4 papers
Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning
Rujie Wu, Haozhe Zhao, Hai Ci +1
Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is highly uneven. We present Goal-…
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Meituan LongCat Team, Bin Xiao, Chao Wang +86
The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal syste…
NEP: Autoregressive Image Editing via Next Editing Token Prediction
Huimin Wu, Xiaojian Ma, Haozhe Zhao +2
Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approach…
LongViTU: Instruction Tuning for Long-Form Video Understanding
Rujie Wu, Xiaojian Ma, Hai Ci +5
This paper introduces LongViTU, a large-scale (~121k QA pairs, ~900h videos), automatically generated dataset for long-form video understanding. We propose a systematic approach th…