2 papers
cs.LG2026
ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration
Yuchen Bao, Chao Wen, Haowei Wang +10
Reward post-training of diffusion generators inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases within-prompt diversity. Existing m…
cs.CV2026
AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization
Yiyang Yao, Shanglin Liu, Jianming Lv +4
Contrastive Language-Image Pretraining learns a shared representation space through large-scale contrastive learning. However, existing methods that enforce global consistency regu…