Yizhi LI

ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding

YuE: Scaling Open Foundation Models for Long-Form Music Generation

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

First return, entropy-eliciting explore

MuPT: A Generative Symbolic Music Pretrained Transformer

Bridging the Data Provenance Gap Across Text, Speech, and Video

LIME: LESS IS MORE FOR MLLM EVALUATION

OmniBench: Towards The Future of Universal Omni-Language Models

MIO: A Foundation Model on Multimodal Tokens