1273993 results (page 101 of 50960)
-
Efficient Near Field Beam Tracking via Thompson Sampling
The shift to the radiative near field region due to large antenna arrays necessitates beamforming that accounts for both angle and range, evolving mobility management into a joint angular range tracking challenge. Conventional schemes rely on rigid pilot payload structures with dedicated training slots, which interrupt data transmission and degrade spectral efficiency. To address this, we propose …
-
TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students. While effective on static single-turn tasks, its behavior in multi-turn agent settings remains underexplored. In this work, we identify a key limitation of vanilla OPD in such settings, which we term Trajectory-Level KL Instability. Specifically, w…
-
Single-Cycle Multidirectional EOG Classification Faster than Human Reaction Time for Wearable Human-Computer Interactions
Electrooculogram (EOG) is a non-invasive bio-signal generated by the potential difference between the retina and cornea during eye movement, and is widely utilized in Human-Computer Interaction (HCI) systems. Expanding the range of detectable eye movements enhances system capability. However, increasing the number of classes typically degrades classification performance. While AI-based approaches …
-
Stabilizing Efficient Reasoning with Step-Level Advantage Selection
Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead through length-based rewards or pruning, many approaches are post-trained under a much shorter context window than base-model training, a factor whose effect has …
-
IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models
Improving the effectiveness of human-robot interaction requires social robots to accurately infer human goals through robust intention understanding. This challenge is particularly critical in multimodal settings, where agents must integrate heterogeneous signals including text, visual cues to form a coherent interpretation of user intent. This paper presents IntentVLM, a novel two-stage video-lan…
-
CT-FineBench: A Diagnostic Fidelity Benchmark for Fine-Grained Evaluation of CT Report Generation
The evaluation of generated reports remains a critical challenge in Computed Tomography (CT) report generation, due to the large volume of text, the diversity and complexity of findings, and the presence of fine-grained, disease-oriented attributes. Conventional evaluation metrics offer only coarse measures of lexical overlap or entity matching and fail to reflect the granular diagnostic accuracy …
-
Shared-kernel Wavelet Neural Networks for Poisson Image Reconstruction
The Laplacian operator transforms the image into its Laplacian field, which usually is sparse and satisfies a stable distribution. On the other hand, an image can be uniquely reconstructed from its Laplacian field via solving a Poisson equation with a proper boundary condition. Such uniqueness is mathematically guaranteed. Thanks to these properties, we propose to use the sparse Laplacian field to…
-
Adaptive-Distribution Randomized Neural Networks for PDEs: A Low-Dimensional Distribution-Learning Framework
Randomized neural networks (RaNNs) are attractive for partial differential equations (PDEs) because they replace expensive end-to-end training with a linear least-squares solve over randomized hidden features. Their practical performance, however, depends strongly on the sampling distribution of the hidden-layer parameters, which is usually chosen heuristically and problem by problem. This distrib…
-
SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs
Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explored. Existing routing strategies are either hand-crafted or modality-agnostic, relying on idealized priors that ignore the layer-dependent modality fusion patterns in MoE-VLMs and provide little guidance for expert specia…
-
Extracting Exact Lie Derivatives Without Backpropagation: A Dual Compiler for Neural Control Barrier Functions
Deploying neural-network control barrier functions (CBFs) on embedded hardware requires evaluating the barrier value and its Lie derivatives along the system vector fields at every control cycle. The standard mechanism for exact gradient extraction, reverse-mode automatic differentiation, constructs a dynamic computational graph whose memory footprint grows with network depth and whose backward tr…
-
When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models
Discrete diffusion language models (dLLMs) enable parallel token updates with bidirectional attention, yet practical generation typically adopts blockwise semi-autoregressive decoding. This switch creates a training-inference mismatch: training denoises with full-sequence context, while inference commits tokens within a bounded block without future context. Therefore, decoding with fixed-size or h…
-
EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce
Product mapping, the task of deciding whether two e-commerce listings refer to the same product, is a core problem for price monitoring and channel visibility. In real marketplaces, however, sellers frequently inject promotional keywords, platform-specific tags, and bundle descriptions into titles, causing the same product to appear under many different names. Recent LLM-based and multi-agent fram…
-
Reconstructing the cosmic expansion with a generalized q(z) parameterization: A decelerating Universe from late-time constraints
We present a generalized phenomenological parameterization of the deceleration parameter $q(z)$ that incorporates an effective radiative component (ERC) in addition to a localized late-time contribution. The proposed framework extends previous two-parameter $q(z)$ reconstructions by explicitly regulating the high-redshift behavior while preserving the late-time transition dynamics. We constrain th…
-
Failure-Centered Runtime Evaluation for Deployed Trilingual Public-Space Agents
This paper presents PSA-Eval, a failure-centered runtime evaluation framework for deployed trilingual public-space agents. The central claim is that, when the evaluation object shifts from a static input-output mapping to a runtime system, the basic unit of analysis should shift from score to failure. PSA-Eval extends the conventional chain Question -> Answer -> Score -> End into Question -> Batch…
-
Fix Initial Codes and Iteratively Refine Textual Directions Toward Safe Multi-Turn Code Correction
Recent work on large language models (LLMs) has emphasized the importance of scaling inference compute. From this perspective, the state-of-the-art method Scattered Forest Search (SFS) has been proposed, employing Monte Carlo Tree Search with carefully crafted initial seeds and textual optimization for multi-turn code correction. However, its complexity makes it unclear what factors contribute to …
-
Hindsight Preference Optimization for Financial Time Series Advisory
Time series models predict numbers; decision-makers need advisory -- directional signals with reasoning, actionable suggestions, and risk management. Training language models for such predictive advisory faces a fundamental challenge: quality depends on outcomes unknown at prediction time. We bridge two ideas from reinforcement learning -- using information unavailable during execution to retrospe…
-
Continual Calibration: Coverage Can Collapse Before Accuracy in Lifelong LLM Fine-Tuning
Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspective is incomplete, because uncertainty reliability can degrade earlier and more sharply than top-1 performance. We study this empirically by measuring conformal coverage and calibration error on sequentially fine-tuned models across three model fam…
-
Representational Curvature Modulates Behavioral Uncertainty in Large Language Models
In autoregressive large language models (LLMs), temporal straightening offers an account of how the next-token prediction objective shapes representations. Models learn to progressively straighten the representational trajectory of input sequences across layers, potentially facilitating next-token prediction via linear extrapolation. However, a direct link between this trajectory and token-level b…
-
A Geometric Witness Framework for Signed Multivariate Tail-Dependence Compatibility: Asymptotic Structure and Finite-Threshold Synthesis
We study multivariate tail-dependence compatibility for complete and partial signed tail families, treating lower-tail, upper-tail, and mixed configurations in one geometric witness representation indexed by active coordinate sets and sign patterns. For a complete signed tail family, witness generator weights w = (w_{I,sigma}) give a linear incidence parametrization and are recovered by explicit t…
-
Hierarchical Prototype-based Domain Priors for Multiple Instance Learning in Multimodal Histopathology Analysis
Digital pathology has fundamentally altered diagnostic workflows by enabling the computational analysis of gigapixel Whole Slide Images (WSIs), yet effectively deciphering their complex tumor microenvironments remains a formidable challenge. Existing Multiple Instance Learning (MIL) frameworks typically treat Whole Slide Images as unstructured bags of patches, discarding critical morphological sem…
-
SUDA-Muon: Structural Design Principles and Boundaries for Fully Decentralized Muon
Fully decentralized Muon is difficult because its nonlinear matrix-sign operator does not commute with linear gossip averaging. This makes decentralized Muon a structural design problem: in designing the algorithm, one must distinguish modular components from non-modular ones. We propose \sudamuon{}, which realizes this separation through a unified primal--dual communication template called SUDA; …
-
SDSL-Solver: Scalable Distributed Sparse Linear Solvers for Large-Scale Interior Point Methods
The solution of sparse linear systems constitutes the dominant computational bottleneck in interior point methods (IPMs), frequently consuming over 70% of the total solution time. As optimization problems scale to millions of variables, direct solvers encounter prohibitive fill-in, excessive memory consumption, and limited parallel scalability. We present SDSL-Solver, a scalable distributed sparse…
-
Supporting Family-School Partnerships with Robot-Facilitated Home-Based Activities
Family-school partnerships (FSP) are critical to children's development, yet families often face barriers such as time constraints, fragmented communication, and limited opportunities for meaningful engagement. As a step toward facilitating broader family-school partnerships, we explore a novel approach that integrates a social robot into family settings, specifically supporting home-based activit…
-
Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification
Accurate biomedical image classification under low-resource conditions remains challenging due to limited annotations, subtle inter-class visual differences, and complex disease semantics. While vision--language models offer a promising foundation for mitigating data scarcity, their effective adaptation in biomedical settings is constrained by the need for parameter-efficient tuning alongside fine…
-
Designing Robots to Support Parent-Child Connections: Opportunities Through Robot-Mediated Communication
The sense of family connectedness may support positive outcomes including individual well-being, resilience, and healthy family functioning. However, as technologies advance, they often replace human-human interactions instead of nurturing them. In this work, we investigate how robot-facilitated communication tools might instead create new opportunities for family connection. We conducted two stud…