CLVR framework adds closed-loop visual verification, proxy prompt reinforcement learning, and delta-space weight merge to improve complex text-to-image generation over single-step or unverified multi-step baselines.
The effective rank: A measure of effective dimensionality
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
CeRA overcomes LoRA's linear ceiling by injecting non-linear SiLU gating and dropout, outperforming high-rank LoRA on complex math reasoning with 1/8 the parameters.
citing papers explorer
-
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
CLVR framework adds closed-loop visual verification, proxy prompt reinforcement learning, and delta-space weight merge to improve complex text-to-image generation over single-step or unverified multi-step baselines.
-
CeRA: Overcoming the Linear Ceiling of Low-Rank Adaptation via Capacity Expansion
CeRA overcomes LoRA's linear ceiling by injecting non-linear SiLU gating and dropout, outperforming high-rank LoRA on complex math reasoning with 1/8 the parameters.
- From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers