1273993 results (page 124 of 50960)
-
UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks
Video Question Answering (VideoQA) demands models that jointly reason over spatial, temporal, and linguistic cues. However, the task's inherent complexity often requires multi-step reasoning that current large multimodal models (LMMs) perform implicitly, leaving their internal decision process opaque. In contrast, large reasoning models (LRMs) explicitly generate intermediate logical steps that en…
-
Predictive Directional Selective Fixed-Filter Active Noise Control for Moving Sources via a Convolutional Recurrent Neural Network
Directional Selective Fixed-Filter Active Noise Control (D-SFANC) can effectively attenuate noise from different directions by selecting the suitable pre-trained control filter based on the Direction-of-Arrival (DoA) of the current noise. However, this method is weak at tracking the direction variations of non-stationary noise, such as that from a moving source. Therefore, this work proposes a Pre…
-
An Algebraic State Observer for a Class of Physical Systems
In this paper we present a radically new approach to design state observers for nonlinear systems, with particular emphasis on physical ones. Our objective is to obtain an algebraic relation between the unmeasurable part of the state and filtered versions of the systems inputs and outputs, which holds true for all $t \geq 0$. The latter qualifier should be contrasted with the usual asymptotic (or …
-
UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks
Emerging AR-LLM-based Social Engineering attack (e.g., SEAR) is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attack, the attacker can leverage AR (Augmented Reality) glass to capture the image and vocal information of the target, using the LLM to identify the target and generate the social profile, using the LLM agents to apply social engineering strategies for …
-
Green Manufacturing Capacity Planning by Integrating Distributionally Robust Optimization and Generative AI
Green manufacturing has become a strategic priority for many firms seeking to address sustainability and social responsibility, while improving production efficiency and profitability. However, integrating green technologies and renewable energy unavoidably introduces climate-related randomness that affects both product demand and renewable energy generation, underscoring the need for coordinated …
-
GreenDyGNN: Runtime-Adaptive Energy-Efficient Communication for Distributed GNN Training
Distributed GNN training is dominated by remote feature fetching, which can be very costly. Multi-hop neighborhood sampling crosses partition boundaries and triggers fine-grained RPCs whose fixed initiation cost and GPU-stall latency waste energy. Prior systems try to reduce this overhead with presampling and static caching, but cache policies cannot react to runtime network variation. We show tha…
-
CNN-ViT Fusion with Adaptive Attention Gate for Brain Tumor MRI Classification: A Hybrid Deep Learning Model
Early detection and classifying brain tumors using Magnetic Resonance Imaging (MRI) images is highly important but difficult to extract in medical images. Convolutional Neural Networks (CNNs) are good at capturing both local texture and spatial information whereas Vision Transformers (ViTs) are good at capturing long-range global dependencies. We propose a new hybrid architecture that combines a S…
-
How Researchers Navigate Accountability, Transparency, and Trust When Using AI Tools in Early-Stage Research: A Think-Aloud Study
In the early stages of scientific research, researchers rely on core scholarly judgments to identify relevant literature, assess credible evidence, and determine which directions merit pursuit. As AI tools become increasingly integrated into these early-stage workflows, the scholarly judgments that were once transparent and attributable to individual researchers become obscured, raising critical R…
-
Surface Sensitivity in Lean 4 Autoformalization
Natural-language variation poses a key challenge in Lean autoformalization: semantically equivalent paraphrases of the same theorem statements can induce divergent formal outputs, yet it remains unclear whether this variation reflects semantic disagreements or shallower failures. We investigate this question in Lean 4 using 60 deterministic paraphrase rules applied to ProofNet\# and miniF2F. Acros…
-
h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network
Accurate molecular representations are critical for drug discovery, and a central challenge lies in capturing the chemical environment of molecular fragments, as key interactions, such as H-bond and π stacking, occur only under specific local conditions. Most existing approaches represent molecules as atom-level graphs; however, atom-level representations can hardly express higher-order chemical c…
-
High-Precision Framework for Expected Hitting Times Analysis in the Dice-Sum Process
We study the expected number of rolls required for the cumulative sum of a fair six-sided die to first enter a prescribed target set $H\subset\mathbb{Z}_{\ge0}$. A one-variable dynamic-programming formulation is introduced that removes dependence on the roll count. Within this framework, the infinite process is truncated at a large cutoff $N$ and corrected by an analytically derived overshoot term…
-
Mechanistic Steering of LLMs Reveals Layer-wise Feature Vulnerabilities in Adversarial Settings
Large language models (LLMs) can still be jailbroken into producing harmful outputs despite safety alignment. Existing attacks show this vulnerability, but not the internal mechanisms that cause it. This study asks whether jailbreak success is driven by identifiable internal features rather than prompts alone. We propose a three-stage pipeline for Gemma-2-2B using the BeaverTails dataset. First, w…
-
MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration
Knowledge workers face increasing challenges in synthesizing information from multiple documents into structured conceptual understanding. This process is inherently iterative: users explore content, identify relationships between concepts, and continuously reorganize their mental models. However, current approaches offer limited support. LLM-based systems let users query information but not shape…
-
System-Level Impacts of Flexible Data Center Load Scheduling on Cost, Emissions, and Transmission Congestion
Large data centers are being deployed in the U.S. at an unprecedented rate, introducing significant flexible load potential. A portion of data center workloads - best-effort (BE) jobs - can be scheduled flexibly to reduce power system operating costs and emissions. However, the system-level impacts of such scheduling remain underexplored. This paper investigates the effects of flexible data center…
-
A Dynamic Learning Observatory Reveals the Rapid Salinization of Satkhira, Bangladesh
Soil salinity is a major environmental challenge in coastal Bangladesh, threatening agricultural productivity and local livelihoods. This study develops a machine-learning-based framework to predict and map soil salinity in Satkhira district by integrating field observations with Landsat-derived spectral indices. A total of 205 soil samples collected during 2024-2025 were used to train an Extreme …
-
PEEPSS: Photonic-Enabled ExoPlanet Spectroscopic Sensor for the Habitable Worlds Observatory
The next few years will be critical for technology development for Habitable Worlds Observatory (HWO) in its mission to search for and characterize extrasolar planets. To achieve its stated goals with contrasts of one part in ten billion, HWO will require outstanding stability and precision, particularly in measuring and controlling the wavefront of the light propagate through the telescope and co…
-
Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label
Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior research has made progress in addressing this combined challenge, it overlooks the severe label-image mismatch inherent to high-noise settings, thereby limiting their effectiveness. Given that observed labels, though mismatched with images, still r…
-
ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiation
As software systems grow in complexity, they must satisfy an increasing number of competing quality attributes, making it essential to balance them in a principled manner -- for example, a safety requirement for sensor-fusion verification may conflict with a tight planning-cycle budget. Multi-agent large language model frameworks support this balancing process by assigning specialized agents to di…
-
The Dependence of the Mean Spectral Energy Distributions on the Accretion Rate for Quasars with $z < 0.75$ from the Sloan Digital Sky Survey
We construct mean spectral energy distributions (SEDs) for a substantial sample of 56,969 Sloan Digital Sky Survey DR16 quasars with $z < 0.75$, utilizing multiwavelength data from the mid-infrared (MIR) to ultraviolet (UV). These SEDs are built on eigenvector 1 parameters -- the relative optical $\rm Fe~ II$ strength ($R_{\rm Fe~II}$) and the H$β$ line width ($\rm Hβ$) -- that capture the princip…
-
Source-Code Analysis of iFogSim for Simulating Distributed IoT Architectures: Coverage, Challenges, and Enhancements
Simulation is an indispensable tool for validating distributed IoT architectures before physical deployment, and iFogSim has emerged as one of the most widely adopted platform in the fog and edge computing research community. Yet the experience of using iFogSim for non-canonical, application-specific architectures remains incompletely documented, leaving practitioners without guidance on when the …
-
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
Have you ever post-trained a generalist vision-language-action (VLA) policy on a small demonstration dataset, only to find that it stops responding to new instructions and is limited to behaviors observed during post-training? We identify this phenomenon as lock-in: after low-data, supervised fine-tuning (SFT), the policy becomes overly specialized to the post-training data and fails to generalize…
-
Analysis of Efficient Scheduling in Layered Decoding of GLDPC Codes
In this study, we investigate the characteristics of scheduling sequences that enable efficient decoding of generalized low-density parity-check (GLDPC) codes under the layered message-passing algorithm. In particular, we show that scheduling sequences leading to higher decoding efficiency should prioritize the update of constraint nodes corresponding to subcodes with larger minimum distance, fewe…
-
Hessian-based photometric substructure as an evolutionary tracer of OB cluster candidates in M31
Using \textit{Hubble Space Telescope} images from the PHAT and PHAST surveys, we construct an updated catalogue of 747 OB cluster (OBC) candidates. We introduce a dimensionless structural metric, the trace coefficient of variation ($CV_{\rm tr}$), derived from the Hessian matrix in four \textit{HST} bands, to quantify the internal photometric substructure of partially resolved OBC candidates. Cros…
-
HBGSA: Hydrogen Bond Graph with Self-Attention for Drug-Target Binding Affinity Prediction
Accurate prediction of drug-target binding affinity accelerates drug discovery by prioritizing compounds for experimental validation. Current methods face three limitations: sequence-based approaches discard spatial geometric constraints, structure-based methods fail to exploit hydrogen bond features, and conventional loss functions neglect prediction-target correlation, a key factor for identifyi…
-
A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning
In limited-data settings, a single endpoint mean of an evaluation metric such as the Continuous Ranked Probability Score (CRPS) is itself a random variable, yet it is routinely reported as if it were a stable property of the method. We study when this practice fails. Using 50 independent repetitions across six regression datasets, we show that CRPS variance trajectories differ substantially across…