Papers
Research papers from arXiv and related sources
MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning
Large Language Models (LLMs) often fail to generate correct code on the first attempt, which requires using generated unit tests as verifiers to validate the solutions. Despite the success of recen...
Sicheng Zhu, Jiajun Wang, Jiawei Ai, Xin Li
Quasar: Quantized Self-Speculative Acceleration for Rapid Inference via Memory-Efficient Verification
Speculative Decoding (SD) has emerged as a premier technique for accelerating Large Language Model (LLM) inference by decoupling token generation into rapid drafting and parallel verification. Whil...
Guang Huang, Zeyi Wen
Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis
Atmospheric turbulence significantly degrades long-range imaging by introducing geometric warping and exposure-time-dependent blur, which adversely affects both visual quality and the performance o...
Junwei Zeng, Dong Liang, Sheng-Jun Huang, Kun Zhan, Songcan Chen
Destruction of wall-bounded vortices using synthetic jet actuators
We experimentally explore the effectiveness of a rectangular orifice synthetic jet actuator for wall-bounded vortex destruction. Vortex flows near a boundary often present unforeseen or undesired f...
Frank A. Tricouros, Cameron Hoober, John C. Vaccaro, Tyler Van Buren
Invariant-Stratified Propagation for Expressive Graph Neural Networks
Graph Neural Networks (GNNs) face fundamental limitations in expressivity and capturing structural heterogeneity. Standard message-passing architectures are constrained by the 1-dimensional Weisfei...
Asela Hevapathige, Ahad N. Zehmakan, Asiri Wijesinghe, Saman Halgamuge
UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images
Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, task-specific feedforward models. We introduce U...
Junhwa Hur, Charles Herrmann, Songyou Peng, Philipp Henzler, Zeyu Ma, Todd Zickler, Deqing Sun
Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations
Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with known ground-truth factors. These metrics are assumed to r...
Shruti Joshi, Théo Saulus, Wieland Brendel, Philippe Brouillard, Dhanya Sridhar, Patrik Reizinger
FaultXformer: A Transformer-Encoder Based Fault Classification and Location Identification model in PMU-Integrated Active Electrical Distribution System
Accurate fault detection and localization in electrical distribution systems is crucial, especially with the increasing integration of distributed energy resources (DERs), which inject greater vari...
Kriti Thakur, Alivelu Manga Parimi, Mayukha Pal
Resolving the Metastable Si-XIII Structure through Convergent Theory and Experiment
Silicon is the undisputed cornerstone of modern technology, with applications ranging from micro- and opto-electronics to quantum technologies. Recently, the exploration of its allotropes has emerg...
Fabrizio Rovaris, Corrado Bongiorno, Anna Marzegalli, Mouad Bikerouin, Davide Spirito, Gerald J. ...
Data-Driven Linearization based Arc Fault Prediction in Medium Voltage Electrical Distribution System
High-impedance arc faults (HIAFs) in medium-voltage electrical distribution systems are difficult to detect due to their low fault current levels and nonlinear transient behavior. Traditional detec...
Mihir Sinha, Kriti Thakur, Prasanta K. Panigrahi, Alivelu Manga Parimi, Mayukha Pal
Weighted Unequal Error Protection over a Rayleigh Fading Channel
We study a variant of unequal error protection in channel coding, where the message bit string is divided into a finite number of blocks and the maximization objective is a weighted sum of per-bloc...
Adeel Mahmood
Comparing Classical and Quantum Variational Classifiers on the XOR Problem
Quantum machine learning applies principles such as superposition and entanglement to data processing and optimization. Variational quantum models operate on qubits in high-dimensional Hilbert spac...
Miras Seilkhan, Adilbek Taizhanov
Vacancy-induced local moments in quantum paramagnetic phases: An SU($N$) designer Hamiltonian study
We explore the effects of non-magnetic impurities (vacancy disorder) on the quantum paramagnetic phases stabilized by SU($N$) designer Hamiltonians on bipartite lattices. Using the results of our q...
Md Zahid Ansari, Souvik Kundu, Kedar Damle
Endpoint Estimates for Bergman Commutators and New Characterizations of the Bloch Space and $H^\infty$
We prove an $\LlogL $-type distributional inequality for the commutator of the Bergman projection with a conjugate Bloch symbol function on the unit ball. Such an inequality can be seen as a Bergma...
Adam B. Christopherson, Zhenghui Huo, Nathan A. Wagner, Yunus E. Zeytuncu
Hypothesis Testing over Observable Regimes in Singular Models
Hypothesis testing in singular statistical models is often regarded as inherently problematic due to non-identifiability and degeneracy of the Fisher information. We show that the fundamental obstr...
Sean Plummer
Robust Skills, Brittle Grounding: Diagnosing Restricted Generalization in Vision-Language Action Policies via Multi-Object Picking
Vision-language action (VLA) policies often report strong manipulation benchmark performance with relatively few demonstrations, but it remains unclear whether this reflects robust language-to-obje...
David Emukpere, Romain Deffayet, Jean-Michel Renders
Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification
Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic impressions unsupported by their own percept...
Vikash Singh, Debargha Ganguly, Haotian Yu, Chengwei Zhou, Prerna Singh, Brandon Lee, Vipin Chaud...
Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the complex reasoning capabilities of Large Reasoning Models. However, standard outcome-based ...
Yanwei Ren, Haotian Zhang, Likang Xiao, Xikai Zhang, Jiaxing Huang, Jiayan Qiu, Baosheng Yu, Quan...
Context-Aware Functional Test Generation via Business Logic Extraction and Adaptation
Functional testing is essential for verifying that the business logic of mobile applications aligns with user requirements, serving as the primary methodology for quality assurance in software deve...
Yakun Zhang, Zihan Wang, Xinzhi Peng, Zihao Xie, Xiaodong Wang, Xutao Li, Dan Hao, Lu Zhang, Yunm...
Ecological memory of hydrodynamic cues shapes growth and migration of motile microorganisms
Microorganisms live in inherently dynamic environments where fluctuations in biotic and abiotic factors shape their behaviour, physiology, and fitness. The concept of ecological memory: the lasting...
Narges Kakavand, Anupam Sengupta