Bilge Soran

5 papers · 2015–2025 · 4 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 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

ICCV (2) CVPR (1) ICLR (1) ICML (1)

Top co-authors

Raghuraman Krishnamoorthi (4) Vikas Chandra (4) Chenchen Zhu (3) Lemeng Wu (3) Zechun Liu (3) Yunyang Xiong (3) Fanyi Xiao (2) Changsheng Zhao (2) Saksham Suri (2) Balakrishnan Varadarajan (2)

Research topics

Artificial Intelligence (4) Machine Learning (4) Application Areas (4) Core AI (4) Computer Vision (3) Processing (3) Analysis (2) Core Methods (1) Learning Paradigms (1)

Keywords

video segmentation (2) model compression (2) vision transformer (1) action recognition (1) knowledge distillation (1) egocentric vision (1) activity recognition (1) segment anything model (1) lightweight model (1) on-device inference (1) memory module (1) activity prediction (1) video object segmentation (1) temporal prediction (1) large language model (1) action forecasting (1) memory attention (1) track anything (1) text-guided compression (1) video token (1)

Papers

EdgeTAM: On-Device Track Anything Model CVPR 2025 Efficient Track Anything ICCV 2025 LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding ICML 2025 SpinQuant: LLM Quantization with Learned Rotations ICLR 2025 Generating Notifications for Missing Actions: Don't Forget to Turn the Lights Off! ICCV 2015