4 papers
PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance
Waikit Xiu, Qiang Lu, Junbiao Chen +1
Removing an object is not the same as filling its mask. Cast shadows and contact shading usually lie outside the user-provided instance mask M_obj, so a frozen Fill model that edit…
Beyond Scene Priors: Fine-Grained Traffic Scene Reasoning with Benchmarking and Query-Guided Small-Object Focus
Waikit Xiu, Qiang Lu, Zian Wang +4
In safety-critical traffic scenarios, answering complex questions relies on minute, localized visual cues. However, standard Multimodal Large Language Models (MLLMs) tend to over-a…
Traffic-MLLM: Curiosity-Regularized Supervised Learning for Traffic Scenario Case-Based Reasoning
Waikit Xiu, Qiang Lu, Bingchen Liu +2
For safe and robust autonomous driving, decision-making systems must effectively leverage past experiences to handle the inherent long-tail of traffic scenarios. Case-Based Reasoni…
Contrastive Learning-Driven Traffic Sign Perception: Multi-Modal Fusion of Text and Vision
Qiang Lu, Waikit Xiu, Xiying Li +2
Traffic sign recognition, as a core component of autonomous driving perception systems, directly influences vehicle environmental awareness and driving safety. Current technologies…