Showing 1–15 of 15 results
/ Date/ Name
Sep 22, 2025Generalizable End-to-End Tool-Use RL with Synthetic CodeGymAug 12, 2025Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build EnvironmentsApr 10, 2025Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement LearningJan 5, 2025ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool UseDec 7, 2022ViTPose++: Vision Transformer for Generic Body Pose EstimationNov 3, 2022Rethinking Hierarchies in Pre-trained Plain Vision TransformerJun 23, 2022CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal PoseJun 12, 2022APT-36K: A Large-scale Benchmark for Animal Pose Estimation and TrackingApr 26, 2022ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationApr 18, 2022VSA: Learning Varied-Size Window Attention in Vision TransformersFeb 21, 2022ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and BeyondNov 24, 2021RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?Aug 28, 2021AP-10K: A Benchmark for Animal Pose Estimation in the WildAug 20, 2021Out-of-boundary View Synthesis Towards Full-Frame Video StabilizationNov 30, 2020DUT: Learning Video Stabilization by Simply Watching Unstable Videos