RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents Paper • 2602.02486 • Published about 1 month ago • 19
RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents Paper • 2602.02486 • Published about 1 month ago • 19
Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems Paper • 2512.24385 • Published Dec 30, 2025 • 8
Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems Paper • 2512.24385 • Published Dec 30, 2025 • 8
Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems Paper • 2512.24385 • Published Dec 30, 2025 • 8
Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future Paper • 2512.16760 • Published Dec 18, 2025 • 15
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion Paper • 2512.04926 • Published Dec 4, 2025 • 42
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning Paper • 2510.02240 • Published Oct 2, 2025 • 18
ReasonMap Collection A fine-grained visual reasoning benchmark (We show more question types in the extension dataset.) • 3 items • Updated Oct 1, 2025 • 8
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning Paper • 2510.02240 • Published Oct 2, 2025 • 18
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning Paper • 2510.02240 • Published Oct 2, 2025 • 18 • 2
A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding Paper • 2508.01197 • Published Aug 2, 2025 • 5
A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding Paper • 2508.01197 • Published Aug 2, 2025 • 5
A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding Paper • 2508.01197 • Published Aug 2, 2025 • 5 • 2
Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport Paper • 2308.01779 • Published Aug 3, 2023 • 1
Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning Paper • 2503.00513 • Published Mar 1, 2025 • 2
Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport Paper • 2308.01779 • Published Aug 3, 2023 • 1
Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning Paper • 2503.00513 • Published Mar 1, 2025 • 2