6 papers
Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning
Zhongan Bi, Kepeng Lin, Xuanang Gao +2
Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further encourage policies to rely on…
Quality Determines Direction, Length Shapes Magnitude: Length Control for Open-Ended Reinforcement Learning
Zijun Weng, Zhongan Bi, Xuanang Gao +5
Reinforcement learning (RL) changes not only what language models say, but also how much they say, often increasing response length at the cost of token efficiency. Controlling thi…
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…