1273993 results (page 118 of 50960)
-
MCMC with Adaptive Principal-Component Transformation: Rotation-Invariant Universal Samplers for Bayesian Structural System Identification
Over decades, Markov chain Monte Carlo (MCMC) methods have been widely studied, with a typical application being the quantification of posterior uncertainties in Bayesian system identification of structural dynamic models. To address the issue of excessively low sampling efficiency in generic MCMC methods when applied to specific problems, researchers developed several MCMC algorithms that integra…
-
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement learning (RL) offers a principled post-training framework, its direct application is hindered by the intractable likelihoods of these models. Prior work therefore either optimizes an induced Markov decision process (MDP) over sampling trajectories, w…
-
Constraint-Based Analysis of Reasoning Shortcuts in Neurosymbolic Learning
Neurosymbolic systems can satisfy logical constraints during learning without achieving the intended concept-label correspondence; this is a problem known as reasoning shortcuts. We formalize reasoning shortcuts as a constraint satisfaction problem and investigate under which conditions concept mappings are uniquely determined by the constraints. We prove that a discrimination property (requiring …
-
Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis
Convolutional neural networks (CNNs) have become increasingly difficult to deploy in resource-constrained environments due to their large memory and computational requirements. Although low-rank compression methods can reduce this burden, most existing approaches compress spatial and channel redundancy independently and therefore do not fully exploit the localised structure within convolutional fe…
-
Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents
Autonomous Large Language Model (LLM) agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorized tool execution. Securing these systems requires effective information flow tracking. Yet, tradition…
-
Physics-Informed Temporal U-Net for High-Fidelity Fluid Interpolation
Reconstructing high-fidelity fluid dynamics from sparse temporal observations is quite challenging, mainly due to the chaotic and non-linear nature of fluid transport. Standard deep learning-based interpolation methods often tend to regress to the mean, which results in spatial blurring and temporal strobing, especially noticeable around the observed anchor frames where transitions become disconti…
-
When Context Sticks: Studying Interference in In-Context Learning
This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's ability to adapt to later tasks. Using synthetic regression tasks over linear and quadratic functions, we examine how models trained under sequential, mixed, and random curricula handle abrupt task switches during inference. By sweeping over struct…
-
Nonlinear Non-Gaussian Density Steering with Input and Noise Channel Mismatch: Sinkhorn with Memory for Solving the Control-affine Schrödinger Bridge Problem
Solutions to the Schrödinger bridge problem and its generalizations yield feedback control policies for optimal density steering over a controlled diffusion. To numerically compute the same, the dynamic Sinkhorn recursion has become a standard approach. The mathematical engine behind this approach is the Hopf-Cole transform that recasts the conditions for optimality into a system of boundary-coupl…
-
TEMPO: Transformers for Temporal Disease Progression from Cross-Sectional Data
Event-Based Models (EBMs) infer biomarker progression from cross-sectional data but typically only as ordinal sequences and rely on rigid model assumptions. We propose \textsc{Tempo}, a Transformer architecture that learns both ordinal and continuous event sequences through simulation-based supervised learning. \textsc{Tempo} uses two Transformer modules: one treats biomarkers as tokens to infer e…
-
GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs
Autonomous multi-agent LLM systems are increasingly deployed to investigate operational incidents and produce structured diagnostic reports. Their trustworthiness hinges on whether each claim is grounded in observed evidence rather than model-internal inference. Existing groundedness evaluators (binary classifiers, LLM-as-judge scalars, self-correction loops) treat supporting evidence as interchan…
-
Spectral Butterfly Effect and Resilient Ringdown in Thick Braneworlds
The quasinormal mode spectrum is a unique fingerprint linking gravitational-wave observations to extra-dimensional geometry. In this Letter, we show that thick braneworlds exhibit a spectral butterfly effect: infinitesimal deformations of the effective potential trigger dramatic migrations of quasinormal modes, challenging the presumed stability of this fingerprint. Frequency-domain instabilities …
-
UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems
Adversarial attacks play a pivotal role in testing and improving the reliability of deep learning (DL) systems. Existing literature has demonstrated that subtle perturbations to the input can elicit erroneous outcomes, thereby substantially compromising the security of DL systems. This has emerged as a critical concern in the development of DL-based safety-critical systems like Autonomous Driving …
-
An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code
Large language models (LLMs) have demonstrated strong performance on a wide range of software engineering tasks, including code generation and analysis. However, most prior work relies on cloud-based models or specialized hardware, limiting practical applicability in privacy-sensitive or resource-constrained environments. In this paper, we present a systematic empirical evaluation of two locally d…
-
Learning from Demonstration with Failure Awareness for Safe Robot Navigation
Learning from demonstration is widely used for robot navigation, yet it suffers from a fundamental limitation: demonstrations consist predominantly of successful behaviors and provide limited coverage of unsafe states. This limitation leads to poor safety when the robot encounters scenarios beyond the demonstration distribution. Failure experiences, such as collisions, contain essential informatio…
-
Modelling spatial heterogeneity in the effects of area-level covariates on income distributions using Bayesian nonparametric methods
Understanding the how the distribution of an economic outcome, such as income, changes with respect to space and covariates is a key concern for policy makers. To address this, we develop a Bayesian nonparametric model, the Normalised Latent Measure Factor Model with Covariates (NLMFM-C), which expresses a large collection of related densities as mixtures of latent factor densities and allows for …
-
VeriLLMed: Interactive Visual Debugging of Medical Large Language Models with Knowledge Graphs
Large language models (LLMs) show promise in medical diagnosis, but real-world deployment remains challenging due to high-stakes clinical decisions and imperfect reasoning reliability. As a result, careful inspection of model behavior is essential for assessing whether diagnostic reasoning is reliable and clinically grounded. However, debugging medical LLMs remains difficult. First, developers oft…
-
LEGO: An LLM Skill-Based Front-End Design Generation Platform
Existing LLM-based EDA agents are often isolated task-specific systems. This leads to repeated engineering effort and limited reuse of successful design and debugging strategies. We present LEGO, a unified skill-based platform for front-end design generation. It decomposes the digital front-end flow into six independent steps and represents every agent capability as a standardized composable circu…
-
Explainable AI in Speaker Recognition -- Making Latent Representations Understandable
Neural networks can be trained to learn task-relevant representations from data. Understanding how these networks make decisions falls within the Explainable AI (XAI) domain. This paper proposes to study an XAI topic: uncovering unknown organisational patterns in network representations, particularly those representations learned by the speaker recognition network that recognises the speaker ident…
-
Testing Scalar Field Dark Matter models in M31 galaxy through the Rotation Curve analysis
We explore the viability of scalar field dark matter halo models through the rotation curve analysis of the Andromeda galaxy (M31), taking into account a realistic description of its baryonic structure. The mass model includes a stellar disk described by the Freeman profile and two alternative bulge configurations: a classical single de Vaucouleurs bulge and a two-component structure consisting of…
-
When Chain-of-Thought Fails, the Solution Hides in the Hidden States
Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant information. We present a mechanistic causal analysis of CoT on GSM8K using activation patching: transferring token-level hidden states from a CoT generation to a direct-answer run for the same question, then measuring the effect on final-answer accu…
-
GeoFunFlow-3D: A Physics-Guided Generative Flow Matching Framework for High-Fidelity 3D Aerodynamic Inference over Complex Geometries
Deep generative models and neural operators have demonstrated significant potential for 3D aerodynamic inference. However, they often face inherent challenges in maintaining physical consistency and preserving high-frequency features, primarily due to spectral bias and gradient conflicts within the governing equations. To address these issues, we propose GeoFunFlow-3D, a physics-guided generative …
-
EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs
Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in applications such as social robots and human-computer interaction, where understanding human emotions is essential. However, existing benchmarks mainly formulate emotion understanding as a static recognition problem, leaving it largely unclear whethe…
-
Evaluating Large Language Models on Computer Science University Exams in Data Structures
We present a comprehensive evaluation of Large Language Models (LLMs) on Computer Science (CS) Data Structure examination questions. Our work introduces a new benchmark dataset comprising exam questions from Tel Aviv University (TAU), curated to assess LLMs' abilities in handling closed and multiple-choice questions. We evaluated the performance of OpenAI's GPT 4o and Anthropic's Claude 3.5, popul…
-
Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue
Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn actions. Large language models (LLMs) can infer such constraints but are unreliable over long horizons, while Reinforcement learning (RL) optimizes long-horizon behavior yet cannot recover constraints from raw dialogue. Naively coupling LLMs with RL is t…
-
Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection
Conventional object detectors typically operate under a closed-set assumption, limiting recognition to a predefined set of base classes seen during training. Open-vocabulary object detection (OVD) addresses this limitation by leveraging vision-language models (VLMs) to generate pseudo labels for novel object classes. However, existing OVD methods suffer from two critical drawbacks: (1) inaccurate …