Imagen de Portada

SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chaybouti, Sofian, Narayan, Sanath, Dahou, Yasser, Khac, Phúc H. Lê, Singh, Ankit, Huynh, Ngoc Dung, Para, Wamiq Reyaz, Kuehne, Hilde, Hacid, Hakim
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition I.4.10; I.5.1
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Falcon Perception
por: Bevli, Aviraj, et al.
Publicado: (2026)

VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs
por: Törtei, Brigitta Malagurski, et al.
Publicado: (2025)

Vision-Language Models Can't See the Obvious
por: Dahou, Yasser, et al.
Publicado: (2025)

MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
por: Chaybouti, Sofian, et al.
Publicado: (2020)

EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System
por: Chaybouti, Sofian, et al.
Publicado: (2021)

ViSpeR: Multilingual Audio-Visual Speech Recognition
por: Narayan, Sanath, et al.
Publicado: (2024)

SigWavNet: Learning Multiresolution Signal Wavelet Network for Speech Emotion Recognition
por: Nfissi, Alaa, et al.
Publicado: (2025)

REVEAL: Relation-based Video Representation Learning for Video-Question-Answering
por: Chaybouti, Sofian, et al.
Publicado: (2025)

CleanMAP: Distilling Multimodal LLMs for Confidence-Driven Crowdsourced HD Map Updates
por: Shaw, Ankit Kumar, et al.
Publicado: (2025)

T-HITL Effectively Addresses Problematic Associations in Image Generation and Maintains Overall Visual Quality
por: Epstein, Susan, et al.
Publicado: (2024)

MaskInversion: Localized Embeddings via Optimization of Explainability Maps
por: Bousselham, Walid, et al.
Publicado: (2024)

LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity
por: Bousselham, Walid, et al.
Publicado: (2024)

Recurrent Memory-Augmented Transformers with Chunked Attention for Long-Context Language Modeling
por: Kashyap, Ankit
Publicado: (2025)

Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems
por: Nguyen, Viet Dung, et al.
Publicado: (2024)

NeuroGaze-Distill: Brain-informed Distillation and Depression-Inspired Geometric Priors for Robust Facial Emotion Recognition
por: Li, Zilin, et al.
Publicado: (2025)

Enhancing Eye Feature Estimation from Event Data Streams through Adaptive Inference State Space Modeling
por: Nguyen, Viet Dung, et al.
Publicado: (2026)

Composition of rocks and minerals from the Mid-Atlantic Ridge 5-7°N
por: Pushcharovsky, Yury M, et al.
Publicado: (2004)

Chemical composition of basalts and basaltic glasses from the Sierra Leone Fracture Zone region
por: Skolotnev, Sergey G, et al.
Publicado: (2003)

CGAN-ECT: Tomography Image Reconstruction from Electrical Capacitance Measurements Using CGANs
por: Deabes, Wael, et al.
Publicado: (2022)

Physical oceanography during L' Atalante cruise Almofront-1
por: Prieur, Louis Marie
Publicado: (2012)

Parameterizing Dataset Distillation via Gaussian Splatting
por: Jiang, Chenyang, et al.
Publicado: (2025)

Federated Learning for Anomaly Detection in Energy Consumption Data: Assessing the Vulnerability to Adversarial Attacks
por: Telila, Yohannis Kifle, et al.
Publicado: (2025)

Chemical and isotopic compositions of basalts and glasses from lavas of the Sierra Leone fault site
por: Sharkov, E V, et al.
Publicado: (2008)

(Table 1) Rock types dredged at stations of R/V Akademik Nikolaj Strakhov (Cruise 22) and R/V Akademik Ioffe (Cruise 10), Mid-Atlantic Ridge 5-7°N
por: Pushcharovsky, Yury M, et al.
Publicado: (2004)

SigGate-GT: Taming Over-Smoothing in Graph Transformers via Sigmoid-Gated Attention
por: Guo, Dongxin, et al.
Publicado: (2026)

Nutrients measured on water bottle samples during L'Atalante cruise Almofront-1
por: Prieur, Louis Marie
Publicado: (2012)

Adaptation of Distinct Semantics for Uncertain Areas in Polyp Segmentation
por: Nguyen, Quang Vinh, et al.
Publicado: (2024)

DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching
por: Yang, Meng, et al.
Publicado: (2025)

CLIP-Joint-Detect: End-to-End Joint Training of Object Detectors with Contrastive Vision-Language Supervision
por: Raoufi, Behnam, et al.
Publicado: (2025)

Training a Student Expert via Semi-Supervised Foundation Model Distillation
por: Taghavi, Pardis, et al.
Publicado: (2026)

Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation
por: Shafique, Muhammad Ali, et al.
Publicado: (2025)

From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring
por: Nguyen, Minh Hoang, et al.
Publicado: (2026)

CCVA-FL: Cross-Client Variations Adaptive Federated Learning for Medical Imaging
por: Gupta, Sunny, et al.
Publicado: (2024)

FLD+: Data-efficient Evaluation Metric for Generative Models
por: Jeevan, Pranav, et al.
Publicado: (2024)

WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
por: Jeevan, Pranav, et al.
Publicado: (2024)

Normalizing Flow-Based Metric for Image Generation
por: Jeevan, Pranav, et al.
Publicado: (2024)

Taming the Tail: Leveraging Asymmetric Loss and Pade Approximation to Overcome Medical Image Long-Tailed Class Imbalance
por: Kashyap, Pankhi, et al.
Publicado: (2024)

Pigments measured on water bottle samples during cruise ALMOFRONT-1
por: Prieur, Louis Marie, et al.
Publicado: (2012)

Towards Accurate and Efficient Waste Image Classification: A Hybrid Deep Learning and Machine Learning Approach
por: Nguyen, Ngoc-Bao-Quang, et al.
Publicado: (2025)

Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
por: Semenov, Andrei, et al.
Publicado: (2024)