867854 results (page 20 of 34715)
-
Passive RIS Is Not Silent: Revisiting Performance Limits Under Thermal Noise
Reconfigurable intelligent surfaces (RISs) have emerged as a promising solution for enabling energy-efficient and flexible spectrum usage in wireless communication, particularly in the context of sixth-generation (6G) networks. While passive RIS architectures are widely regarded as virtually noiseless due to the lack of active components, this idealized assumption can lead to misleading performanc…
-
DeepRitzSplit Neural Operator for Phase-Field Models via Energy Splitting
The multi-scale and non-linear nature of phase-field models of solidification requires fine spatial and temporal discretization, leading to long computation times. This could be overcome with artificial-intelligence approaches. Surrogate models based on neural operators could have a lower computational cost than conventional numerical discretization methods. We propose a new neural operator appr…
-
Geometry-Guided 3D Visual Token Pruning for Video-Language Models
Multimodal large language models have demonstrated remarkable capabilities in 2D vision, motivating their extension to 3D scene understanding. Recent studies represent 3D scenes as 3D spatial videos composed of image sequences with depth and camera pose information, enabling pre-trained video-language models to perform 3D reasoning tasks. However, the large number of visual tokens in spatial video…
-
Long-Text-to-Image Generation via Compositional Prompt Decomposition
While modern text-to-image (T2I) models excel at generating images from intricate prompts, they struggle to capture the key details when the inputs are descriptive paragraphs. This limitation stems from the prevalence of concise captions that shape their training distributions. Existing methods attempt to bridge this gap by either fine-tuning T2I models on long prompts, which generalizes poorly to…
-
DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
Query auto-completion (QAC) has been widely studied in the context of web search, yet remains underexplored for in-document search, which we term DocQAC. DocQAC aims to enhance search productivity within long documents by helping users craft faster, more precise queries, even for complex or hard-to-spell terms. While global historical queries are available to both WebQAC and DocQAC, DocQAC uniquel…
-
Domain-Specialized Object Detection via Model-Level Mixtures of Experts
Mixture-of-Experts (MoE) models provide a structured approach to combining specialized neural networks and offer greater interpretability than conventional ensembles. While MoEs have been successfully applied to image classification and semantic segmentation, their use in object detection remains limited due to challenges in merging dense and structured predictions. In this work, we investigate mo…
-
WiFo-MiSAC: A Wireless Foundation Model for Multimodal Sensing and Communication Integration via Synesthesia of Machines (SoM)
Current learning-based wireless methods struggle with generalization due to the fragmented processing of communication and sensing data. WiFo-MiSAC addresses this as a task-agnostic foundation model that tokenizes heterogeneous signals into a unified space for self-supervised pre-training. A shared-specific disentangled mixture-of-experts (SS-DMoE) architecture is employed to decouple modality-sha…
-
LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL
Recently, code-oriented large language models (LLMs) have demonstrated strong capabilities in translating natural language into executable code. Text-to-SQL is a significant application of this ability, enabling non-technical users to interact with relational databases using natural language. However, state-of-the-art models continue to struggle with highly complex logic, particularly deeply neste…
-
Impact of Cold Jupiter Scattering on the Mean-Motion Resonance of Inner Small Planets
A key feature of close-in, multiple super-Earth (SE) systems is the tendency for adjacent planet pairs to lie just wide of low-order mean-motion resonances (MMR). This period ratio distribution has motivated numerous theoretical studies, particularly those invoking post-disk processes that perturb initially resonant architectures. We investigate whether orbital instability among cold Jupiters (CJs…
-
Style-Based Neural Architectures for Real-Time Weather Classification
In this paper, we present three neural network architectures designed for real-time classification of weather conditions (sunny, rain, snow, fog) from images. These models, inspired by recent advances in style transfer, aim to capture the stylistic elements present in images. One model, called "Multi-PatchGAN", is based on PatchGANs used in well-known architectures such as Pix2Pix and CycleGAN, bu…
-
Medical Image Understanding Improves Survival Prediction via Visual Instruction Tuning
Accurate prognostication and risk estimation are essential for guiding clinical decision-making and optimizing patient management. While radiologist-assessed features from CT scans provide valuable indicators of disease severity and outcomes, interpreting such images requires expert knowledge, and translating rich visual information into textual summaries inevitably leads to information loss. In t…
-
Where Do Self-Supervised Speech Models Become Unfair?
Speech encoder models are known to model members of some speaker groups (SGs) better than others. However, there has been little work in establishing why this occurs on a technological level. To our knowledge, we present the first layerwise fairness analysis of pretrained self-supervised speech encoder models (S3Ms), probing each embedding layer for speaker identification (SID) automatic speech re…
-
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection
Current open-source prompt-injection detectors converge on two architectural choices: regular-expression pattern matching and fine-tuned transformer classifiers. Both share failure modes that recent work has made concrete. Regular expressions miss paraphrased attacks. Fine-tuned classifiers are vulnerable to adaptive adversaries: a 2025 NAACL Findings study reported that eight published indirect-i…
-
Near-Codewords Aware Bit Flipping Decoding of QC-MDPC Codes
Bit-Flipping (BF) decoders are a family of decoders widely employed in post-quantum cryptographic schemes based on Quasi-Cyclic Moderate-Density Parity-Check (QC-MDPC) codes, such as BIKE. BF decoders suffer from trapping sets, corresponding to low-weight error patterns that likely lead to decoding failures. For QC-MDPC codes, the most relevant family of trapping sets is that of near-codewords, wh…
-
Holographic dark energy as a source for slowly rotating wormholes: Implications for null geodesics and shadows
In this work, we explore for the first time slowly rotating traversable wormholes embedded in holographic dark energy. We focus on three representative holographic dark energy models -- Rényi, mixed, and Moradpour -- and construct the wormhole shape functions directly from these energy density profiles using a Teo-type rotating wormhole metric. This allows us to examine the wormhole geometry in de…
-
Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols
Large language models are increasingly deployed as protocols: structured multi-call procedures that spend additional computation to transform a baseline answer into a final one. These protocols are evaluated only by end-to-end accuracy, giving limited insight into when they help, when they hurt, and whether their behavior transfers under distribution shift or composition. We propose a paired-outco…
-
Horospherical Depth and Busemann Median on Hadamard Manifolds
\We introduce the horospherical depth, an intrinsic notion of statistical depth on Hadamard manifolds, and define the Busemann median as the set of its maximizers. The construction exploits the fact that the linear functionals appearing in Tukey's half-space depth are themselves limits of renormalized distance functions; on a Hadamard manifold the same limiting procedure produces Busemann function…
-
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation
As reinforcement learning continues to scale the training of large language model-based agents, reliably verifying agent behaviors in complex environments has become increasingly challenging. Existing approaches rely on rule-based verifiers or LLM-as-a-Judge models, which struggle to generalize beyond narrow domains. Agent-as-a-Judge addresses this limitation by actively interacting with environme…
-
Towards Disentangled Preference Optimization Dynamics Beyond Likelihood Displacement
Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based objectives suppress the chosen response along with the rejected one, a phenomenon known as likelihood displacement, and no general mechanism currently prevents this across objectives. We bridge this gap by presenting a unified \emph{incentive-score decomposition} of pre…
-
Semantic-based Distributed Learning for Diverse and Discriminative Representations
In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint extraction of structural representations from data samples. However, conventional task-specific approaches often result in nonstructural embeddings, leading to collapsed variability among data samples within the same class, particularly in classification tasks…
-
COFFAIL: A Dataset of Successful and Anomalous Robot Skill Executions in the Context of Coffee Preparation
In the context of robot learning for manipulation, curated datasets are an important resource for advancing the state of the art; however, available datasets typically only include successful executions or are focused on one particular type of skill. In this short paper, we briefly describe a dataset of various skills performed in the context of coffee preparation. The dataset, which we call COFFA…
-
Negative Advantage Is a Double-Edged Sword: Calibrating Advantage in GRPO for Deep Search
Deep search agents can autonomously initiate multi-turn interactions with search engines, thereby exhibiting strong question-answering capabilities. Such performance critically relies on Group Relative Policy Optimization (GRPO) as its core training algorithm. However, GRPO still faces several challenges in deep search settings. First, there exists a substantial mismatch between the correctness of…
-
Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge to answer questions more accurately. However, research on evaluating RAG systems-particularly the retriever component-remains limited, as most existing work focuses on single-context retrieval rather than multi-hop queries, where individual contexts may appear irrelevant in isolation but are essent…
-
Aether: Network Validation Using Agentic AI and Digital Twin
Network change validation remains a critical yet predominantly manual, time-consuming, and error-prone process in modern network operations. While formal network verification has made substantial progress in proving correctness properties, it is typically applied in offline, pre-deployment settings and faces challenges in accommodating continuous changes and validating live production behavior. Cu…
-
Order Optimal Task Allocation in Distributed Computing via Interweaved Cliques
We consider a distributed computing system in which a master node coordinates $N$ workers to evaluate a function over $n$ input files, where this function accepts general decomposition. In particular, we focus on the general case where the requested function admits a $d$-uniform decomposition, meaning that it can be decomposed into a set of subfunctions that each depends on a unique $d$-tuple of t…