proprietary models
Proprietary models are proprietary AI systems or algorithms that are owned and controlled by a specific company or entity. These models are often kept confidential and may use unique methodologies that differentiate them from open models.
- BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
- CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models
- EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
- Panoptic Captioning: An Equivalence Bridge for Image and Text
- Position: Require Frontier AI Labs To Release Small "Analog" Models
- RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
- ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code
- Self-Refining Language Model Anonymizers via Adversarial Distillation
- SimpleStrat: Diversifying Language Model Generation with Stratification
- T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
- The Leaderboard Illusion
- Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
- Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
- WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch