3 papers
cs.RO2026
Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models
Meng Zheng, Samhita Marri, Anwesa Choudhuri +6
Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral cloning leaves them brittle; lacki…
cs.CV2026
SPOT: Contrast-Driven Face Occlusion Segmentation via Self-Supervised Prompt Learning
Lingsong Wang, Mancheng Meng, Ziyan Wu +3
Existing face parsing methods usually misclassify occlusions as facial components. This is because occlusion is a high-level concept, it does not refer to a concrete category of ob…
cs.AI2025
BlueLM-2.5-3B Technical Report
Baojiao Xiong, Boheng Chen, Chengzhi Wang +58
We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reas…