4 papers
GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models
Pedram MohajerAnsari, Amir Salarpour, Run Wang +1
Vision-language models such as CLIP and SigLIP provide strong zero-shot recognition, but their predictions can degrade when deployed on target data that differ from the pretraining…
Adversarial Prompts for Acceptance Collapse in Speculative Decoding
Run Wang, Chaoyi Zhou, Xi Liu +7
Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model.…
Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning
Qiaoyi Yang, Chaoyi Zhou, Xi Liu +9
Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and large-scale geographic mappin…
FlexMap: Robust HD Map Construction under Flexible Camera Configurations
Run Wang, Chaoyi Zhou, Amir Salarpour +5
High-definition (HD) maps provide essential semantic information about road structures for autonomous driving, but existing HD map construction methods typically require calibrated…