arXiv subjects

Hua Huang

Publications and source records attributed to Hua Huang.

At least 19 recordsLinked to original sources

arXiv2026

R2QRec: Learning Recommendation Queries from Retrieval Feedback

Query-based recommendation separates expressing user needs from locating matching items. Its central learning problem is how to turn item interactions into effective retrieval requests when interaction logs do not annotate queries. We present R2QRec, which uses a fixed retrieval system to construct query supervision and evaluate recommendation outcomes. Retrieval verification first selects generated expressions that recover observed items as supervised fine tuning targets, allowing retrieval behavior to determine the target wording. Policy refinement then evaluates generated query sets by the observed item's rank in their fused recommendation list. Log-rank feedback distinguishes outcomes beyond the recommendation cutoff, while a KL penalty constrains policy change relative to the supervised reference. The stages have distinct roles: verification identifies expressions to imitate, and policy refinement improves the combined ranking produced by newly generated queries. Only the query generator is trained; the retriever and item index remain fixed, and no query annotations or learned reward model are required. Across three public datasets, R2QRec achieves state-of-the-art overall recommendation performance among the evaluated methods. Extensive experiments demonstrate the effectiveness of the proposed design and its generalization across generators and domains.

cs.IR↗

arXiv2026

Imitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents

An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy. We formulate passive imitation (PI) as an architectural loop that localizes a violated contract, extracts a local goal, proposes an effect-matched skill, tests a small patch, and retains evidence after full-task verification. We instantiate this loop as a deterministic symbolic controller and analyze its finite repair-query complexity under explicit identifiability and noninterference assumptions. Across ten simulated tool worlds, PI solves all 600 cold held-out composition tasks with three allowed small trials, compared with 6.17% for a whole-trajectory control, while an equally expressive compositional repair control matches PI. On an unseen tool revision, PI achieves 70.0% success versus 24.0% without small trials and 79.0% with self-trial enumeration; an exploratory 24-task adaptation stream subsequently raises first-submission success to 100%, supporting a limited correction-and-retention mechanism rather than a unique incentive advantage or general intelligence. The CPU-only implementation, integrity checks, and reproducible results are available at https://github.com/FriendOfYishan/PI.

cs.AI↗

arXiv2026

CAST: Real-Time Motion Capture for Any Skeleton Topology

This paper studies the problem of recovering motion from monocular video, even when the target skeleton topology differs from the subject observed in the video. Although previous methods have made efforts to resolve this problem, they remain vulnerable to joint-rotation errors that are coupled across the skeleton and can propagate along its kinematic hierarchy. To mitigate these errors, we present CAST, a topology-aware motion capture framework that combines learned local rotations with geometric correction guided by predicted global bone directions. Our observability analysis characterizes which rotational components can be constrained by outgoing bone directions. Guided by this analysis, GRACE uses reliability-gated alignment to correct composed orientations in parent-to-child order, leaving unconstrained components to the learned rotation predictor. The motion predictor and correction module are trained jointly with motion-derived supervision, using a frozen image encoder. Experiments under the TopoCap evaluation protocol show that the proposed framework improves motion recovery across different target topologies, including unseen structures. Reference-based cross-skeleton evaluation on a curated Mixamo benchmark and a user preference study further assess transfer to different target structures. A causal CAST-B variant achieves over 51 FPS on a single NVIDIA A100 GPU, with timing covering image encoding and motion prediction. Code repository: https://github.com/fankewen/CAST.

cs.CV↗

arXiv2026

Bounds on the minimum orbital period of four-dimensional black holes: From singular to non-singular spacetimes

It was conjectured that the lower bound $T_{\min}\geq 4πM $ may be a universal property of four-dimensional black holes, where $M$ is the black hole mass and $T_{\min}$ is the minimum orbital period around black holes. Recently, we established an upper bound $T_{\min}\le 6\sqrt{3}πM$ for Schwarzschild, Reissner--Nordström and Kerr--Newman black holes [23]. In this work we incorporate that analysis, which is not intended for separate publication, into a unified treatment and extend it to the non-singular Hayward and Bardeen black holes, demonstrating that the combined bounds $4πM\le T_{\min}\le 6\sqrt{3}πM$ hold for all five types of four-dimensional black holes investigated here. For all types of studied black holes, the upper bound is saturated by the standard Schwarzschild black hole and the lower bound by the maximally rotating Kerr black hole, suggesting that these bounds $4πM \leq T_{\min} \leq 6\sqrt{3}πM$ may be a universal property of four-dimensional black holes with horizons.

gr-qc↗

arXiv2026

CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling

Long-form instructional videos require automatic chaptering to support browsing, navigation, and knowledge access. Recent long-context language models can perform chaptering from textualized video inputs, but they remain costly and brittle for content-dense lecture videos with long transcripts, smooth topic transitions, and detailed chapter outputs. A scalable segment-then-caption paradigm reduces this cost, but introduces two new challenges: boundary error propagation and fragmented cross-chapter context. We propose \textbf{CausalChapter}, an intervention-inspired framework for long-video chaptering that estimates prediction-level influence through lightweight masking and removal interventions. For boundary localization, our Local Dependency Shift module detects drops in predictive dependency between adjacent temporal windows; for chapter description generation, our Cross-Segment Support Selection module reranks historical contexts according to their support for the current prediction. Experiments on long-video chaptering benchmarks show that CausalChapter improves boundary localization, chapter description quality, and cross-chapter coherence.

cs.CV↗

arXiv2026

WiP: Characterizing and Defending Against Mobile-Agent-Driven MFA Automation

Mobile agents automate smartphone tasks by interpreting interfaces, interacting with apps, and coordinating cross-app workflows. This capability challenges the human-mediated separation assumed by passcode-based MFA, creating factor collapse: valid authentication factors are combined within one autonomous environment. Our modular pipeline com- pletes all 10 authorized MFA workflows, compared with 3/10 and 6/10 for two single-agent baselines. We also de- velop a motion-based Android risk signal that distinguishes human- from agent-driven logins with 98.4% table-top and 92.6% hand-held accuracy across 116 pilot sessions. These results demonstrate factor collapse and motivate physical- interaction sensing as complementary evidence of user pres- ence.

cs.NI↗

arXiv2026

DTRNet: Dual Text-Radical Decoding for Handwritten Chinese Text Recognition with Faked Character Detection

In K-12 educational scenarios, handwritten Chinese text recognition should not only transcribe student writing, but also detect faked characters. However, existing recognition models are usually confined to a predefined set of normal characters and therefore cannot explicitly identify faked characters. Existing detection methods exhibit complementary limitations: character-level methods provide interpretable structural evidence but suffer from low efficiency, whereas line-level methods are efficient but rely heavily on confidence scores, making them prone to missed detections and lacking explicit structural evidence. Thus, the key challenge is to preserve character-structural evidence independent of contextual inference while maintaining line-level efficiency. To this end, we propose DTRNet, a dual Text-Radical decoding framework for line-level faked character detection. DTRNet decouples context-aware text recognition from character-wise structural verification, where the text branch performs line-level transcription and the radical branch predicts legal Ideographic Description Sequences (IDS) for lexicon-based faked character judgment. We further introduce IDS-Guided Confidence Adjustment (IGCA) to refine text predictions using structural evidence during inference. Experimental results demonstrate that DTRNet effectively detects faked characters while maintaining strong recognition performance and providing interpretable radical-level evidence. Code, checkpoints, and the processed dataset are publicly available at https://github.com/BNU-ERC-ITEA/DTRNet.

cs.CV↗

arXiv2026

Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing

Geometry Problem Solving have increasingly adopt the neuro-symbolic paradigm, combining neural intuition with symbolic rigor. However, current frameworks suffer from severe bottlenecks in two core stages: autoformalization, which treats multimodal translation as a static task decoupled from downstream solver compatibility, and theorem prediction, where solvers frequently hit a deductive impasse due to fixed rule libraries. To address these, we propose SD-GPS, a solver-driven framework that treats the symbolic solver as an execution oracle throughout both formalization and deduction. First, Solver-Driven Autoformalization unifies supervised formal-language adaptation and solvability-guided reinforcement learning into a single module built on QwenVL3-2B, making executability the central training signal. Second, Verified Theorem Proposing introduces an impasse-aware agent that proposes local auxiliary lemmas from current proof states, ensuring soundness by filtering all proposals through symbolic verification. Empirical evaluations on Geometry3K and PGPS9K demonstrate that SD-GPS consistently outperforms existing MLLM, neural, and neuro-symbolic methods across standard completion, multiple-choice, and cross-modal reference regimes, proving that closing the loop between multimodal perception and symbolic execution significantly improves geometric reasoning, offering profound insights into how neural agents can be grounded by formal systems to achieve verifiable problem-solving capabilities.

cs.AI↗

arXiv2026

The distance from functions in BMO to BLO

Let BMO and BLO denote the spaces of all locally integrable real-valued functions on $\mathbb{R}^n$ with bounded mean oscillation and bounded lower oscillation, respectively. It is well known that $$L^\infty(\mathbb{R}^n)\subsetneqq {\rm BLO}\subsetneqq {\rm BMO}.$$ In 1978, Garnett and Jones gave distance formulas of $f\in {\rm BMO}$ to $L^\infty(\mathbb{R}^n)$ and recently, Angrisani studied the distance of $f\in {\rm BLO}$ to $L^\infty(\mathbb{R}^n)$. In this paper, we characterize the distance from any given function $f \in {\rm BMO}$ to BLO via the Muckenhoupt weight class $A_p$ as follows \begin{center} dist\,($f$,\ BLO)\,$\sim\inf\left\{ξ\in(0,\infty):\ e^{-\frac fξ}\in A_p\ \mathrm{for\ some\ }p\in(1,\infty)\right\}$. \end{center} Two equivalent representations of this distance are also established in terms of exponential form and the infimum of the constant in a variant of John--Nirenberg inequality, respectively.

math.CA↗

arXiv2026

GeoLoom: High-quality Geometric Diagram Generation from Textual Input

High-quality geometric diagram generation presents both a challenge and an opportunity: it demands strict spatial accuracy while offering well-defined constraints to guide generation. Inspired by recent advances in geometry problem solving that employ formal languages and symbolic solvers for enhanced correctness and interpretability, we propose GeoLoom, a novel framework for text-to-diagram generation in geometric domains. GeoLoom comprises two core components: an autoformalization module that translates natural language into a specifically designed generation-oriented formal language GeoLingua, and a coordinate solver that maps formal constraints to precise coordinates using the efficient Monte Carlo optimization. To support this framework, we introduce GeoNF, a dataset aligning natural language geometric descriptions with formal GeoLingua descriptions. We further propose a constraint-based evaluation metric that quantifies structural deviation, offering mathematically grounded supervision for iterative refinement. Empirical results demonstrate that GeoLoom significantly outperforms state-of-the-art baselines in structural fidelity, providing a principled foundation for interpretable and scalable diagram generation.

cs.CV↗

arXiv2026

Non-Parametric Structural Priors for Geometry Theorem Prediction

Multi-step theorem prediction is a central challenge in geometry problem solving. Existing neural-symbolic approaches rely heavily on supervised parametric models, which exhibit limited generalization to evolving theorem libraries. In this work, we explore training-free theorem prediction through the lens of in-context learning (ICL). We identify a critical scalability bottleneck, termed Structural Drift: as reasoning depth increases, the performance of vanilla ICL degrades sharply, often collapsing to near zero. We attribute this failure to the LLM's inability to recover latent topological dependencies, leading to unstructured exploration. To address this issue, we propose Theorem Precedence Graphs, which encode temporal dependencies from historical solution traces as directed graphs, and impose explicit topological constraints that effectively prune the search space during inference. Coupled with retrieval-augmented graph construction and a stepwise symbolic executor, our approach enables LLMs to act as structured planners without any gradient-based optimization. Experiments on the FormalGeo7k benchmark show that our method achieves 89.29% accuracy, substantially outperforming ICL baselines and matching state-of-the-art supervised models. These results indicate that explicit structural priors offer a promising direction for scaling LLM-based symbolic reasoning.

cs.AI↗

arXiv2026

How Much Orthogonalization Does Muon Need?

Muon optimizers improve neural-network training by replacing ill-conditioned momentum updates with approximately semi-orthogonal updates. This motivates a practical question: how much orthogonalization does Muon actually require? We study this question using a relaxed cubic Newton--Schulz schedule derived directly for Muon's low precision singular value band. The resulting five-step cubic construction uses ten dominant matrix multiplications, compared with fifteen for five quintic Newton--Schulz iterations. The cubic schedule is not intended as a more accurate polar solver; instead, it is a principled low-cost variant that lets us probe the relation between polar accuracy, spectral shaping, and training quality. Across synthetic diagnostics, NanoGPT ablations, and training experiments on hybrid MoE/Mamba models, we find that training quality is not governed monotonically by polar-decomposition accuracy: truncated Polar Express, Muon-Jordan, cubic Newton--Schulz, and an explicit FP32 SVD polar factor can reach nearly indistinguishable final loss on GPT-2 Small, and cubic5 matches the Muon-Jordan quintic update within about $10^{-3}$ validation loss on hybrid MoE/Mamba models with one billion to four billion parameters. These results support cubic5 as a practical low-cost Muon orthogonalization variant, with empirical evidence of training-quality parity in the settings tested.

cs.LG↗

arXiv2026

Breaking Spatial Uniformity: Prior-Guided Mamba with Radial Serialization for Lens Flare Removal

Lens flares, caused by complex optical aberrations, severely degrade image quality especially in nighttime photography. Although recent restoration methods have made remarkable progress, most still rely on spatially uniform processing. They are failing to handle the region-dependent restoration demands of flare scenes, where saturated light sources should be preserved, flare artifacts removed, and background details recovered. To address this challenge, we propose DeflareMambav2, a prior-guided Mamba framework for lens flare removal. Specifically, we introduce a Flare Prior Network (FPN) to estimate flare priors and guide adaptive restoration. Besides, a novel radial serialization strategy breaks spatially homogeneous processing by performing flare-aware targeted sampling, and better supports long-range modeling in State Space Models (SSMs). Based on these priors, the backbone adopts a dual-level adaptive scheme. It explicitly preserves light-source regions to avoid over-processing, and applies curriculum-based restoration to the remaining contaminated areas while calibrating restoration intensity at the pixel level. Extensive experiments demonstrate that DeflareMambav2 achieves state-of-the-art performance with reduced parameter burden. Code is available at https://github.com/BNU-ERC-ITEA/DeflareMambav2.

cs.CV↗

arXiv2026

SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving

Large Language Models (LLMs) have achieved remarkable performance across a wide range of mathematical benchmarks. However, concerns remain as to whether these successes reflect genuine reasoning or superficial pattern recognition. Existing evaluation methods, which typically focus either on the final answer or on the intermediate reasoning steps, reduce mathematical reasoning to a shallow input-output mapping, overlooking its inherently multi-stage and multi-dimensional cognitive nature. Inspired by Polya's problem-solving theory, we propose SMART, a benchmark that decomposes mathematical problem-solving into four cognitive dimensions: Semantic Understanding, Mathematical Reasoning, Arithmetic Computation, and Reflection & Refinement, and introduces dimension-specific tasks to measure the corresponding cognitive processes of LLMs. We apply SMART to 22 state-of-the-art open- and closed-source LLMs and uncover substantial discrepancies in their capabilities across dimensions. Our findings reveal genuine weaknesses in current models and motivate a new metric, the All-Pass Score, designed to better capture true problem-solving capability.

cs.AI↗

arXiv2026

Accelerating Density Fitting with Adaptive-precision and 8-bit Integer on AI Accelerators

The emergence of artificial intelligence (AI) accelerators like NVIDIA Tensor Cores offers new opportunities to speed up tensor-heavy scientific computations. However, applying them to quantum chemistry is challenging due to strict accuracy demands and irregular data patterns. We propose an adaptive precision algorithm to accelerate the density fitting (DF) method with Gaussian basis sets on AI accelerators using 8-bit integer (INT8) arithmetics. Implemented in the GPU-accelerated PySCF package, the algorithm is tested on more than twenty molecular systems with different NVIDIA GPUs. Compared to the standard FP64 code, our algorithm is up to 204\% faster on a RTX 4090 gaming GPU and up to 364\% faster on a RTX 6000 Ada workstation GPU without compromising the converged energy. This work demonstrates a practical approach to use AI hardware for reliable quantum chemistry simulations.

physics.chem-ph↗

arXiv2026

VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMs

Large Multimodal Models have achieved remarkable progress in integrating vision and language, enabling strong performance across perception, reasoning, and domain-specific tasks. However, their capacity to reason over multiple, visually similar inputs remains insufficiently explored. Such fine-grained comparative reasoning is central to real-world tasks, especially in mathematics and education, where learners must often distinguish between nearly identical diagrams to identify correct solutions. To address this gap, we present VisioMath, a curated benchmark of 1,800 high-quality K-12 mathematics problems in which all candidate answers are diagrams with subtle visual similarities. A comprehensive evaluation of state-of-the-art LMMs, covering both leading closed-source systems and widely adopted open-source models, reveals a consistent decline in accuracy as inter-image similarity increases. Analysis indicates that the dominant failure mode stems from image-text misalignment: rather than grounding reasoning in textual cues, models often resort to shallow positional heuristics, resulting in systematic errors. We further explore three alignment-oriented strategies, spanning training-free approaches and finetuning, and achieve substantial accuracy gains. We hope that VisioMath will serve as a rigorous benchmark and catalyst for developing LMMs toward deeper diagram understanding, precise comparative reasoning, and grounded multi-image-text integration.

cs.AI↗

arXiv2026

Preconditioned Truncated Single-Sample Estimators for Scalable Stochastic Optimization

Many large-scale stochastic optimization algorithms involve repeated solutions of linear systems or evaluations of log-determinants. In these regimes, computing exact solutions is often unnecessary; it is more computationally efficient to construct unbiased stochastic estimators with controlled variance. However, classical iterative solvers incur truncation bias, whereas unbiased Krylov-based estimators typically exhibit high variance and numerical instability. To mitigate these issues, we introduce the Preconditioned Truncated Single-Sample (PTSS) estimators--a family of stochastic Krylov methods that integrate preconditioning with truncated Lanczos iterations. PTSS yields low-variance, stable estimators for linear system solutions, log-determinants, and their derivatives. We establish theoretical results on their mean, variance, and concentration properties, explicitly quantifying the variance reduction induced by preconditioning. Numerical experiments confirm that PTSS achieves superior stability and variance control compared with existing unbiased and biased alternatives, providing an efficient framework for stochastic optimization.

math.NA↗

arXiv2026

Geo-Code: A Code Framework for Reverse Code Generation from Geometric Images Based on Two-Stage Multi-Agent Evolution

Program code serves as a bridge linking vision and logic, providing a feasible supervisory approach for enhancing the multimodal reasoning capability of large models through geometric operations such as auxiliary line construction and perspective transformation. Nevertheless, current inverse graphics methods face tremendous challenges in accurately reconstructing complex geometric details, which often results in the loss of key geometric constraints or structural distortion. To address this bottleneck, we propose Geo-coder -- the first inverse programming framework for geometric images based on a multi-agent system. Our method innovatively decouples the process into geometric modeling via pixel-wise anchoring and metric-driven code evolution: Stage 1 leverages the complementary advantages of visual operators and large models to achieve precise capture of pixel coordinates and visual attributes; Stage 2 introduces a synthesis-rendering-validation closed loop, where bidirectional visual feedback drives the self-correction of code. Extensive experiments demonstrate that Geo-coder achieves a substantial lead in both geometric reconstruction accuracy and visual consistency. Notably, by effectively preserving the core geometric semantics, the images reconstructed with our method exhibit equivalent performance to the original ones in multimodal reasoning tasks, which fully validates the robustness of the framework. Finally, to further reduce research costs, we have open-sourced the Geo-coder dataset constructed on the GeoCode framework, which contains more than 1,500 samples. On this basis, we have also open-sourced the GeocodeLM model, laying a solid data and model foundation for subsequent research in this field.

cs.AI↗