6 papers
InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward
Zhiwei Ning, Wenwen Tong, Xiangli Kong +12
While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-cent…
V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning
Zhiwei Ning, Xuanang Gao, Jiaxi Cao +6
Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although re…
Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object Detection
Zhiwei Ning, Xuanang Gao, Jiaxi Cao +5
Linear modeling methods like Mamba have been merged as the effective backbone for the 3D object detection task. However, previous Mamba-based methods utilize the bidirectional enco…
CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Prediction
Zhiwei Ning, Zhaojiang Liu, Xuanang Gao +4
Multi-modal methods based on camera and LiDAR sensors have garnered significant attention in the field of 3D detection. However, many prevalent works focus on single or partial sta…
FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text
Bingchao Wang, Zhiwei Ning, Jianyu Ding +5
CLIP has shown promising performance across many short-text tasks in a zero-shot manner. However, limited by the input length of the text encoder, CLIP struggles on under-stream ta…
CD-NGP: A Fast Scalable Continual Representation for Dynamic Scenes
Zhenhuan Liu, Shuai Liu, Zhiwei Ning +4
Novel view synthesis (NVS) in dynamic scenes faces persistent challenges in memory consumption, model complexity, training efficiency, and rendering quality. Offline methods offer…