Imagen de Portada

From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Viakhirev, Ivan, Borodin, Kirill, Mkrtchian, Grach
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Interpreting Multi-Branch Anti-Spoofing Architectures: Correlating Internal Strategy with Empirical Performance
por: Viakhirev, Ivan, et al.
Publicado: (2026)

Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative
por: Lysikova, Ksenia, et al.
Publicado: (2026)

Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision
por: Borodin, Kirill, et al.
Publicado: (2026)

Application of ASV for Voice Identification after VC and Duration Predictor Improvement in TTS Models
por: Nikolayevich, Borodin Kirill, et al.
Publicado: (2024)

AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge
por: Borodin, Kirill, et al.
Publicado: (2024)

When Spoof Detectors Travel: Evaluation Across 66 Languages in the Low-Resource Language Spoofing Corpus
por: Borodin, Kirill, et al.
Publicado: (2026)

Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales
por: Xu, Yongzhong
Publicado: (2026)

From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification
por: Kudryavtsev, Vasiliy, et al.
Publicado: (2026)

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations
por: Acharya, Pratyush, et al.
Publicado: (2026)

Manifold of Failure: Behavioral Attraction Basins in Language Models
por: Munshi, Sarthak, et al.
Publicado: (2026)

Origin-Destination Demand Prediction: An Urban Radiation and Attraction Perspective
por: Ma, Xuan, et al.
Publicado: (2024)

Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
por: Ettori, Davide
Publicado: (2026)

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
por: Suresh, Praneet, et al.
Publicado: (2025)

Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts
por: Samandarov, Samandar, et al.
Publicado: (2026)

Hallucination Detection in LLMs Using Spectral Features of Attention Maps
por: Binkowski, Jakub, et al.
Publicado: (2025)

Combining Masked Language Modeling and Cross-Modal Contrastive Learning for Prosody-Aware TTS
por: Borodin, Kirill, et al.
Publicado: (2026)

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
por: Haim, Shahar, et al.
Publicado: (2026)

Dynamics-inspired Structure Hallucination for Protein-protein Interaction Modeling
por: Wu, Fang, et al.
Publicado: (2026)

Generation Constraint Scaling Can Mitigate Hallucination
por: Kollias, Georgios, et al.
Publicado: (2024)

Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
por: Wang, Siqi, et al.
Publicado: (2024)

Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix
por: Zhang, Jinhao, et al.
Publicado: (2026)

WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper
por: Akinrintoyo, Emmanuel, et al.
Publicado: (2025)

Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions
por: Li, Xiaoyi
Publicado: (2026)

Towards Scalable AASIST: Refining Graph Attention for Speech Deepfake Detection
por: Viakhirev, Ivan, et al.
Publicado: (2025)

Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling
por: Xiao, Qiao, et al.
Publicado: (2026)

From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity
por: Liew, Yee Zhing, et al.
Publicado: (2026)

PSNE: Efficient Spectral Sparsification Algorithms for Scaling Network Embedding
por: Lin, Longlong, et al.
Publicado: (2024)

Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
por: Ashiq, Muhammad H., et al.
Publicado: (2026)

Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches
por: Chen, Yifang, et al.
Publicado: (2025)

Spectral Guardrails for Agents in the Wild: Detecting Tool Use Hallucinations via Attention Topology
por: Noël, Valentin
Publicado: (2026)

Spectral Edge Dynamics Reveal Functional Modes of Learning
por: Xu, Yongzhong
Publicado: (2026)

Approaching Deep Learning through the Spectral Dynamics of Weights
por: Yunis, David, et al.
Publicado: (2024)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
por: Muthuraman, Mannmohan
Publicado: (2025)

Learning Robust Spectral Dynamics for Temporal Domain Generalization
por: Yu, En, et al.
Publicado: (2025)

When Denoising Hinders: Revisiting Zero-Shot ASR with SAM-Audio and Whisper
por: Islam, Akif, et al.
Publicado: (2026)

Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models
por: Aminmansour, Farzane, et al.
Publicado: (2020)

HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling
por: Vu, Minh, et al.
Publicado: (2025)

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models
por: Wu, Changlong, et al.
Publicado: (2024)

Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples
por: Lukyanov, Kirill, et al.
Publicado: (2024)

Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
por: Wang, Shengyuan, et al.
Publicado: (2025)