Sample Complexity and Representation Ability of Test-time Scaling Paradigms
arXiv:2506.05295v1 Announce Type: cross Abstract: Test-time scaling paradigms have significantly advanced the capabilities of large language models (LLMs) on complex…
ProRefine: Inference-time Prompt Refinement with Textual Feedback
arXiv:2506.05305v1 Announce Type: cross Abstract: Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning,…
Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving
arXiv:2506.03568v2 Announce Type: replace-cross Abstract: Autonomous driving promises significant advancements in mobility, road safety and traffic efficiency, yet reinforcement learning…
Rectified Point Flow: Generic Point Cloud Pose Estimation
arXiv:2506.05282v1 Announce Type: cross Abstract: We introduce Rectified Point Flow, a unified parameterization that formulates pairwise point cloud registration and…
Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
arXiv:2504.18026v3 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) propose to enhance the trustworthiness of AI systems by constraining their…
