2 papers
cs.CL2026
Reciprocal Co-Training (RCT): Coupling Gradient-Based and Non-Differentiable Models via Reinforcement Learning
Yunshuo Tian, Akayou Kitessa, Tanuja Chitnis +1
Language models (LMs) and classical machine learning methods offer complementary strengths for predictive modeling, yet their fundamentally different representations and training p…
cs.CV2026
Beyond Compression: Quantifying Spectral Accessibility in Vision Representations
Akayou A. Kitessa, Yijun Zhao
Vision-language models map visual features into a shared embedding space through learned projection layers, yet it remains unclear how these transformations alter the structure of…