Paper Trail
Search
Search
Dark mode
Light mode
Explorer
Tag: huawei
6 items with this tag.
Mar 18, 2026
T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation
paper
reward-model
hku
tsinghua
huawei
modality/image
modality/text
Mar 18, 2026
VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video Understanding
paper
reward-model
ustc
huawei
modality/video
modality/text
Mar 18, 2026
EMMA: Efficient Visual Alignment in Multi-Modal LLMs
paper
understanding-generation
multimodal
huawei
Mar 18, 2026
ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance
paper
understanding-generation
huawei
Mar 18, 2026
ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
paper
understanding-generation
huawei
Mar 05, 2026
2025-03 DualToken
paper
computer-vision
nlp
multimodal
huawei