6 papers
TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems
Shunwen Bai, Ziping Ma, Chaoyang Zhang +4
The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning paths and all…
Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding
Yifan Wang, Peiming Li, Shiyu Li +5
While Multimodal Large Language Models (MLLMs) excel in cross-modal reasoning, they often struggle to perceive fine-grained details in complex high-resolution images. Recent traini…
SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection
Yifan Wang, Yian Zhao, Fanqi Pu +4
Existing monocular 3D detectors typically tame the pronounced nonlinear regression of 3D bounding box through decoupled prediction paradigm, which employs multiple branches to esti…
TGM-VLA: Task-Guided Mixup for Sampling-Efficient and Robust Robotic Manipulation
Fanqi Pu, Lei Jiang, Wenming Yang
The performance of robotic imitation learning is fundamentally limited by data quality and training strategies. Prevalent sampling strategies on RLBench suffer from severe keyframe…
Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection
Yifan Wang, Xiaochen Yang, Fanqi Pu +2
Monocular 3D object detection has attracted great attention due to simplicity and low cost. Existing methods typically follow conventional 2D detection paradigms, first locating ob…
MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors
Fanqi Pu, Yifan Wang, Jiru Deng +1
Perspective projection has been extensively utilized in monocular 3D object detection methods. It introduces geometric priors from 2D bounding boxes and 3D object dimensions to red…