Papers

• OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment (2026)
  Ming Zhang et al.
  6.91
• Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training (2026)
  Yiwei Qin et al.
  1.94
• Function2Scene: 3D Indoor Scene Layout from Functional Specifications (2026)
  Ruiqi Wang et al.
  1.89
• 2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining (2025)
  Wenqi Zhang et al.
  1.28
• Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers (2025)
  Daniel D'souza et al.
  1.28
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations (2023)
  Hakan Inan et al.
  —
• DeepSeek-VL: Towards Real-World Vision-Language Understanding (2024)
  Haoyu Lu et al.
  —
• Are We Done with MMLU? (2024)
  Aryo Pradipta Gema et al.
  —
• MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding (2024)
  Xinyu Fang et al.
  —