CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark Paper β’ 2401.11944 β’ Published Jan 22 β’ 27
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval Paper β’ 2401.13478 β’ Published Jan 24 β’ 1
PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents Paper β’ 2406.13923 β’ Published Jun 20 β’ 21
MMRA: A Benchmark for Multi-granularity Multi-image Relational Association Paper β’ 2407.17379 β’ Published Jul 24 β’ 2
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment Paper β’ 2410.13785 β’ Published Oct 17 β’ 18
OmniBench: Towards The Future of Universal Omni-Language Models Paper β’ 2409.15272 β’ Published Sep 23 β’ 26
Chinese Open Instruction Generalist: A Preliminary Release Paper β’ 2304.07987 β’ Published Apr 17, 2023 β’ 2
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training Paper β’ 2306.00107 β’ Published May 31, 2023 β’ 3
CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark Paper β’ 2401.11944 β’ Published Jan 22 β’ 27
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval Paper β’ 2401.13478 β’ Published Jan 24 β’ 1
ChatMusician: Understanding and Generating Music Intrinsically with LLM Paper β’ 2402.16153 β’ Published Feb 25 β’ 56
MuPT: A Generative Symbolic Music Pretrained Transformer Paper β’ 2404.06393 β’ Published Apr 9 β’ 14