Zahidul Islam

3 papers · 2025–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

WACV (2) EMNLP (1)

Top co-authors

Mrigank Rochan (3) Sujoy Paul (2)

Research topics

Machine Learning (3) Computer Vision (2) Deep Learning (2) Learning Types · Machine Learning (2) Learning Types · Deep Learning (2) Processing (2) Artificial Intelligence (1) Application Areas (1) Core AI (1) Learning Paradigms (1)

Keywords

video highlight detection (2) unsupervised learning (1) multimodal learning (1) test-time adaptation (1) audio visual (1) audio processing (1) large multimodal model (1) model generalization (1) inference efficiency (1) cross-modality learning (1) token merging (1) temporal generalization (1) vision-language reasoning (1) meta-auxiliary learning (1) cross-modality hallucination (1) video generalization (1) model compression (1) adaptive token reduction (1)

Papers

Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations WACV 2026 AdaptMerge: Inference Time Adaptive Visual and Language-Guided Token Merging for Efficient Large Multimodal Models EMNLP 2025 Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence WACV 2025