Miles Yang
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Vision×2
Frequent co-authors
Research Timeline
2026
GEAR: Guided End-to-End AutoRegression for Image Synthesis
This paper introduces GEAR, a method for training a vector-quantized tokenizer and an autoregressive generator jointly and end-to-end, resolving the issue of non-differentiable VQ indices.
Twins: Learn to Predict Unified Representations with Focal Loss
This paper proposes Twins, a unified continuous token space for multimodal models using ViT and VAE features, and addresses optimization imbalance with a focal regression objective.
Highlighted terms show continued research focus across papers
Papers
cs.CVEmpiricalRecentJul 24, 2026
Twins: Learn to Predict Unified Representations with Focal Loss
Kaixiong Gong, Xin Cai, Bin Lin, Hao Wang +8 more
This paper proposes Twins, a unified continuous token space for multimodal models using ViT and VAE features, and addresses optimization imbalance with a focal regression objective.
View →
cs.CVEmpiricalRecent