ProEval Cuts Benchmark Eval Samples 8-65x

Also Worth Noting

• ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation score 4
  机构: Google; 关键词(1): reasoning
• Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective score 4
  关键词(1): fine-tuning; 顶会接收: ACL
• Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search score 4
  关键词(2): lightweight, reasoning; 顶会接收: ACL
• Learning from Noisy Prompts: Saliency-Guided Prompt Distillation for Robust Segmentation with SAM score 4
  关键词(4): lightweight, distillation, deployment, reasoning; 顶会接收: CVPR
• Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection score 4
  关键词(1): vision-language; 顶会接收: CVPR
• One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition score 3
  顶会接收: CVPR
• MotionHiFlow: Text-to-motion via hierarchical flow matching score 3
  顶会接收: CVPR
• SemiGDA: Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentation score 3
  顶会接收: CVPR
• Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing score 3
  顶会接收: ACL