Paper Decoupled Reward Normalization for Stable Multi‑Reward RL ▲ 74 • reinforcement-learning, efficiency • advanced
Design Thinking, MVP, Rapid Onboarding Transform Muller 1m • Unknown Channel • entrepreneurship • intermediate
Paper DiffThinker: Diffusion‑Based Generative Multimodal Reasoning ▲ 22 • multimodal, computer-vision, efficiency • advanced