Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality Paper • 2509.23765 • Published Sep 28, 2025 • 2
MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment Paper • 2508.19527 • Published Aug 27, 2025 • 10
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning Paper • 2505.15400 • Published May 21, 2025 • 23
Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona Paper • 2305.11482 • Published May 19, 2023