Skip to content
conftrace_

Runsen Xu

11 papers · 2023–2026 · 6 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 ↓
+3 more ↓ 🐣 Hot Topic Early Bird 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Gold πŸ—ΊοΈ Taxonomy Completionist (23) πŸ—ƒοΈ Keyword Collector (61)
πŸ’Ž Century Club Β· Bronze ⚑ Prolific Year Β· Productive 🌈 Renaissance Researcher (5)

Venues

CVPR (4) NeurIPS (3) CoRL (1) ECCV (1) ICCV (1) ICLR (1)

Top co-authors

Jiangmiao Pang (8) Tai WANG (8) Dahua Lin (6) Yilun Chen (4) Chenming Zhu (3) Xiaohan Mao (2) Haifeng Huang (2) Ruiyuan Lyu (2) Wenwei Zhang (2) Jingli Lin (2)

Research topics

Computer Vision (8) Artificial Intelligence (7) Core AI (7) Analysis (6) Machine Learning (4) Domain-Specific (4) Natural Language Processing (2) Robotics (2) Application Areas (2) Capabilities (2) Learning Types (2) Resources & Methods (2) Deep Learning (1) Interdisciplinary (1) Applications (1)

Keywords

visual grounding (2) vision-language model (2) 3d object detection (2) language grounding (2) scene understanding (2) point cloud (2) multimodal learning (2) question answering (2) self-supervised learning (1) egocentric vision (1) visual question answering (1) 3d scene understanding (1) large multimodal model (1) embodied ai (1) object detection (1) visual correspondence (1) information entropy (1) in-context learning (1) depth perception (1) contrastive learning (1)

Papers

G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning CVPR 2026 Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models CVPR 2026 VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization ICCV 2025 Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers NeurIPS 2024 EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI CVPR 2024 MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations NeurIPS 2024 PointLLM: Empowering Large Language Models to Understand Point Clouds ECCV 2024 VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding CoRL 2024 CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving ICLR 2023 Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator NeurIPS 2023 MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training CVPR 2023