arXiv subjects

Alex Huang

Publications and source records attributed to Alex Huang.

7 recordsLinked to original sources

arXiv2026

Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems

Multi-agent large language model (LLM) systems enable complex, long-horizon reasoning by composing specialized agents, but practical deployment remains hindered by inefficient routing, noisy feedback, and high interaction cost. We introduce REDEREF, a lightweight and training-free controller for multi-agent LLM collaboration that improves routing efficiency during recursive delegation. REDEREF integrates (i) belief-guided delegation via Thompson sampling to prioritize agents with historically positive marginal contributions, (ii) reflection-driven re-routing using a calibrated LLM or programmatic judge, (iii) evidence-based selection rather than output averaging, and (iv) memory-aware priors to reduce cold-start inefficiency. Across multi-agent split-knowledge tasks, we show that while recursive retry alone saturates task success, belief-guided routing reduces token usage by 28%, agent calls by 17%, and time-to-success by 19% compared to random recursive delegation, and adapts gracefully under agent or judge degradation. These results demonstrate that simple, interpretable probabilistic control can meaningfully improve the efficiency and robustness of multi-agent LLM systems without training or fine-tuning.

cs.CL↗

arXiv2026

Journal Impact Factor and Federal Reserve Monetary Policy: An Econometric Analysis Based on 1975-2026

The Journal Impact Factor (IF), as a core indicator of academic evaluation, has not been systematically studied in relation to its historical evolution and global macroeconomic environment. This paper employs a period-based regression analysis using long-term time series data from 1975-2026 to examine the statistical relationship between IF and Federal Reserve monetary policy (using real interest rate as a proxy variable). The study estimates three nested models using Ordinary Least Squares (OLS): (1) a baseline linear model, (2) a linear model controlling for time trends, and (3) a log-transformed model. Empirical results show that: (i) in the early period (1975-2000), there is no significant statistical relationship between IF and real interest rate ($p>0.1$); (ii) during the quantitative easing period (2001-2020), they exhibit a significant negative correlation ($\beta=-0.069$, $p<0.01$), meaning that for every 1 percentage point decrease in real interest rate, IF increases by approximately 6.9\%; (iii) the adjusted $R^2$ of the full-sample model reaches 0.893, indicating that real interest rate and time trends can explain 89.3\% of IF variation. This finding reveals the indirect impact of monetary policy on the academic publishing system through multiple channels such as research funding and journal pricing power, providing econometric evidence for understanding the phenomenon of "financialization of academic capital." This study not only enriches the literature on monetary policy transmission mechanisms but also provides a new perspective for valuation analysis of the academic publishing industry.

econ.EM↗

arXiv2026

THETA: Triangulated Hand-State Estimation for Teleoperation and Automation in Robotic Hand Control

The teleoperation of robotic hands is limited by the high costs of depth cameras and sensor gloves, commonly used to estimate hand relative joint positions (XYZ). We present a novel, cost-effective approach using three webcams for triangulation-based tracking to approximate relative joint angles (theta) of human fingers. We also introduce a modified DexHand, a low-cost robotic hand from TheRobotStudio, to demonstrate THETA's real-time application. Data collection involved 40 distinct hand gestures using three 640x480p webcams arranged at 120-degree intervals, generating over 48,000 RGB images. Joint angles were manually determined by measuring midpoints of the MCP, PIP, and DIP finger joints. Captured RGB frames were processed using a DeepLabV3 segmentation model with a ResNet-50 backbone for multi-scale hand segmentation. The segmented images were then HSV-filtered and fed into THETA's architecture, consisting of a MobileNetV2-based CNN classifier optimized for hierarchical spatial feature extraction and a 9-channel input tensor encoding multi-perspective hand representations. The classification model maps segmented hand views into discrete joint angles, achieving 97.18% accuracy, 98.72% recall, F1 Score of 0.9274, and a precision of 0.8906. In real-time inference, THETA captures simultaneous frames, segments hand regions, filters them, and compiles a 9-channel tensor for classification. Joint-angle predictions are relayed via serial to an Arduino, enabling the DexHand to replicate hand movements. Future research will increase dataset diversity, integrate wrist tracking, and apply computer vision techniques such as OpenAI-Vision. THETA potentially ensures cost-effective, user-friendly teleoperation for medical, linguistic, and manufacturing applications.

cs.RO↗

arXiv2021

Point Source Localization with a Planar Optical Phased Array Compressive Sensor

Compressive sensing has been used to demonstrate scene reconstruction and source localization in a wide variety of devices. To date, optical compressive sensors have not been able to achieve significant volume reduction relative to conventional optics of equivalent angular resolution. Here, we adapt silicon-photonic optical phased array technology to demonstrate, to our knowledge, the first application of compressive imaging in a photonic-integrated device. Our novel sensor consists of an $8\times 8$ grid of grating couplers with a spacing of $100~\mu$m. Path-matched waveguides route to a single multimode interferometer (MMI), which mixes and randomizes the signals into 64 outputs to be used for compressed sensing. Our device is fully passive, having no need for phase shifters, as measurement matrix calibration makes the measurements robust to phase errors. For testing, we use an Amplified Spontaneous Emission (ASE) source with a bandwidth of 40 nm, centered at 1545 nm. We demonstrate simultaneous multi-point (2 sources demonstrated in this work) brightness recovery and localization with better than 10 arcsecond precision in a sub-millimeter thick form-factor. We achieve a single source recovery rate higher than 99.9\% using 10 of the 64 outputs, and a 90\% recovery rate with only 6 outputs, 10 times fewer than the 64 needed for conventional imaging. This planar optical phased array compressive sensor is well-suited for imaging sparse scenes in applications constrained by form factor, volume, or high-cost detectors, with the potential to revolutionize endoscopy, beam locators, and LIDAR.

physics.app-ph↗

arXiv2018

On Visual Hallmarks of Robustness to Adversarial Malware

A central challenge of adversarial learning is to interpret the resulting hardened model. In this contribution, we ask how robust generalization can be visually discerned and whether a concise view of the interactions between a hardened decision map and input samples is possible. We first provide a means of visually comparing a hardened model's loss behavior with respect to the adversarial variants generated during training versus loss behavior with respect to adversarial variants generated from other sources. This allows us to confirm that the association of observed flatness of a loss landscape with generalization that is seen with naturally trained models extends to adversarially hardened models and robust generalization. To complement these means of interpreting model parameter robustness we also use self-organizing maps to provide a visual means of superimposing adversarial and natural variants on a model's decision space, thus allowing the model's global robustness to be comprehensively examined.

cs.LG↗

arXiv2018

Adversarial Deep Learning for Robust Detection of Binary Encoded Malware

Malware is constantly adapting in order to avoid detection. Model based malware detectors, such as SVM and neural networks, are vulnerable to so-called adversarial examples which are modest changes to detectable malware that allows the resulting malware to evade detection. Continuous-valued methods that are robust to adversarial examples of images have been developed using saddle-point optimization formulations. We are inspired by them to develop similar methods for the discrete, e.g. binary, domain which characterizes the features of malware. A specific extra challenge of malware is that the adversarial examples must be generated in a way that preserves their malicious functionality. We introduce methods capable of generating functionally preserved adversarial malware examples in the binary domain. Using the saddle-point formulation, we incorporate the adversarial examples into the training of models that are robust to them. We evaluate the effectiveness of the methods and others in the literature on a set of Portable Execution~(PE) files. Comparison prompts our introduction of an online measure computed during training to assess general expectation of robustness.

cs.CR↗

arXiv2017

Digital Grid: Transforming the Electric Power Grid into an Innovation Engine for the United States

The electric power grid is one of the largest and most complex infrastructures ever built by mankind. Modern civilization depends on it for industry production, human mobility, and comfortable living. However, many critical technologies such as the 60 Hz transformers were developed at the beginning of the 20th century and have changed very little since then.1 The traditional unidirectional power from the generation to the customer through the transmission-distribution grid has also changed nominally, but it no longer meets the need of the 21st century market energy customers. On one hand, 128m US residential customers pay $15B/per month for their utility bill, yet they have no option to select their energy supplier. In a world of where many traditional industries are transformed by digital Internet technology (Amazon, Ebay, Uber, Airbnb), the traditional electric energy market is lagging significantly behind. A move towards a true digital grid is needed. Such a digital grid requires a tight integration of the physical layer (energy and power) with digital and cyber information to allow an open and real time market akin to the world of e-commerce. Another major factor that is pushing for this radical transformation are the rapidly changing patterns in energy resources ownership and load flow. Driven by the decreasing cost in distributed solar, energy storage, electric vehicle, on site generation and microgrids, the high penetration of Distributed Energy Resource (DER) is shifting challenges substantially towards the edge of grid from the control point of view. The envisioned Digital Grid must facilitate the open competition and open innovation needed to accelerate of the adoption of new DER technologies while satisfying challenges in grid stability, data explosion and cyber security.

cs.CY↗