3 papers
cs.LG2026
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams
Cong Wan, Zeyu Guo, Zijian Cai +6
Raw multimodal streams are abundant but noisy, redundant, and unaligned with any particular training objective. Turning them into supervision today means either brittle heuristics…
cs.CV2026
CoRe: A Comprehensive Framework for Cross-Image Comparative Reasoning in Vision-Language Models
Lin Peng, Cong Wan, Zeyu Guo +2
Cross-image comparative reasoning remains challenging for vision-language models (VLMs), especially when correct prediction requires fine-grained attribute grounding and globally c…
cs.CV2026
ReMoT: Reinforcement Learning with Motion Contrast Triplets
Cong Wan, Zeyu Guo, Jiangyang Li +5
We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency -- a critical failure point in navigatio…