430400 results (page 9 of 17216)
-
Cross-Modal Knowledge Distillation for PET-Free Amyloid-Beta Detection from MRI
Detecting amyloid-$β$ (A$β$) positivity is crucial for early diagnosis of Alzheimer's disease but typically requires PET imaging, which is costly, invasive, and not widely accessible, limiting its use for population-level screening. We address this gap by proposing a PET-guided knowledge distillation framework that enables A$β$ prediction from MRI alone, without requiring non-imaging clinical cova…
-
IDEA: An Interpretable and Editable Decision-Making Framework for LLMs via Verbal-to-Numeric Calibration
Large Language Models are increasingly deployed for decision-making, yet their adoption in high-stakes domains remains limited by miscalibrated probabilities, unfaithful explanations, and inability to incorporate expert knowledge precisely. We propose IDEA, a framework that extracts LLM decision knowledge into an interpretable parametric model over semantically meaningful factors. Through joint le…
-
Deriving volume density profiles of filaments from observed surface densities
Accurate characterization of filamentary structures in star-forming clouds is essential for understanding star formation. Traditional methods fit observed surface density profiles $Σ(r)$ with slope $γ$ and width $H$ using the Plummer function, assuming $β=γ+1$ and $h\approx H$ for the volume density slope and width. These assumptions are inconsistent with the finite nature of filaments. We present…
-
M1-92: AGB interruption and isotopic ratio paradox. Chemistry and morpho-kinematics from improved shapemol modelling
The shaping of planetary nebulae on their evolution from asymptotic giant branch circumstellar envelopes to their final, most often axisymmetrical, form is still a process with many unknown details. The key to understanding the whole shaping process is the study of the transition objects called pre-planetary nebulae (pPNe). In this context, modelling tools must be kept to the standard of radio tel…
-
Evolution-Inspired Sample Competition for Deep Neural Network Optimization
Conventional deep network training generally optimizes all samples under a largely uniform learning paradigm, without explicitly modeling the heterogeneous competition among them. Such an oversimplified treatment can lead to several well-known issues, including bias under class imbalance, insufficient learning of hard samples, and the erroneous reinforcement of noisy samples. In this work, we pres…
-
Scalable Trajectory Generation for Whole-Body Mobile Manipulation
Robots deployed in unstructured environments must coordinate whole-body motion -- simultaneously moving a mobile base and arm -- to interact with the physical world. This coupled mobility and dexterity yields a state space that grows combinatorially with scene and object diversity, demanding datasets far larger than those sufficient for fixed-base manipulation. Yet existing acquisition methods, in…
-
FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing
Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grained fact access. To address this, we propose FABLE, a hierarchical framework that decouples fine-grained fact injection from holistic text generation. FABLE follows a two-stage, fact-first strategy: discrete facts are anchored in shallow layers, fol…
-
Evidence for a bloated massive protostar in IRAS20126+4104
Variability is a well known phenomenon in low-mass young stellar objects, but in recent years the monitoring of methanol masers and infrared continuum emission has permitted the detection of both burst-like episodes and periodic variations also in high-mass (proto)stars. Multi-epoch studies on large samples of these objects have become possible thanks to the NEOWISE database, which surveyed the sk…
-
Cross-Attentive Multiview Fusion of Vision-Language Embeddings
Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and average 2D descriptors across views, or heuristically select a single representative one, often resulting in suboptimal 3D representations. In this work, we intro…
-
DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection
Prompt injection has emerged as a critical security threat to large language models (LLMs), yet existing studies predominantly focus on single-dimensional attack strategies, such as semantic rewriting or character-level obfuscation, which fail to capture the combined effects of multi-space perturbations in realistic scenarios. In addition, systematic black-box robustness evaluations of recent Chin…
-
Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents
Improving policymaking is a central concern in public administration. Prior human subject studies reveal substantial cross-cultural differences in citizens' emotional responses to red tape during policy implementation. While LLM agents offer opportunities to simulate human-like responses and reduce experimental costs, their ability to generate culturally appropriate emotional responses to red tape…
-
A Two-Stage LLM Framework for Accessible and Verified XAI Explanations
Large Language Models (LLMs) are increasingly used to translate the technical outputs of eXplainable Artificial Intelligence (XAI) methods into accessible natural-language explanations. However, existing approaches often lack guarantees of accuracy, faithfulness, and completeness. At the same time, current efforts to evaluate such narratives remain largely subjective or confined to post-hoc scorin…
-
When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP
Data scarcity limits NLP development for low-resource African languages. We evaluate two data augmentation methods -- LLM-based generation (Gemini 2.5 Flash) and back-translation (NLLB-200) -- for Hausa and Fongbe, two West African languages that differ substantially in LLM generation quality. We assess augmentation on named entity recognition (NER) and part-of-speech (POS) tagging using MasakhaNE…
-
MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models
Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptimal. Existing approaches uniformly assign positional indices to all tokens, overlooking variations in information density within and across modalities, which leads to inefficient attention allocation where redundant visual regions dominate while inform…
-
MCAnalysis: An Open-Source Package for Preprocessing, Modelling, and Visualisation of Menstrual Cycle Effects in Digital Health Data
The menstrual cycle influences numerous physiological and psychological outcomes, yet standardised, open-source statistical methods for quantifying these cyclic effects remain lacking. We developed mcanalysis, an open-source package in R and Python implementing a Fourier-basis generalised additive model (GAM) for menstrual cycle research. The package provides a complete pipeline: processing period…
-
Technical Report -- A Context-Sensitive Multi-Level Similarity Framework for First-Order Logic Arguments: An Axiomatic Study
Similarity in formal argumentation has recently gained attention due to its significance in problems such as argument aggregation in semantics and enthymeme decoding. While existing approaches focus on propositional logic, we address the richer setting of First-Order Logic (FOL), where similarity must account for structured content. We introduce a comprehensive framework for FOL argument similarit…
-
Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA
Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on everything else. This setting becomes especially difficult when deletion requests arrive sequentially, because the model must repeatedly adapt without erasing previously retained knowledge. Low-Rank Adaptation (LoRA) offers an efficient way to impleme…
-
CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
Recent advanced diffusion methods typically derive strong generative priors by scaling diffusion transformers. However, scaling fails to generalize when adapted for real-time compression scenarios that demand lightweight models. In this paper, we explore the design of real-time and lightweight diffusion codecs by addressing two pivotal questions. First, does diffusion pre-training benefit lightwei…
-
Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems
Recent work established a generalized-Fano framework for lower bounding prior-predictive (Bayesian) CVaR in interactive statistical decision making. In this paper, we show how to instantiate that framework in concrete interactive problems and derive explicit Bayesian CVaR lower bounds from its abstract corollaries. Our approach compares a hard model with a reference model using squared Hellinger d…
-
Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis
Multimodal sentiment analysis (MSA) integrates heterogeneous text, audio, and visual signals to infer human emotions. While recent approaches leverage cross-modal complementarity, they often struggle to fully utilize weaker modalities. In practice, dominant modalities tend to overshadow non-verbal ones, inducing modality competition and limiting overall contributions. This imbalance degrades fusio…
-
Agentic Control in Variational Language Models
We study whether a variational language model can support a minimal and measurable form of agentic control grounded in its own internal evidence. Our model combines local variational hidden computation (EVE), a homeostatic latent regulator, structurally aware checkpoint retention and a calibrated uncertainty-aware controller operating on top of the retained model. Rather than treating uncertainty …
-
NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)
In this paper, we present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1: Professional Image Quality Assessment. Conventional Image Quality Assessment (IQA) typically relies on scalar scores. By compressing complex visual characteristics into a single number, these methods fundamentally struggle to distinguish subtle differe…
-
Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers
Mobile Manipulation (MoMa) of articulated objects, such as opening doors, drawers, and cupboards, demands simultaneous, whole-body coordination between a robot's base and arms. Classical whole-body controllers (WBCs) can solve such problems via hierarchical optimization, but require extensive hand-tuned optimization and remain brittle. Learning-based methods, on the other hand, show strong general…
-
From Attenuation to Attention: Variational Information Flow Manipulation for Fine-Grained Visual Perception
While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle visual relationships. We attribute this limitation to Visual Attenuation: a phenomenon where sparse fine-grained visual signals are prematurely suppressed or dilut…
-
Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs
Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion: while excelling at complex reasoning tasks, they consistently underperform on fine-grained acoustic perception. We attribute this gap to a fundamental limitation of ASR-centric training, which provides precise linguistic targets but implicitly teaches models to suppress paralinguistic cues and acoustic events …