arXiv subjects

Hao Ma

Publications and source records attributed to Hao Ma.

At least 19 recordsLinked to original sources

arXiv2026

Engram-E2VID: Reference-Based Event-to-Video Reconstruction via Generative Activation of Appearance Engrams

Reference-based event-to-video reconstruction aims to recover target RGB frames from a reference frame and the event stream captured over the reference-to-target interval. Although events provide fine-grained temporal cues, they encode sparse and asynchronous log-intensity changes rather than absolute appearance, making faithful reconstruction intrinsically challenging. The central challenge lies in associating event-derived target-time structures with relevant appearance information from the reference frame, especially under complex motion and long temporal intervals. In this work, we propose Engram-E2VID, a structure-guided framework that reconstructs target frames through the generative activation of appearance engrams. Specifically, the reference frame is encoded into token-space appearance engrams, while the event stream and reference context are transformed into a target-time motion-structure scaffold that captures motion boundaries and event-induced structural changes. Within a one-step diffusion backbone, scaffold-derived structural tokens progressively interact with and activate relevant appearance engrams across layers. This token-space association allows target structures to access reference appearance without relying on direct pixel-wise correspondence, while the diffusion prior complements uncertain or newly revealed regions. Across three benchmarks, Engram-E2VID improves PSNR by up to 3.29 dB and reduces LPIPS by up to 0.08 over the strongest same-input baseline, while degrading more slowly as the reconstruction interval increases.

cs.CV↗

arXiv2026

LLM-PDESR: Robust PDE Discovery via Subdomain Weighted Residuals and LLM-Guided Symbolic Hypothesis Generation

Discovering governing partial differential equations (PDEs) from noisy observational data is a fundamental challenge in scientific machine learning. Traditional symbolic regression (SR) methods often struggle to identify accurate equations within vast combinatorial search spaces, largely due to their inability to incorporate essential domain-specific prior knowledge. Furthermore, reliance on pointwise evaluations and discrete finite differences inherently amplifies high-frequency noise, creating deceptive fitness landscapes that derail the optimization process. To resolve these bottlenecks, we propose LLM-PDESR, a framework that integrates the structural hypothesis generation of Large Language Models (LLMs) with a mathematically rigorous evaluation environment. By employing C^4-continuous quintic splines for robust differentiation and subdomain weighted residuals as natural low-pass filters, our approach effectively mitigates the fitness landscape distortion that plagues existing methods. A Pareto-driven feedback loop then enables the LLM to iteratively refine candidate equations, balancing predictive accuracy with structural parsimony. We evaluate LLM-PDESR on 23 canonical PDEs and five structurally novel equations (including a multivariate system) specifically designed to preclude dataset memorization and test true discovery capabilities. Demonstrating real-world applicability, the framework successfully extracts a consistent structural skeleton for an interpretable 1D dynamical surrogate (1D-CACE) directly from noisy ERA5 reanalysis data. Extensive experiments and out-of-distribution testing confirm that LLM-PDESR significantly outperforms state-of-the-art methodologies in structural recovery, noise resilience, and the avoidance of spurious complexity and equation bloat.

cs.LG↗

arXiv2026

Solving Hamiltonian Constraint Equation with Physics-Informed Neural Networks

Numerical relativity (NR), solving Einstein equation numerically, plays an important role in source modelling for gravitational wave astronomy. Traditional methods for NR including finite difference method, spectral method and finite element method have been well developed. But newly developed neural network methods for partial differential equations (PDE) have not been well studied yet for NR. We present a Physics-Informed Neural Network (PINN) method to solve the Hamiltonian constraint equation for binary black hole (BBH) initial data in NR. This equation is a highly non-linear elliptic PDE, posing significant challenges for conventional PINN approaches. To overcome these difficulties, we introduce a set of new techniques. We show that our PINN together with these techniques can successfully solve the Hamiltonian constraint equation for generic BBH systems. Validation against the traditional results demonstrates the high accuracy and robustness of our method, revealing the immense potential of constructing a PINN-based initial data solution to all BBH systems for NR.

gr-qc↗

arXiv2026

Knowledge-Enhanced Agentic Vulnerability Repair

Frontier foundation models have changed the math on vulnerability discovery, but the bigger challenge is how the remediation side keeps up. Despite recent progresses in Automated Vulnerability Repair (AVR), current solutions struggle to reliably identify the root causes of vulnerabilities, and insufficiently utilize the prior fix knowledge to guide the patch generation process, thus undermining their effectiveness in practice. To address this gap, we propose KeaRepair, a novel agentic AVR approach that grounds patch generation in verified program facts and high-level vulnerability knowledge. Specifically, KeaRepair first extracts multi-dimensional vulnerability knowledge from historical vulnerability-patch pairs from dual complementary views, and constructs dedicated retrieval knowledge bases. It then employs a tool-augmented agent that performs ReAct-style reasoning to collect verified program facts for vulnerability diagnosis. Finally, based on the diagnostic results, KeaRepair performs knowledge-level retrieval-augmented patch generation and iteratively refines patches through a closed-loop validation process involving compilation, PoC replay, and test-suite execution. Experimental results show that KeaRepair significantly outperforms existing AVR approaches on 55 reproducible C/C++ vulnerabilities. When paired with Gemini-3.1-Pro, KeaRepair successfully repairs 46 vulnerabilities, achieving a repair rate of 83.64%. Moreover, KeaRepair fixes six unique vulnerabilities that none of the baselines can address, and further demonstrates strong cross-language generalizability.

cs.SE↗

arXiv2026

Positive-Incentive Noise Predictor for Adversarial Purification in Speaker Verification

Modern automatic speaker verification (ASV) systems are vulnerable to adversarial perturbations. Diffusion-based purification has recently shown strong effectiveness against such perturbations, but its reverse denoising process requires iterative sampling and leads to high inference latency. We find that the forward noising process provides most of the robustness gain. Motivated by this observation, we reformulate adversarial purification as a learnable noising problem, and propose the Positive-Incentive Noise Predictor (PnP), the first framework that explicitly introduces positive-incentive noise ({\pi}-noise) into the purification task. PnP learns input-adaptive {\pi}-noise and mixes it with the input to improve the robustness of downstream ASV systems. Experiments on four advanced ASV backbones show that PnP effectively defends against adversarial attacks while preserving performance on natural speech. Compared with representative purification baselines, the proposed framework provides a competitive balance among defense effectiveness, impact on genuine utterances, and inference efficiency under white-box, black-box, and defender-aware adaptive attacks, with a real-time factor as low as 0.014. Moreover, PnP can be cascaded with a diffusion denoiser to further improve the perceptual quality of purified utterances. Code and purified audio examples are available at https://eurecom-asp.github.io/pnp/

eess.AS↗

arXiv2026

Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control

Diffusion models sample effectively from high-dimensional, multimodal distributions, but their outputs may violate deployment constraints. For task-space robot policies, generated grasps, waypoints, or trajectories can be distributionally valid yet infeasible, violating reachability, collision-avoidance, or closed-loop executability requirements. This embodiment gap limits zero-shot deployment across robots, even when the task-space behavior itself is transferable. We propose an inference-time optimization framework that couples the behavior generation to physical feasibility by formulating diffusion guidance as a constrained optimization problem. Our key insight is to replace the sampling perturbation in the backward process with an optimized correction, allowing hard constraints or soft penalties to be imposed during sampling without the need to retrain the diffusion model, while keeping samples close to the learned prior. We evaluate the method on dexterous grasp synthesis with reachability and collision-avoidance constraints, and dynamic manipulation with controller-level trackability constraints. Across settings and robot embodiments, optimization-guided denoising matches the feasibility of projection- and gradient-guidance baselines while better preserving grasp quality, and improving controller-level executability and task success, with task success improving by up to 20pp. on dexterous grasping and 23pp. on visuomotor manipulation over the best baseline.

cs.RO↗

arXiv2026

A Minute-Cadence Deep Bulge Survey: First Data Release of DREAMS

The DECam Rogue Earths and Mars Survey (DREAMS), a NOIRLab survey program, has been conducting a three-year survey covering a 5 deg$^2$ area in the Galactic bulge (roughly spanning $-1.2^\circ \lesssim \ell \lesssim +2.1^\circ$ and $-2.8^\circ \lesssim b \lesssim -0.6^\circ$) since 2025 June. Its primary science goal is to detect low-mass free-floating planets through microlensing, while its minute-level cadence ($20-40\,\mathrm{hr}^{-1}$ in $z$ band and $4-8\,\mathrm{hr}^{-1}$ in $r$ band) also enables the detection and characterization of rapid phenomena on timescales of minutes to hours such as stellar flares and pulsating stars. The survey reaches a single-exposure depth of $z_{\rm AB}\sim 22$ mag, about two magnitudes deeper than previous bulge time-domain surveys. We present the data reduction and calibration of the DREAMS observations obtained in 2025 and introduce the first DREAMS data release (DR1). DR1 includes 1,856 $z$-band observations and 325 $r$-band observations for 59,372,789 stars. The DREAMS DR1 catalog contains about twice as many stars as previous catalog covering the same 5 deg$^2$ area. We present DREAMS light curves for a known blue large-amplitude pulsator (BLAP) and a known low-amplitude transiting system to demonstrate the survey's capabilities. We also perform a pilot search for short-duration variables over about 0.4% of the DR1 sample, identifying one new short microlensing event, two stellar flares, and 24 new short variables. This suggests that DREAMS DR1 may contain hundreds of stellar flares and thousands of previously unknown short variables.

astro-ph.SR↗

arXiv2026

Vib2Conf: AI-driven discrimination of molecular conformations from vibrational spectra

Retrieving or generating two-dimensional molecular structures on the basis of vibrational spectra has been well demonstrated via deep learning models. However, deciphering three-dimensional molecular conformations is still challenging, primarily due to spectral ambiguities caused by conformational heterogeneity, which are difficult to resolve. To address this limitation, we propose Vib2Conf, a deep learning model directly discriminating 3D molecular conformations from vibrational spectra. We implement an attentional resampler to distill conformation-sensitive features from sparse spectral signals, and integrate Mixture-of-Experts (MoE) to partition the conformational space for precise geometric mapping. These modules enable Vib2Conf to achieve state-of-the-art top-1 recall exceeding 95% on traditional spectrum-structure benchmarks, including QM9S, VB-Mols, and QMe14S. More importantly, Vib2Conf can discriminate near-isomeric conformers with a top-1 recall of 82.06% on VB-Confs test set, where conformational isomers differ by a root-mean-square deviation (RMSD) of only ~1 {\AA}. In general, Vib2Conf is a promising method for fine-grained spectrum-to-conformation analysis.

physics.chem-ph↗

arXiv2026

CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding

Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object constancy. In addition, existing approaches typically rely on expensive human annotations or large-scale chain-of-thought (CoT) data generation. We propose Compositional Grounded Contrast (abbr. CGC), a low-cost full framework for boosting fine-grained multi-image understanding of MLLMs. Built on existing single-image grounding annotations, CGC constructs compositional multi-image training instances through Inter-Image Contrast and Intra-Image Contrast, which introduce semantically decoupled distractor contexts for cross-image discrimination and correlated cross-view samples for object constancy, respectively. CGC further introduces a Rule-Based Spatial Reward within the GRPO framework to improve source-image attribution, spatial alignment, and structured output validity under a Think-before-Grounding paradigm. Experiments show that CGC achieves state-of-the-art results on fine-grained multi-image benchmarks, including MIG-Bench and VLM2-Bench. The learned multi-image understanding capability also transfers to broader multimodal understanding and reasoning tasks, yielding consistent gains over the Qwen3-VL-8B base model on MathVista (+2.90), MuirBench (+2.88), MMStar (+1.93), MMMU (+1.77), and BLINK (+1.69).

cs.CV↗

arXiv2026

StreamingClaw Technical Report

Emerging applications such as embodied intelligence, AI hardware, autonomous driving, and intelligent cockpits rely on a real-time perception-decision-action closed loop, posing stringent challenges for streaming video understanding. However, current agents mostly suffer from fragmented capabilities, such as supporting only offline video understanding, lacking long-term multimodal memory mechanisms, or struggling to achieve real-time reasoning and proactive interaction under streaming input. These shortcomings have become a key bottleneck for preventing agents from sustaining perception, making real-time decisions, and executing closed-loop actions in complex real-world environments, constraining their deployment and potential in dynamic, open physical worlds. To alleviate these issues, we propose StreamingClaw, a unified agent framework for streaming video understanding and embodied intelligence. Beyond maintaining full compatibility with the OpenClaw framework, it natively supports real-time, multimodal streaming interactions. StreamingClaw integrates five core capabilities: (1) It supports real-time streaming reasoning. (2) It supports reasoning about future events and proactive interaction under the online evolution of interaction objectives. (3) It supports multimodal long-term memory storage, hierarchical memory evolution, efficient memory retrieval, and memory sharing across multiple agents. (4) It supports a closed loop of perception-decision-action. In addition to conventional tools and skills, it also provides streaming tools and action-centric skills tailored for real-world physical environments. (5) It is compatible with the OpenClaw framework, allowing it to leverage the resources and support of the open-source community.

cs.CV↗

arXiv2026

Efficient Soft Actor-Critic with LLM-Based Action-Level Guidance for Continuous Control

We present GuidedSAC, a novel reinforcement learning (RL) algorithm that facilitates efficient exploration in vast state-action spaces. GuidedSAC leverages large language models (LLMs) as intelligent supervisors that provide action-level guidance for the Soft Actor-Critic (SAC) algorithm. The LLM-based supervisor analyzes the most recent trajectory using state information and visual replays, offering action-level interventions that enable targeted exploration. Furthermore, we provide a theoretical analysis of GuidedSAC, proving that it preserves the convergence guarantees of SAC while improving convergence speed. Through experiments in both discrete and continuous control environments, including toy text tasks and complex MuJoCo benchmarks, we demonstrate that GuidedSAC consistently outperforms standard SAC and state-of-the-art exploration-enhanced variants (e.g., RND, ICM, and E3B) in terms of sample efficiency and final performance.

cs.LG↗

arXiv2026

Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner

Constraints are essential for stabilizing reinforcement learning fine-tuning (RFT) and preventing degenerate outputs, yet they inherently conflict with the optimization objective because stronger constraints limit the ability of a fine-tuned model to discover better solutions. We propose \textit{dynamic constraints} that resolve this tension by adapting to the evolving capabilities of the fine-tuned model based on the insight that constraints should only intervene when degenerate outputs occur. We implement this by using a reference model as an \textit{online refiner} that takes the response from the fine-tuned model and generates a minimally corrected version which preserves correct content verbatim while fixing errors. A supervised fine-tuning loss then trains the fine-tuned model to produce the refined output. This mechanism yields a constraint that automatically strengthens or relaxes based on output quality. Experiments on dialogue and code generation show that dynamic constraints outperform both KL regularization and unconstrained baselines, achieving substantially higher task rewards while maintaining training stability.

cs.LG↗

arXiv2026

Denoising diffusion and latent diffusion models for physics field simulations

Accurate prediction of physical fields is critical in various engineering applications, including thermal management in electronic systems, airfoil shape optimization in aerospace, and flow field control in hypersonic vehicles. This study employs the Denoising Diffusion Probabilistic Models (DDPMs) for predicting the temperature field caused by the thermal diffusion, and the flow fields spanning from incompressible to hypersonic regimes. A conditional DDPM framework is first validated with a steady-state thermal diffusion problem by predicting the temperature distribution around a plate with holes. Strong agreement with ground truth data is shown with an average error of approximately 0.013 for plates with a central circular hole. The model also delivers high accuracy in critical regions, such as near the inner circular or square holes. Its performance is further evaluated on incompressible flow around an airfoil and hypersonic flow over a compression ramp, confirming robust predictive capability across diverse flow conditions. Additionally, a latent-space implementation of DDPM is introduced, which employs an Autoencoder (AE) for dimensionality reduction and reconstruction of the physical data. The resulting Latent Diffusion Model (LDM) maintains reconstruction quality comparable to the standard DDPM while substantially reducing the computational cost of the diffusion training process. When applied to hypersonic flow over a compression ramp in the original parameter space, LDM predictions align well with ground truth, achieving a deviation of only 4.28% in separation length estimation. This work confirms the high predictive accuracy of the DDPM framework and highlights the efficiency gains from performing diffusion in a learned latent space. The findings establish an efficient framework for high fidelity generative modeling of complex thermal/flow fields.

physics.flu-dyn↗

arXiv2026

Evaluating the Search Agent in a Parallel World

Integrating web search tools has significantly extended the capability of LLMs to address open-world, real-time, and long-tail problems. However, evaluating these Search Agents presents formidable challenges. First, constructing high-quality deep search benchmarks is prohibitively expensive, while unverified synthetic data often suffers from unreliable sources. Second, static benchmarks face dynamic obsolescence: as internet information evolves, complex queries requiring deep research often degrade into simple retrieval tasks due to increased popularity, and ground truths become outdated due to temporal shifts. Third, attribution ambiguity confounds evaluation, as an agent's performance is often dominated by its parametric memory rather than its actual search and reasoning capabilities. Finally, reliance on specific commercial search engines introduces variability that hampers reproducibility. To address these issues, we propose a novel framework, Mind-ParaWorld, for evaluating Search Agents in a Parallel World. Specifically, MPW samples real-world entity names to synthesize future scenarios and questions situated beyond the model's knowledge cutoff. A ParaWorld Law Model then constructs a set of indivisible Atomic Facts and a unique ground-truth for each question. During evaluation, instead of retrieving real-world results, the agent interacts with a ParaWorld Engine Model that dynamically generates SERPs grounded in these inviolable Atomic Facts. We release MPW-Bench, an interactive benchmark spanning 19 domains with 1,608 instances. Experiments across three evaluation settings show that, while search agents are strong at evidence synthesis given complete information, their performance is limited not only by evidence collection and coverage in unfamiliar search environments, but also by unreliable evidence sufficiency judgment and when-to-stop decisions-bottlenecks.

cs.AI↗

arXiv2026

Simulation Study on the Discrimination of $0\nu\beta\beta$ Events from Single-Electron Events Using Orthogonal-Strip HPGe Detectors

Neutrinoless double beta decay ($0\nu\beta\beta$) offers a sensitive probe of neutrino mass and its Majorana nature. Orthogonal-strip high-purity germanium (HPGe) detectors with high spatial resolution provide a promising approach for distinguishing $0\nu\beta\beta$ events from single-electron backgrounds. In this work, a simulation framework was developed to evaluate the discrimination performance of these detectors. The framework combined Geant4 simulations with a hybrid numerical-analytical approach to model charge cloud dynamics. A dual-branch convolutional neural network (CNN) was implemented to extract topological features for event classification. The impact of detector geometry on discrimination performance was quantitatively assessed. For a fixed crystal thickness of 15 mm, the background rejection efficiency decreased from 79.5\% to 59.0\% as the strip pitch increased from 0.1 mm to 0.5 mm. For a strip pitch of 0.25 mm, a crystal thickness of 20 mm was found to be optimal, balancing full-energy peak (FEP) efficiency with discrimination capability. These results demonstrate that orthogonal-strip HPGe detectors can effectively suppress single-electron backgrounds, and provide quantitative guidance for detector design in $^{76}$Ge $0\nu\beta\beta$ decay searches.

physics.ins-det↗

arXiv2026

Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning

Existing Tool-Integrated Reasoning (TIR) models have effectively extended the question-answering capabilities of LLMs by incorporating external tools. However, real-world scenarios present numerous open-ended problems where fixed tools often fail to meet task requirements. Furthermore, the lack of self-optimization mechanisms means that erroneous tool outputs can mislead the LLM's responses. Additionally, the construction of existing tools entails significant manual effort, which consequently constrains their applicability. Recognizing that the reasoning traces of LLMs encapsulate implicit problem-solving capabilities, we propose UCT, a novel training-free framework that transforms agents from tool users to tool creators. This approach harvests reasoning experiences and distills them into reusable assets. This method transforms the agent from a mere tool user into a tool creator, enabling adaptive tool creation and self-updating during the inference process. We also introduce a memory consolidation mechanism to maintain the tool library, ensuring high reusability of retained experiential memory for subsequent reasoning tasks. This novel automated tool construction paradigm continuously improves tool quality during reasoning, allowing the overall agent system to progress without additional training. Extensive experiments demonstrate that our method serves as a novel paradigm for enhancing the capabilities of TIR models. In particular, the significant performance gains achieved +20.86%$\uparrow$ and +23.04%$\uparrow$ on benchmarks across multi-domain mathematical and scientific reasoning tasks validate the self-evolving capability of the agent.

cs.AI↗

arXiv2026

SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference

Modern large language models are increasingly deployed under compute and memory constraints, making flexible control of model capacity a central challenge. While sparse and low-rank structures naturally trade off capacity and performance, existing approaches often rely on heuristic designs that ignore layer and matrix heterogeneity or require model-specific architectural modifications. We propose SALAAD, a plug-and-play framework applicable to different model architectures that induces sparse and low-rank structures during training. By formulating structured weight learning under an augmented Lagrangian framework and introducing an adaptive controller that dynamically balances the training loss and structural constraints, SALAAD preserves the stability of standard training dynamics while enabling explicit control over the evolution of effective model capacity during training. Experiments across model scales show that SALAAD substantially reduces memory consumption during deployment while achieving performance comparable to ad-hoc methods. Moreover, a single training run yields a continuous spectrum of model capacities, enabling smooth and elastic deployment across diverse memory budgets without the need for retraining.

cs.LG↗

arXiv2026

High-Fidelity Generative Audio Compression at 0.275kbps

High-fidelity general audio compression at ultra-low bitrates is crucial for applications ranging from low-bandwidth communication to generative audio-language modeling. Traditional audio compression methods and contemporary neural codecs are fundamentally designed for waveform reconstruction. As a result, when operating at ultra-low bitrates, these methods degrade rapidly and often fail to preserve essential information, leading to severe acoustic artifacts and pronounced semantic distortion. To overcome these limitations, we introduce Generative Audio Compression (GAC), a novel paradigm shift from signal fidelity to task-oriented effectiveness. Implemented within the AI Flow framework, GAC is theoretically grounded in the Law of Information Capacity. These foundations posit that abundant computational power can be leveraged at the receiver to offset extreme communication bottlenecks--exemplifying the More Computation, Less Bandwidth philosophy. By integrating semantic understanding at the transmitter with scalable generative synthesis at the receiver, GAC offloads the information burden to powerful model priors. Our 1.8B-parameter model achieves high-fidelity reconstruction of 32kHz general audio at an unprecedented bitrate of 0.275kbps. Even at 0.175kbps, it still preserves a strong intelligible audio transmission capability, which represents an about 3000x compression ratio, significantly outperforming current state-of-the-art neural codecs in maintaining both perceptual quality and semantic consistency.

eess.AS↗