MM-OPD: Towards One More Bottleneck Between Perception and Reasoning
Paper ā¢ 2609.32690 ā¢ Published ā¢ 1
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection
CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering
JosephTongĀ
authored 5
papers 23 days ago
SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs
Paper ā¢ 2602.06040 ā¢ Published ā¢ 10
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
Paper ā¢ 2604.08545 ā¢ Published ā¢ 38
Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs
Paper ā¢ 2512.16584 ā¢ Published ā¢ 4
FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
Paper ā¢ 2505.19536 ā¢ Published
hongyuyang23casiaĀ
submitted a
paper to Daily Papers 2 months ago
guojhĀ
authored 3
papers 2 months ago
PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration
Paper ā¢ 2502.09075 ā¢ Published ā¢ 2
TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints
Paper ā¢ 2502.19800 ā¢ Published ā¢ 2
SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
Paper ā¢ 2509.17664 ā¢ Published ā¢ 4
Chaos-2025Ā
authored a
paper 3 months ago
cpystanĀ
authored a
paper 3 months ago
lubinfanĀ
authored 9
papers 3 months ago
PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration
Paper ā¢ 2502.09075 ā¢ Published ā¢ 2
AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization
Paper ā¢ 2407.08156 ā¢ Published ā¢ 2
AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models
Paper ā¢ 2508.10667 ā¢ Published ā¢ 2
CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering
Paper ā¢ 2602.23952 ā¢ Published ā¢ 6
CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery
Paper ā¢ 2502.08902 ā¢ Published ā¢ 2
TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints
Paper ā¢ 2502.19800 ā¢ Published ā¢ 2
Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis
Paper ā¢ 2109.07683 ā¢ Published
Homography Loss for Monocular 3D Object Detection
Paper ā¢ 2204.00754 ā¢ Published ā¢ 3
CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction
Paper ā¢ 2509.15459 ā¢ Published