KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues
First benchmark for evaluating multi-turn long-form question answering in knowledge-intensive domains.
Sep 26, 2025
Video Signature: In-generation Watermarking for Latent Video Diffusion Models
An in-generation watermarking method for latent video diffusion models, which enables implicit and adaptive watermark integration during generation.
May 31, 2025
Videomark: A distortion-free robust watermarking framework for video diffusion models
A distortion-free robust watermarking framework for video diffusion models.
Apr 23, 2025