariate Time Series Anomaly Detection

Multivariate time series produced by industrial installations and server clusters are under continuous monitoring, and anomaly detection is the first line of defense before a local fault escalates into a system-wide failure. In the absence of labels, the dominant paradigm trains a reconstruction model on normal data and scores the residual to reach a verdict. Recent work has steadily enriched the expressiveness of the recovery map through Transformers, diffusion models, and cross-scale associations. A residual, however, only certifies that an observation can be recovered; it does not certify that the variables still explain one another as they do under normal operation. A coordinated yet unfamiliar operating transition inflates the residual without breaking any relationship, whereas a sensor drifting away from its peers may leave the residual silent. Methods that fold inter-variable dependencies into the reconstruction objective inherit this ambiguity, because their relational evidence is ultimately supervised by the same recovery loss. We therefore propose CLOSURE, which evaluates recoverability and cross-channel consistency as two normal-data prediction tasks learned in separation. The recoverability task is solved by a diffusion reconstructor conditioned on a discrete memory of normal temporal bases. The consistency task is solved by a relation-closure operator that predicts every channel exclusively from the others, where the target's own trajectory is withheld and sparse signed gates decide which peers are actually used. The two scores are reconciled only through calibration on normal data. Extensive experiments show that CLOSURE consistently outperforms recent reconstruction-, frequency-, and topology-based detectors on public benchmark streams, confirming the value of examining consistency alongside recoverability.

cs.AI↗

arXiv2026

Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding

Generative Vision-Language Models (VLMs) express bounding boxes as coordinate sequences, whose token identities often leave axis and place value implicit. We study how explicitly encoding these roles improves visual grounding. Hi-Token assigns a distinct token to each combination of axis, decimal place, and digit value, representing a box with 12 tokens drawn from 60 types. This design exposes coarse-to-fine coordinate structure and increases token reuse relative to atomic location tokens while retaining the existing VLM architecture. Hi-GAR complements this representation with a geometry-based reward for Group Relative Policy Optimization (GRPO), combining box overlap, coordinate accuracy at multiple scales, strict-IoU bonuses, and validity gating. Matched training comparisons show that Hi-Token improves localization throughout the evaluated IoU range, with gains across three VLM backbones. Hi-Token also outperforms an additionally tuned atomic-token baseline on the RefCOCO family before reinforcement learning. Hi-GAR further improves localization and is used only during training. The resulting Hi-R1 model achieves higher values than strong specialist baselines on most reported metrics. Token-frequency and geometric diagnostics characterize the representation and reward stages. These results establish explicit axis and place-value encoding as an effective design for generative visual grounding. Project page: https://xyzzzh.github.io/Hi-Token/

cs.CV↗

arXiv2026

Toward Near-Optimal Floorplanning with Complex Design Constraints for Modern SoCs

Modern system-on-chip (SoC) floorplanning is increasingly challenged by highly coupled complex design constraints. Existing methods often relax constraints into objectives via multi-objective optimization, leading to infeasible solutions or degraded quality. To address this, we formulate the problem as a constrained optimization task and propose a novel three-stage analytical framework integrating semidefinite programming (SDP), augmented Lagrangian method (ALM), and second-order cone programming (SOCP), which enforces constraints more rigorously and achieves higher-quality solutions. First, we adopt a two-step SDP formulation to obtain a robust initialization in the non-convex search space. Next, we incorporate differentiable objectives and constraints into an incremental ALM to jointly handle coupled design constraints during global floorplanning. Finally, an SOCP-based legalization strictly enforces feasibility while further reducing area. Experiments on the FloorSet benchmark show that our method satisfies all constraints with the fastest runtime. Compared with state-of-the-art methods, it reduces wirelength and area by 90\% and 16\% on average, and achieves near-optimal results, with wirelength and area being merely 2\% and 1\% larger than the ground-truth references, respectively.

cs.AR↗

arXiv2026

Replicate What Varies: Resource Sharing for Domain-Randomized Embodied Simulation

Simulation provides a low-cost sandbox where embodied agents can attempt tasks, observe outcomes, and learn from experience. Running many diverse simulation environments concurrently can consume substantial CPU and GPU memory because independently constructed scenes duplicate resources that remain unchanged across instances. We present Patchwork, a resource-sharing system for domain-randomized simulation, built around the representation $E=T+Δ$: a shared template contains common resources, and a patch records the mutations needed to construct a target environment. Patchwork separates randomization sampling from replay and selects reusable templates together with patches that preserve each target environment's intended configuration. Its layered runtime shares compiled model structure and immutable assets while keeping mutable parameters and simulation state private to each instance. We implement Patchwork on robosuite and MuJoCo and evaluate it on LIBERO-plus and RoboCasa365 workloads. At 32 replicas, shared-template execution reduces CPU RSS by 88-92% relative to process-per-environment execution. Controlled experiments show how sharing shifts memory growth toward template diversity and unique asset content rather than instance count, within the supported sharing boundaries.

cs.DC↗

arXiv2026

Rescuing Your Pruning: Rethinking Visual Token Pruning and Post-Training Recovery in MLLMs

Visual token pruning substantially reduces the inference cost of multimodal large language models (MLLMs), yet existing methods are mostly training-free and plug-and-play. They treat the resulting performance drop as an inevitable cost of compression and pursue increasingly complex pruning rules. We rethink this view through two questions: how much of the loss can post-training rescue, and, building on this recovery, how can joint compression push pruning to its limit? We curate a 282K-sample post-training mixture covering general VQA, reasoning, OCR, and grounding, and post-train 36 configurations that drop or merge tokens under a unified protocol. Post-training rescues most of the loss, even for OCR and grounding, and its adaptation gain in closing the gap between the pruned and the dense model grows as the budget tightens. For joint compression, we find that the vision encoder, not the LLM, dominates prefill time in native-resolution MLLMs, so where tokens are removed matters more than how many: keeping 40% of tokens at the encoder runs faster than keeping 10% at the projector. Our best configuration prunes the encoder lightly and the projector aggressively, leaves the LLM intact, and keeps general understanding and reasoning at the dense level. It accelerates the LLM stage by 3.49x but the end-to-end time-to-first-token by only 1.54x, showing that LLM-stage speedups overstate end-to-end gains. We hope these findings offer insights for future research on joint visual token compression. Our data, protocol, and code will be released.

cs.CV↗

arXiv2026

foap4: Adaptive mesh refinement with OpenACC/OpenMP, MPI, and p4est

GPUs and other accelerators are increasingly used for scientific computing. We want to add GPU support to existing parallel adaptive mesh refinement (AMR) codes written in Fortran. To understand which changes are necessary to obtain good performance we have developed foap4, an AMR framework implemented in Fortran that uses OpenACC/OpenMP, MPI, and the p4est library. We discuss the design and implementation of the framework. Several benchmark problems are considered, in which Euler's equations of gas dynamics are solved using explicit time integration. These benchmarks are performed in both 2D and 3D, using static and adaptive meshes, for varying problem sizes on different hardware. Our results show that AMR simulations can be carried out efficiently on GPUs, even when using relatively small grid blocks of $8^3$ or $16^3$ cells. With NVIDIA's nvfortran compiler similar performance is obtained with OpenACC and OpenMP offloading. Initial results with the gfortran compiler and OpenACC demonstrate the portability of foap4.

physics.comp-ph↗

arXiv2026

A Large-Volume GAGG(Ce) Detector Module for In-Beam $γ$-Ray Spectroscopy

We report on the development and characterization of large-volume GAGG(Ce) scintillation detector modules equipped with silicon photomultiplier (SiPM) readout. Each module houses four large-volume GAGG(Ce) crystals within a compact thin carbon-fiber enclosure, minimizing the passive material budget and enabling the construction of high-efficiency, large-solid-angle detector arrays for in-beam $γ$-ray spectroscopy. The performance of 10 GAGG modules (40 detectors), including the energy linearity, energy and timing resolution, and intrinsic full-energy peak efficiency, was evaluated using standard $γ$-ray sources and $^{14}$N(p,$γ$)$^{15}$O reactions, covering a $γ$-ray energy range from about 0.3 MeV to 8 MeV. Non-linear energy response across the measured energy range was observed due to the non-linear response of the SiPM. The detector modules exhibit good energy resolution (FWHM below 5\% at 1.33 MeV), good timing resolution (FWHM $\sim$500 ps at $\sim$1 MeV), and intrinsic full-energy peak efficiencies in good agreement with Geant4 simulations, making the detector modules a promising solution for next-generation high efficiency in-beam $γ$-ray experiments at RI-beam facilities.

physics.ins-det↗

arXiv2026

Multiple SLEs and Dyson Brownian motion: transition density and Green's function

We consider multiple chordal Schramm-Loewner evolution (SLE) with $κ\in (0,4]$. Under common-time parameterization, we show that the transition density of the driving function of multiple chordal SLEs can be given by the transition density of Dyson Brownian motion and Green's function. This is a companion paper of [FWY24].

math.PR↗

arXiv2026

Group Contrastive Policy Optimization: Learning Beyond the Self-Exploration Limit with Golden Answers

Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving the reasoning abilities of large language models, yet group-based methods lose their learning signal when every sampled response receives zero reward. We propose Group Contrastive Policy Optimization (GCPO), a hybrid objective that preserves standard on-policy optimization for informative rollout groups and activates a proximal contrastive objective only when exploration completely fails. The auxiliary objective pairs an offline golden reasoning trajectory with the current policy's failed responses, thereby providing a reliable positive reference and prompt-specific hard negatives without treating the golden trajectory as an on-policy rollout. Its old-policy token probabilities are evaluated through teacher forcing and used solely to constrain the update, rather than as an importance-sampling correction for the teacher distribution. A first-order analysis shows that the resulting update increases a length-normalized likelihood margin between reliable reasoning and observed failures. Experiments across two model scales and 10 core mathematical reasoning benchmarks demonstrate that GCPO improves training efficiency and final reasoning performance over competitive supervised and RLVR baselines.

cs.AI↗

arXiv2026

ATTUNE: Agentic Throughput Tuning for LLM Training

The throughput of an LLM training job depends on its recipe: how the model is split across GPUs, how memory is traded for compute, and which kernels and communication overlaps it uses. The best recipe changes with every model, accelerator and framework version. Automated tuners search a fixed space of knobs and check only that a job runs, so they miss levers outside that space and can ship a configuration that silently changes training. ATTUNE is a coding agent that tunes any working recipe unattended within a GPU-hour budget. Guided by a skill of search rules, scripts and lessons from past tuning campaigns, it diagnoses each run and changes one lever at a time. A correctness gate outside the agent refuses any argument known to change the training objective. ATTUNE tunes Amazon's production post-training recipes on H100, H200 and B200 clusters, raising throughput by 1.7x on average. It beats the published throughput of four of NVIDIA's own benchmark recipes on NVIDIA's AutoModel framework by 6-17%. On models held out from its development, it improves the strongest public recipes most where they were written for another setting, by up to 2.6x on MiniMax-M2, and least where the vendor tuned them for the same hardware. Given the same GPU-hour budget, it outperforms existing automated tuners, including Bayesian optimization, random search and OptiCo, a recent LLM-agent tuner. Its gain on GLM-4.5 is more than four times the best alternative's. The same coding agent without ATTUNE's skill gains less and fails half its launches. We release ATTUNE at https://github.com/amazon-science/attune and OpenRecipes, a leaderboard of tuned and verified training recipes, at https://openrecipes.ai.

cs.DC↗

arXiv2026

simesh: A Python Framework for Quantitative Analysis of Native AMR Data from MPI-AMRVAC

Adaptive mesh refinement (AMR) is widely used in large-scale astrophysical simulations, but the resulting multilevel data are challenging to analyze quantitatively. We present simesh, an independent Python framework for quantitative analysis of cell-centered fields on block-structured AMR meshes. The current implementation targets three-dimensional Cartesian datasets from MPI-AMRVAC and compatible AGILE snapshots, preserving the native AMR hierarchy and connecting complementary scientific diagnostics within a common numerical representation. The framework combines Python workflow interfaces with compiled Cython kernels, supporting efficient analysis on AMR meshes. We compare native AMR analysis with a VTK point-data conversion and uniform-grid resampling, which shows that changes in data association, interpolation support, and differentiation scale affect both sampled magnetic fields and derived current densities. Small differences in the sampled primary field can become more pronounced in derivative-based quantities, particularly near coarse-fine interfaces. The applications combine field diagnostics, tracing, regional statistics, and line-of-sight integration on the same native AMR representation. simesh makes these operations available through reusable Python interfaces for reproducible analysis of multiscale simulation data.

astro-ph.SR↗

arXiv2026

Symmetry-Preserving Local Representation for Short-Range Interaction in Complex Materials

Modeling short-range interactions in highly disordered materials remains challenging due to the immense configuration space and the disruption of local symmetry in truncated theoretical models. Here, we propose a symmetry-preserving local representation framework that strictly enforces topological continuity and translational invariance via boundary passivation. Applied to high-entropy alloys, this approach autonomously unravels the nonlinear ligand effects modulating local reactivity and accurately captures coverage-dependent many-body interactions without explicit periodic expansion. By resolving the conflict between localized chemical environments and extended periodic boundaries, this framework not only reduces computational complexity by an order of magnitude but also provides a physically transparent paradigm for deciphering short-range order in complex condensed matter systems.

cond-mat.dis-nn↗

arXiv2026

Delta N-gram: Forward-Only Continual Writing into a Language Model's Native N-gram Memory

Our previous analysis found that a model's native hashed N-gram table is where continual updates disturb the base least, but its writes needed backpropagation and changed the pretrained table. We present Delta N-gram, a forward-only write path into that table. The pretrained table T^0 is never modified. Evidence is written into a sparse patch Δon the rows it addresses: a 4.1M-parameter writer emits a target and a gate per (position, hash head) event, and a block-averaged delta rule keeps each row a convex combination of its old value and the gated targets. The writer is trained offline on raw text with the pretraining objective; at use time writing takes forward passes only, and clearing Δrestores the original model. A 0.6B prototype trained to answer questions keeps 16/16 facts after a second write; online gradient writes keep 2--4/16. We study two writers: a plain writer that encodes evidence with the T^0-only model, and a delta writer that reads its current memory while encoding. On Qwen3.8-Flash-Next, the plain writer's memory is document-specific: on 64 held-out news events it lowers continuation NLL by 0.068 nats/token against empty memory and by 0.024 against another document's memory, and 0.063 and 0.013 after 16 intervening articles. The delta writer's memory is more document-specific and keeps more of it under distraction (70% vs 54%). Over 35,000 writes on our previous seven-task chain both writers stay stable and the delta writer drifts less (layer-2 math drift 176% vs 188%); later accuracy changes by -0.26/-0.52pp (-7.29pp for gradient updates) and small-k_i drift is 17.9/17.5% (39.2%). Acquisition is negative, and general-input drift reaches 32.8% (20.75%): format rows read by every example grow to 4--12 times their pretrained norm. Zeroing eight such rows removes over 98% of layer-2 drift on math inputs, together with their NLL gain.

cs.CL↗

arXiv2026

Weaponizing the Exit: Input Privacy Leakage via Exit Routing Manipulation in Multi-Exit Networks

Multi-exit networks improve inference efficiency by allowing inputs to terminate early at intermediate exits. We identify a privacy vulnerability in cloud deployments of these networks: a malicious Cloud Service Provider (CSP) can infer sensitive properties of individual user inputs solely from inference latency, without accessing inputs, intermediate states, or model outputs. The attack exploits the CSP's control over the model supply chain. Prior to deployment, the CSP supplies a specially crafted multi-exit network manipulated so that inputs carrying a target sensitive property are routed to a designated exit with high probability, while other inputs exit elsewhere. At serving time, the CSP infers the exit index from per-query latency, thereby determining whether each input possesses the target property without accessing inputs, outputs, or internal model states. We propose a training framework combining selective label smoothing and entropy-covariance optimization to control confidence distributions across exits and reduce premature termination. We conduct experiments on four datasets across ten target properties. The results demonstrate strong attack effectiveness and stealthiness. The attack achieves an average F1 score of 0.73, compared to 0.25 for the strongest baseline, while main task accuracy drops by less than 1.3\% and inference speedup degradation remains below 0.1 in most settings. Our code is available at https://github.com/kazefjj/Weaponizing_the_Exit.

cs.CR↗

arXiv2026

Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate

Multi-Agent Debate (MAD) improves the reasoning performance of Large Language Models (LLMs) through multi-round interaction. However, LLMs in MAD are highly susceptible to blind conformity. Existing individual evaluation methods, typically based on confidence or perplexity, fail to reflect the correctness of reasoning and may even exacerbate blind conformity. To address this, we shift the perspective from individual evaluation to group interaction. We define mutual referencing among LLMs as \textbf{Debate Relationships} and recognize that regulating these relationships is the key to mitigating blind conformity. In this paper, we propose a novel framework for \textbf{D}ynamically r\textbf{E}gulating deb\textbf{A}te \textbf{R}elationships (DEAR) from the group perspective. At first, DEAR quantifies consensus and divergence as \textit{group evidence} to capture the debate state. Then, DEAR operates through three stages: 1) What: perceiving group consultation tendency and uncertainty; 2) Who: introducing a Selection RL-Agent to dynamically select reference peers; and 3) How: adopting a Behavior RL-Agent to adaptively adjust generation behaviors. Notably, we formulate the execution of the two RL-Agents as a sequential decision-making process, jointly optimizing via multi-agent reinforcement learning. Extensive experiments demonstrate that DEAR achieves superior performance while significantly reducing token consumption.

cs.MA↗

arXiv2026

DriftNeRF: Cross-Ray Density Drifting for Sparse-View Neural Radiance Fields

Neural Radiance Fields (NeRF) synthesize photorealistic novel views from dense image collections, but degrade sharply when few views are available. We attribute a specific, measurable defect to the objective itself: the rendering loss is a sum over independent rays and contains no term comparing densities that different rays assign to the same region of space, so nearby 3D points can settle on contradictory densities while every training pixel is reproduced correctly. We make this quantity explicit by measuring cross-ray density disagreement directly during training, and show that it stays high in vanilla NeRF, falls only incidentally under frequency-based regularization, and moves together with held-out quality in the sparse regime. We then close the gap with DriftNeRF, a drop-in regularizer that instantiates the drifting-field template on density samples: a masked exponential kernel aggregates densities from nearby points on other rays into a stop-gradient consensus target, and the resulting drifting field penalizes unsupported disagreement while leaving agreed-upon boundaries intact. The regularizer reads only sampled positions, ray identifiers, and predicted densities, so it requires no pretrained model, external geometry, or additional images, and transfers across field parameterizations. On NeRF-Synthetic it reduces residual disagreement by an order of magnitude, and across NeRF-Synthetic, DTU, and LLFF it improves 3-view PSNR over the strongest MLP-NeRF baseline by 0.42-0.65 dB and remains competitive with sparse-view Gaussian pipelines under a matched protocol without their depth, flow, or covisibility preprocessing.

cs.CV↗