arXiv subjects

Yuheng Yang

Publications and source records attributed to Yuheng Yang.

11 recordsLinked to original sources

arXiv2026

Configurational-space separation and structure selection in three hard squares

Self-assembly of hard particles with diverse shapes gives rise to a rich variety of structures through excluded-volume constraints alone. Here we show that even a minimal system of three hard squares confined in a two-dimensional periodic box exhibits nontrivial configurational behavior relevant to structure selection. As the packing fraction increases, radial distribution functions obtained from Markov-chain Monte Carlo and uniform non-overlapping insertion sampling agree at low densities, deviate markedly over an intermediate range, and converge again at higher densities. Pressure measurements provide strong numerical evidence that the discrepancy originates from the separation of the allowed configurational space into two disconnected regions above a characteristic density. We identify the separation density as $\phi_{\rm sep}=3/5$, construct explicit overlap-free transition pathways connecting the two regions immediately below it, and quantify their relative configurational-space volumes. At higher packing fractions, an approximately L-shaped arrangement of the particle centers becomes strongly favored over a staggered one, revealing a structural motif characteristic of tetratic and square-lattice ordering in larger hard-square systems. These results show that excluded-volume geometry can govern both configurational connectivity and local structure selection even in a three-particle system, revealing how signatures of many-particle self-assembly can already emerge in the few-particle limit.

cond-mat.soft↗

arXiv2026

Efficient Hardware Information-Flow Tracking for Pre-Silicon Security Testing

Register-Transfer Level (RTL) simulation is widely used to test hardware before it is fabricated. To allow testing for security related information flow properties, such as confidentiality and integrity, taint logic can be automatically added to the design to track how information flows through it. However, taint logic instrumented by the state-of-the-art, such as CellIFT, makes simulation-based testing prohibitively expensive: On our evaluation of Mega-BOOM (136K cells), it increases the instrumented design to 5.81x the original cell count and causes a 143.72x simulation slowdown. The taint logic could be simplified to improve simulation speed, but it will inevitably trade off its precision. This lightweight, imprecise taint logic will introduce false positives and may eventually result in even more overhead to check these false positives. This paper explores the research question of where precision is actually needed in the design to overcome the overhead of false positives. It presents CEGAR-T, a framework that automatically synthesizes taint logic that minimizes the taint-logic instrumentation overhead while guaranteeing no false positives (relative to the precise CellIFT baseline). We have implemented CEGAR-T and evaluated it on the safe instruction set problem for timing side-channel security across open-source RISC-V cores. Over all evaluated cores, CEGAR-T reduces both instrumentation and simulation overhead, in geometric-mean, from 5.64x to 1.42x and from 34.65x to 1.79x, respectively, without compromising the precision benefit of the CellIFT baseline.

cs.CR↗

arXiv2026

Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction

Large Language Models (LLMs) can be seen as compressed knowledge bases, but it remains unclear what knowledge they truly contain and how far their knowledge boundary extends. Existing benchmarks are mostly static and provide limited support for systematic knowledge probing. In this paper, we propose an interactive agentic framework to systematically extract and quantify the knowledge of LLMs. Our method includes four adaptive exploration policies to probe knowledge at different granularity. To ensure the quality of extracted knowledge, we introduce a three-stage knowledge processing pipeline that combines vector-based filtering to remove strict duplicates, LLM-based adjudication to resolve ambiguous semantic overlap, and domain relevance auditing to retain valid knowledge units. Through extensive experiments, we find that Recursive Taxonomy is the most effective exploration strategy. We also observe a clear knowledge scaling law, where larger models consistently recover more knowledge. In addition, we identify a Pass@1 versus Pass@k trade-off: domain-specialized models achieve higher initial accuracy but experience rapid degradation, while general-purpose models maintain stable performance over extended extraction. Finally, our results show that differences in training data composition lead to distinct and measurable knowledge profiles across model families, reflecting how pretraining shapes each model's parametric knowledge.

cs.LG↗

arXiv2026

Hierarchical Orthogonal Residual Spread for Precise Massive Editing in Large Language Models

Large language models (LLMs) exhibit exceptional performance across various domains, yet they face critical safety concerns. Model editing has emerged as an effective approach to mitigate these issues. Existing model editing methods often focus on optimizing an information matrix that blends new and old knowledge. While effective, these approaches can be computationally expensive and may cause conflicts. In contrast, we shift our attention to Hierarchical Orthogonal Residual SprEad of the information matrix, which reduces noisy gradients and enables more stable edits from a different perspective. We demonstrate the effectiveness of our method HORSE through a clear theoretical comparison with several popular methods and extensive experiments conducted on two datasets across multiple LLMs. The results show that HORSE maintains precise massive editing across diverse scenarios. The code is available at https://github.com/XiaojieGu/HORSE

cs.CL↗

arXiv2025

Evolution without an Oracle: Driving Effective Evolution with LLM Judges

The integration of Large Language Models (LLMs) with Evolutionary Computation (EC) has unlocked new frontiers in scientific discovery but remains shackled by a fundamental constraint: the reliance on an Oracle--an objective, machine-computable fitness function. This paper breaks this barrier by asking: Can evolution thrive in a purely subjective landscape governed solely by LLM judges? We introduce MADE (Multi-Agent Decomposed Evolution), a framework that tames the inherent noise of subjective evaluation through "Problem Specification." By decomposing vague instructions into specific, verifiable sub-requirements, MADE transforms high-variance LLM feedback into stable, precise selection pressure. The results are transformative: across complex benchmarks like DevAI and InfoBench, MADE outperforms strong baselines by over 50% in software requirement satisfaction (39.9% to 61.9%) and achieves a 95% perfect pass rate on complex instruction following. This work validates a fundamental paradigm shift: moving from optimizing "computable metrics" to "describable qualities," thereby unlocking evolutionary optimization for the vast open-ended domains where no ground truth exists.

cs.SE↗

arXiv2025

Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations

The rapid progress of large language models (LLMs) has opened new opportunities for education. While learners can interact with academic papers through LLM-powered dialogue, limitations still exist: the lack of structured organization and the heavy reliance on text can impede systematic understanding and engagement with complex concepts. To address these challenges, we propose Auto-Slides, an LLM-driven system that converts research papers into pedagogically structured, multimodal slides (e.g., diagrams and tables). Drawing on cognitive science, it creates a presentation-oriented narrative and allows iterative refinement via an interactive editor to better match learners' knowledge level and goals. Auto-Slides further incorporates verification and knowledge retrieval mechanisms to ensure accuracy and contextual completeness. Through extensive user studies, Auto-Slides demonstrates strong learner acceptance, improved structural support for understanding, and expert-validated gains in narrative quality compared with conventional LLM-based reading. Our contributions lie in designing a multi-agent framework for transforming academic papers into pedagogically optimized slides and introducing interactive customization for personalized learning.

cs.HC↗

arXiv2024

Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion

Human skeleton-based action recognition has long been an indispensable aspect of artificial intelligence. Current state-of-the-art methods tend to consider only the dependencies between connected skeletal joints, limiting their ability to capture non-linear dependencies between physically distant joints. Moreover, most existing approaches distinguish action classes by estimating the probability density of motion representations, yet the high-dimensional nature of human motions invokes inherent difficulties in accomplishing such measurements. In this paper, we seek to tackle these challenges from two directions: (1) We propose a novel dependency refinement approach that explicitly models dependencies between any pair of joints, effectively transcending the limitations imposed by joint distance. (2) We further propose a framework that utilizes the Hilbert-Schmidt Independence Criterion to differentiate action classes without being affected by data dimensionality, and mathematically derive learning objectives guaranteeing precise recognition. Empirically, our approach sets the state-of-the-art performance on NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA datasets.

cs.CV↗

arXiv2024

RTL Verification for Secure Speculation Using Contract Shadow Logic

Modern out-of-order processors face speculative execution attacks. Despite various proposed software and hardware mitigations to prevent such attacks, new attacks keep arising from unknown vulnerabilities. Thus, a formal and rigorous evaluation of the ability of hardware designs to deal with speculative execution attacks is urgently desired. This paper proposes a formal verification technique called Contract Shadow Logic that can considerably improve RTL verification scalability while being applicable to different defense mechanisms. In this technique, we leverage computer architecture design insights to improve verification performance for checking security properties formulated as software-hardware contracts for secure speculation. Our verification scheme is accessible to computer architects and requires minimal formal-method expertise. We evaluate our technique on multiple RTL designs, including three out-of-order processors. The experimental results demonstrate that our technique exhibits a significant advantage in finding attacks on insecure designs and deriving complete proofs on secure designs, when compared to the baseline and two state-of-the-art verification schemes, LEAVE and UPEC.

cs.AR↗

arXiv2023

A geometry-originated universal relation for arbitrary convex hard particles

We have discovered that two significant quantities within hard particle systems: the probability of successfully inserting an additional particle at random and the scale distribution function, can be connected by a concise relation. We anticipate that this relation holds universal applicability for convex hard particles. Our investigations encompassed a range of particle shapes, including one-dimensional line segments, two-dimensional disks, equilateral and non-equilateral triangles, squares, rectangles, and three-dimensional spheres. Remarkably, we have observed a close alignment between the two sides of the relation in all cases we examined. Furthermore, we show that this relation can be derived from the fundamental thermodynamic relation that connects entropy, pressure, and chemical potential. Our study unveils a geometrically rooted relation that underpins essential thermodynamic relations, shedding light on the intricate interplay of geometry and thermodynamics in hard particle systems.

cond-mat.soft↗

arXiv2023

Seeing the Unheard: dynamics of thin liquid film in holographic ultrasonic field revealed by time-resolved Schlieren imaging

In this study, we introduce a unique approach that employs time-resolved Schlieren imaging to capture and visualize the dynamic changes of a thin liquid (mixture of water, soap and glycerin) film in ultrasonic wave field with high spatial and temporal resolution. By placing a soap film spanning a wire frame vertically in the path of light, we harnessed the vibrations induced by the ultrasonic waves, resulting in remarkable Schlieren imaging patterns. The investigation not only uncovers an unexpected branch flow phenomenon within the film, challenging existing assumptions, but also reveals a fascinating interplay between vortex flow and branch flow. The experiments have revealed a captivating spectrum of dynamic phenomena within the thin liquid films. The observation of small-scale capillary waves, large-scale standing waves, traveling waves, and the intricate fusion of capillary-gravity wave patterns underscores the rich complexity inherent in the interaction between the films and the holographic ultrasonic wave field. These diverse states of film dynamics provide a comprehensive understanding of the intricate interplay between various wave modes and fluid behavior, further enhancing comprehension of this fascinating phenomenon. The ability to visualize the pressure field opens up new avenues for optimizing acoustic levitation techniques, investigating particle behavior, and exploring potential applications in materials science and bioengineering.

physics.flu-dyn↗

arXiv2023

Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization

Action recognition has long been a fundamental and intriguing problem in artificial intelligence. The task is challenging due to the high dimensionality nature of an action, as well as the subtle motion details to be considered. Current state-of-the-art approaches typically learn from articulated motion sequences in the straightforward 3D Euclidean space. However, the vanilla Euclidean space is not efficient for modeling important motion characteristics such as the joint-wise angular acceleration, which reveals the driving force behind the motion. Moreover, current methods typically attend to each channel equally and lack theoretical constrains on extracting task-relevant features from the input. In this paper, we seek to tackle these challenges from three aspects: (1) We propose to incorporate an acceleration representation, explicitly modeling the higher-order variations in motion. (2) We introduce a novel Stream-GCN network equipped with multi-stream components and channel attention, where different representations (i.e., streams) supplement each other towards a more precise action recognition while attention capitalizes on those important channels. (3) We explore feature-level supervision for maximizing the extraction of task-relevant information and formulate this into a mutual information loss. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets, NTU RGB+D, NTU RGB+D 120, and NW-UCLA. Our code is anonymously released at https://github.com/ActionR-Group/Stream-GCN, hoping to inspire the community.

cs.CV↗