benchmark RWKU Benchmarking Real-World Knowledge Unlearning for Large Language Models. The dataset has been downloaded over 100,000 times on Hugging Face. Omni-RewardBench Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences. The first omni-modal RM benchmark with free-form preferences, covering nine tasks across five modalities including text, image, video, audio, and 3D MMR-V What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos. toolkit CogIE An Information Extraction Toolkit for Bridging Text and CogNet CogKGE A Knowledge Graph Embedding Toolkit and Benckmark for Representing Multi-source and Heterogeneous Knowledge CogKTR A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding
