Mahmoud Ahmed

4 papers · 2024–2025 · 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 🌉 Interdisciplinary Bridge · Bronze 📈 Trend Setter

Venues

EMNLP (1) ICCV (1) ICLR (1) NeurIPS (1)

Top co-authors

Mohamed Elhoseiny (4) Eslam Mohamed Bakr (3) Jian Ding (2) Khushbu Pahwa (1) Habib Slim (1) Junjie Fei (1) Mohamed Ayman Mohamed (1) Chenhui Gou (1) Kirolos Ataallah (1) Arpit Prajapati (1)

Research topics

Artificial Intelligence (3) Computer Vision (3) Deep Learning (3) Analysis (3) Core AI (3) Architectures (1) Learning Types (1) Models (1) Processing (1)

Keywords

representation learning (1) temporal reasoning (1) question answering (1) chain-of-thought reasoning (1) point cloud (1) 3d vision (1) video understanding (1) data efficiency (1) spatial reasoning (1) long video understanding (1) multimodal model (1) long-form video (1) referring expression comprehension (1) multimodal benchmark (1) sequence-to-sequence model (1) part segmentation (1) compositional understanding (1) shape retrieval (1) 3d visual grounding (1) video-language evaluation (1)

Papers

InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows EMNLP 2025 Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description ICCV 2025 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition NeurIPS 2024 CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding ICLR 2024