Searcharxiv⌕ Search

arXiv subjects

Shuo Zhang

Publications and source records attributed to Shuo Zhang.

At least 37 records · Page 2Linked to original sources
arXiv2026

A Natural Decomposition Method for Essential Boundary Conditions in Noninterpolatory Meshfree Spaces

This paper develops a natural decomposition method (NDM)for imposing essential boundary conditions in noninterpolatory meshfree Galerkin spaces without boundary parameter tuning or auxiliary constraint construction. In such spaces, algebraic coefficients generally do not coincide with boundary values; hence coefficient assignment or nodal boundary prescription is not equivalent to imposing the continuous trace required by the variational problem. NDM introduces boundary data before discretization through a natural transfer mechanism: a source subproblem accounts for the forcing term, a weighted curl correction transfers the remaining trace mismatch, and a scalar recovery step reconstructs the solution from the corrected weighted gradient. For topologically trivial single domains with connected boundary, the reconstructed solution is equivalent, at the continuous level, to the solution satisfying the prescribed essential boundary data. The discrete analysis separates the approximation defect of the recovery space from the upstream transfer error visible to that space. Numerical experiments on benchmark problems evaluate the proposed transfer mechanism and report the associated conditioning, computational cost, and boundary perturbation behavior.

math.NA↗
arXiv2026

SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes

Smart homes are evolving toward complex state-dependent living environments, requiring Large Language Models (LLMs) to reason over user intent, preferences, and multi-device interactions. However, existing smart-home benchmarks often focus on static instruction-to-API mapping or limited simulations, failing to evaluate whether LLMs can reason, interact, and act reliably in realistic household scenarios. To address these limitations, we introduce SMH-Bench, a comprehensive benchmark for evaluating LLMs in smart-home environments. Built upon HomeEnv, an executable and verifiable smart-home simulator, SMH-Bench contains 1,100 high-quality tasks spanning 7 categories and 22 fine-grained subcategories. It further stratifies tasks across simple, medium and complex homes, ranging from small apartments to dense multi-room environments with 135 devices. Experiments show that although frontier LLMs achieve strong performance on explicit control and query tasks, they still exhibit significant weaknesses in automation task scheduling, ambiguity handling and personalized reasoning, especially as home complexity increases. We hope SMH-Bench will facilitate the development of more reliable, context-aware, and practically deployable smart-home agents.

cs.AI↗
arXiv2026

Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition

Long-tailed recognition poses a significant challenge for deep learning. The two-stage decoupling paradigm, which separates representation learning from classifier retraining, offers a promising solution. During the classifier retraining stage, adaptive norm rescaling is a popular technique. It adjusts the per-class weight norms via parameter regularization, which inevitably introduces hyperparameters. However, many studies report that long-tailed recognition is sensitive to these hyperparameters, as their setup significantly impacts performance. In this paper, we first provide a class-conditional distribution perspective to support norm rescaling methods. Furthermore, we propose a simple but effective approach called Self-Adaptive Monotonic Normalization (SAMN). SAMN avoids the need for parameter regularization. It directly enforces monotonicity on per-class weight norms using the Pool Adjacent Violators Algorithm, making the method hyperparameter-friendly. SAMN is a universal strategy that integrates seamlessly with other methods for enhanced performance. Experiments on benchmark datasets demonstrate that our method significantly boosts long-tailed recognition performance, often achieving state-of-the-art results.

cs.CV↗
arXiv2026

HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation

Large language model agents are moving beyond text-only interaction toward physical-world control, with smart homes as a representative domain. Real domestic interaction requires understanding ambiguous intents, operating in dynamic environments, and performing multi-turn reasoning. However, existing methods struggle to generate high-quality training data for smart home agents. We propose HomeFlow, a verifiable data flywheel for this domain. HomeFlow uses HomeEnv as a unified simulation environment and HomeMaker to procedurally generate diverse home settings. Subsequently, Blueprint compiles open-ended user intents into executable state-based success conditions, while MCTS-Flow synthesizes diverse, verifiable multi-turn trajectories through environment-guided tree search. We then optimize the agents via supervised fine-tuning and step-wise RLVE, which facilitates iterative improvement through authentic physical feedback. We further construct SmartHome-Bench to evaluate the agent across various smart home tasks. On this benchmark, HomeFlow-RL-4B and HomeFlow-RL-8B achieve task success rates of 84.60% and 87.03%. It is worth noting that HomeFlow-RL-8B even surpasses the leading GPT-5.5 by 1.23 percentage points.

cs.AI↗
arXiv2026

Refined convergence structures of the rectangular Raviart-Thomas element

In this work, we fully explore three refined convergence structures of the lowest-order rectangular Raviart-Thomas element in solving the Laplace eigenvalue problem. Firstly, the scheme possesses a property of supercloseness between the discrete eigenfunctions and the interpolated ones, so that post-processing can be easily constructed to improve the accuracy at most by one order. The essentially skillful method is the integral expansion for interpolation terms. Secondly, based on the supercloseness property, we derive the error expansions for not only simple eigenvalues but also multiple eigenvalues, and provide a rigorous proof for them, based on which Richardson extrapolation can be performed. As a byproduct, we prove that all eigenvalues converge from above. Moreover, by utilizing the supercloseness property and Rayleigh quotient analysis, we give a rigorous proof for the convergence behavior for multiple eigenvalues on uniform meshes for the problem on the square domain. Thirdly, the equivalence between the lowest-order rectangular Raviart-Thomas element and the enriched rotated bilinear element is also indicated. At the last of this work, several numerical experiments are designed to demonstrate our theory.

math.NA↗
arXiv2026

Hierarchical Contrastive Learning for Multi-Domain Protein-Ligand Binding

Predicting protein-ligand binding affinity remains intractable for multi-domain proteins, where inter-domain dynamics govern molecular recognition. Existing geometric deep learning methods typically treat proteins as monolithic static graphs, suffering from rigid-body assumptions and aleatoric noise in flexible regions. To address this, we introduced HCLBind, a self-supervised framework that decouples geometric representation learning from affinity regression. HCLBind leverages a general-to-specific pre-training paradigm on the Q-BioLiP database to learn a robust physical grammar of binding. We propose a novel hierarchical decoy strategy: the model learns local physicochemical constraints through protein coordinate perturbation in single-domain proteins and global conformational geometry through inter-domain rotation in multi-domain complexes. Our hybrid architecture integrates a domain-gated graph attention network and cross-modal attention to explicitly prioritize domain interfaces. Furthermore, we employ LoRA on protein and ligand foundation models, ensuring efficient optimization while preserving evolutionary knowledge. Experiments on PDBBind demonstrate that HCLBind effectively learns discriminative interface features and provides robust uncertainty estimation, overcoming the limitations of standard supervised learning. The code is available at https://github.com/jiankliu/HCLBind.

cs.LG↗
arXiv2026

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents

As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, reusable, and executable skills from repositories and documents. Existing benchmarks primarily evaluate the efficacy of given skills or the ability of agents to solve downstream tasks from raw context, but they do not isolate skill generation itself as the object of study. We introduce SkillGenBench, a benchmark for evaluating skill generation pipelines under a unified and controlled protocol. In SkillGenBench, a generator receives raw corpora and produces standardized skill artifacts, which are then executed under fixed harnesses and assessed with unified evaluation procedures. The benchmark covers two generation regimes: task-conditioned generation, where a task-specific skill is synthesized after the task is revealed, and task-agnostic generation, where a reusable skill library must be distilled before downstream tasks are known. It also spans two complementary procedural sources: repository-grounded instances, where procedures are distributed across code, configuration, and scripts, and document-grounded instances, where procedures and constraints must be distilled from long-form text. We provide standardized task specifications, pinned environments, and evaluation protocols centered on deterministic execution-based checks, supplemented by auxiliary signals for diagnosis. Experiments across a range of skill-generation methods and backbones show substantial performance variation, highlight the difficulty of reusable skill distillation, and reveal distinct failure modes in skill generation from software repositories versus long-form documents. SkillGenBench establishes a reproducible testbed for studying skill generation as an independent research problem in agent systems.

cs.AI↗
arXiv2026

Res$^2$CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment

Few-shot Generalist Anomaly Detection requires models to generalize to novel categories without retraining, posing significant challenges in real-world scenarios with scarce samples and rapidly changing categories. Existing CLIP-based methods face two major challenges: coarse-grained unified text prompts struggle to adapt to fine-grained foreground-background differences, causing cross-granularity mismatch; and fine-tuning on auxiliary datasets disrupts CLIP's inherent open-world generalization due to domain shift, leading to cross-category generalization degradation. To address these, we propose to shift multimodal alignment entirely into a unified residual space, where residual representations naturally eliminate fine-grained normal feature differences across regions and class-specific biases, simultaneously resolving both problems. Based on this insight, Res$^2$CLIP, the first residual-to-residual alignment framework that symmetrically bridges visual and text modalities within CLIP's residual space, is designed. The framework is developed from a residual perspective into three branches: a text prompt-based branch, a visual prompt-based branch, and a novel residual-to-residual alignment branch. All learnable optimizations are constrained within the residual domain, and the residual alignment optimization objectives are designed to force the model to focus on relative anomaly deviations rather than optimizing class-specific features. Experiments on multiple datasets demonstrate the effectiveness of our architecture. The code is available at https://github.com/hito2448/Res2CLIP.

cs.CV↗
arXiv2026

FSD50K-Solo: Automated Curation of Single-Source Sound Events

High-quality training datasets are essential for the performance of neural networks. However, the audio domain still lacks a large-scale, strongly-labeled, and single-source sound event dataset. The FSD50K dataset, despite being relatively large and open, contains a considerable fraction of multi-source samples where background interference or overlapping events could limit the usefulness of the data. To address this challenge, we introduce a data curation framework designed for large-scale open audio corpora. Our approach leverages a generative diffusion model to synthesize clean single-class events to construct controlled noisy mixtures for supervision. We subsequently employ a pre-trained audio encoder coupled with a discriminative classifier to automatically identify and filter out multi-source samples. Experiments show that our framework achieves strong performance on a human expert-curated test set. Finally, we release FSD50K-Solo, a model-curated subset of FSD50K containing single-source audio samples identified by our method. Beyond FSD50K, our method establishes a scalable paradigm for curating open source audio corpora.

eess.AS↗
arXiv2026

Infrared Line Diagnostics Fail to Constrain Sgr A*'s UV Output

Sgr A*, the 4 x $10^6 M_{sun}$ supermassive black hole at the Galactic Center, exhibits frequent flaring with X-ray luminosities of $L_X \sim 10^{35}-10^{36}$ erg s$^{-1}$, while its ultraviolet (UV) emission remains unconstrained due to extreme extinction ($A_V \sim 30$ mag). We use JWST/MIRI time-resolved spectroscopy of the central 0.3" region to search for mid-infrared emission line variability driven by Sgr A* flares, comparing the results to CLOUDY photoionization models spanning flare luminosities of $L_{UV} = 10^{32}$-$10^{39}$ erg s$^{-1}$. We detect no continuum-correlated variability in any mid-infrared line, including [Fe II] (5.34 $\mu$m), [Ne II] (12.813 $\mu$m), [Fe II] (17.936 $\mu$m), and [S III] (18.713 $\mu$m) over lags of $\sim1$-8~hr. Despite expectations of a flare-driven response, we show that the lack of variability is consistent with the physical conditions in the spatially extended line-emitting gas, where light-crossing timescales of $\sim0.1$-$10$ days and recombination and cooling timescales much longer than the variability timescales suppress any observable response to individual flares. We further find that the modeled infrared spectra are dominated by continuum emission rather than isolated line emission. The brightest predicted lines are intrinsically weak (lower than 10$^{-5}$ mJy), and their detectability is further reduced by the large kinematic broadening expected at the CLOUDY-predicted emitting radii, reducing their contrast against the continuum. Extending the analysis to higher-ionization mid-infrared and near-infrared lines does not improve sensitivity. These results demonstrate that infrared emission lines trace a steady-state radiation field rather than individual flaring events, and therefore infrared line diagnostics cannot be used to constrain the instantaneous UV flux of Sgr A*.

astro-ph.HE↗
arXiv2026

StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models

While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints remains underexplored. We investigate this by specializing small LLMs on micro-datasets of foundational Stoic texts using preference optimization (ORPO, AlphaPO). Evaluated via a multi-model critic bank, our results show that just 300 high-fidelity examples can induce strong alignment with inward-facing Stoic virtues, closely approaching few-shot prompting while freeing the context window. Critically, however, all models, including few-shot baselines, exhibit a persistent failure on Stoicism's outward-facing cosmopolitan duties, pointing to a representational limitation of small models that micro-dataset adaptation alone cannot overcome.

cs.CL↗
arXiv2026

Localization phase diagram of the Hexagonal Lattice with irrational magnetic flux

We study the Hofstadter model on a hexagonal lattice with irrational magnetic flux in this work. The Hofstadter model of the square lattice with irrational flux has been solved mathematically by Avila and his collaborators in his Fields medal work. However, this theory is usually not applicable to lattices with internal degrees of freedom, such as spin or sublattice. In this work, we show that for the hexagonal lattice with only nearest neighbor hopping, the system can still be characterized by a two by two transfer matrix and solved exactly by the Avila global theory although this lattice has two sublattices. We obtained the exact localization phase diagram of the hexagonal lattice with irrational flux by this theory, which reveals three pure phases, i.e., the extended, localized and critical states but no mobility edge due to the chiral symmetry. We used the renormalization group (RG) theory to verify these results, which can determine part of the phase diagram. We then computed the fractal dimension of the remaining part numerically. The results from both the RG theory and numerical analysis confirmed the phase diagram we get from the Avila global theory. Our results can be tested in various hexagonal Moire lattices and artificial superlattices in recent experiments.

cond-mat.mes-hall↗
arXiv2026

Bridging Krylov Complexity and Universal Analog Quantum Simulator

Quantum simulation of complex many-body systems beyond classical computational capabilities provides a promising route toward understanding novel quantum phases and their transitions. In particular, analog quantum simulators with global control fields have attracted considerable attention due to their potential to simulate arbitrary Hamiltonians and perform quantum computing tasks. However, a clear, quantitative measure for the complexity of implementing specific quantum operations in such systems is still lacking. In this Letter, we address this challenge by introducing generalized Krylov complexity, a concept originating from operator growth dynamics, as a direct diagnosis for this synthesis complexity. We construct the block Krylov basis generated by a set of Hamiltonians, which naturally organizes the operator space achievable through the simulator's native interactions and their nested commutators. By analyzing representative systems including Rydberg atom arrays, we demonstrate that the generalized Krylov complexity of a target operation serves as a strong predictor of the minimum time required for its realization. Our results establish Krylov complexity as an intuitive and predictive tool for designing efficient control protocols in analog quantum simulators.

quant-ph↗
arXiv2026

Melding LLM and temporal logic for reliable human-swarm collaboration in complex scenarios

Robot swarms promise scalable assistance in complex and hazardous environments. Task planning lies at the core of human-swarm collaboration, translating the operator's intent into coordinated swarm actions and helping determine when validation or intervention is required during execution. In long-horizon missions under dynamic scenarios, however, reliable task planning becomes difficult to maintain: emerging events and changing conditions demand continual adaptation, and sustained operator oversight imposes substantial cognitive burden. Existing LLM-based planning tools can support plan generation, yet they remain susceptible to invalid task orderings and infeasible robot actions, resulting in frequent manual adjustment. Here we introduce a neuro-symbolic framework for long-horizon human-swarm collaboration that tightly melds verifiable task planning with context-grounded LLM reasoning. We formalize mission goals and operational rules as temporal logic formulas and admissible task orderings as task automata. Conditioned on these formal constraints and live perceptual context, LLMs generate executable subtask sequences that satisfy mission rules and remain grounded in the current scene. An uncertainty-aware scheduler then assigns subtasks across the heterogeneous swarm to maximize parallelisms while remaining resilient to disruptions. An event-triggered interaction protocol further limits operator involvement to sparse, high-level confirmation and guidance. Deployment on a heterogeneous robotic fleet yields similar results while remaining robust to hardware-specific actuation and communication uncertainties. Together, these results support a formal and scalable paradigm for reliable and low-overhead human-swarm collaboration in dynamic environments

cs.RO↗
arXiv2026

Private Private Information in Second-Price Auction

Classic results show that even an arbitrarily small correlation across bidders' information can enable full surplus extraction in auctions and related mechanism design settings. Motivated by this fragility, we study the information independence in a second-price auction when the seller commits to a private private information structure, meaning bidders' signals are independent ex ante, while bidders share a symmetric and arbitrarily correlated prior distribution over their valuations. We first show that the seller optimal efficient outcome with full surplus extraction can always be implemented by a private private information structure that admits a Bayes Nash equilibrium. However, this equilibrium may not be stable. We then further construct a private private information structure that achieves revenue arbitrarily close to maximum welfare while admitting a strict equilibrium. At the same time, we establish an impossibility result: under private private information, in general, bidder surplus cannot achieve maximal welfare exactly, and we characterize necessary and sufficient conditions on the prior distribution under which bidder surplus can be made arbitrarily close to maximal welfare. We finally explore which other efficient outcomes are achievable under private private information.

econ.TH↗
arXiv2026

Low Light Image Enhancement Challenge at NTIRE 2026

This paper presents a comprehensive review of the NTIRE 2026 Low Light Image Enhancement Challenge, highlighting the proposed solutions and final results. The objective of this challenge is to identify effective networks capable of producing clearer and visually compelling images in diverse and challenging conditions by learning representative visual cues with the purpose of restoring information loss due to low-contrast and noisy images. A total of 195 participants registered for the first track and 153 for the second track of the competition, and 22 teams ultimately submitted valid entries. This paper thoroughly evaluates the state-of-the-art advances in (joint denoising and) low-light image enhancement, showcasing the significant progress in the field, while leveraging samples of our novel dataset.

cs.CV↗
arXiv2026

Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure

AI coding agents have become central to developer workflows, yet every existing solution locks its reasoning capabilities within a specific delivery form, such as a CLI, IDE plugin, or web application. This limitation creates systemic barriers when enterprises attempt to reuse these capabilities across heterogeneous engineering environments. To address this challenge, we present Sema Code, an open AI coding framework built on the principle of being embeddable, pluggable, and framework-first. Sema Code completely decouples the core agent engine from all client layers, publishing it as a standalone npm library that any runtime can drive programmatically. Built around this architecture, we designed eight key mechanisms: multi-tenant engine isolation, FIFO input queuing with safe session reconstruction, adaptive context compression, multi-agent collaborative scheduling, intelligent Todo-based process management, four-layer asynchronous permission control, three-tier ecosystem integration spanning MCP, Skills, and Plugins, and a background task framework with separated execution and observation privileges. These mechanisms collectively address the engineering challenges of transforming a complex agent engine into a shared, programmable core. Demonstrating its architectural versatility, the same Sema Core engine simultaneously powers a VSCode extension and a multi-channel messaging gateway, which we name SemaClaw, to unify agent interactions across platforms such as Telegram and Feishu. These represent two fundamentally different product forms sharing an identical reasoning kernel, differing only at the client layer.

cs.SE↗
arXiv2026

SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering

The rise of OpenClaw in early 2026 marks the moment when millions of users began deploying personal AI agents into their daily lives, delegating tasks ranging from travel planning to multi-step research. This scale of adoption signals that two parallel arcs of development have reached an inflection point. First is a paradigm shift in AI engineering, evolving from prompt and context engineering to harness engineering-designing the complete infrastructure necessary to transform unconstrained agents into controllable, auditable, and production-reliable systems. As model capabilities converge, this harness layer is becoming the primary site of architectural differentiation. Second is the evolution of human-agent interaction from discrete tasks toward a persistent, contextually aware collaborative relationship, which demands open, trustworthy and extensible harness infrastructure. We present SemaClaw, an open-source multi-agent application framework that addresses these shifts by taking a step towards general-purpose personal AI agents through harness engineering. Our primary contributions include a DAG-based two-phase hybrid agent team orchestration method, a PermissionBridge behavioral safety system, a three-tier context management architecture, and an agentic wiki skill for automated personal knowledge base construction.

cs.AI↗