Tag
SpatialCORE is a post-training framework that uses a model's confidence in its generated bounding-box grounding as a learning signal for spatial reasoning in large vision-language models, achieving state-of-the-art results among open-source models on spatial reasoning benchmarks.
Robust-TO addresses the Blind Trust Problem in video reasoning by integrating per-frame trustworthiness into an agentic framework, improving accuracy under realistic perturbations through calibrated evidence weighting and reliability-aware reasoning.
CONF-KV is a KV-cache management system that uses model uncertainty to dynamically adjust cache retention, improving memory efficiency for long-context LLM inference while maintaining accuracy within 1.5-2.1 perplexity points.