Neurosymbolic Framework for Interpretable Human Action Recognition
Discover a neurosymbolic framework enhancing skeleton-based human action recognition with logical reasoning for improved accuracy and interpretability.
Structural Rationale Distillation via Reasoning Compression
Discover how Distillation through Reasoning Path Compression (D-RPC) improves AI model training by enhancing rationale consistency and learning efficiency.
Adaptive Negative Reinforcement Boosts LLM Reasoning Accuracy
Discover how Adaptive Negative Sample Reinforcement enhances Large Language Models by balancing error correction and reasoning diversity in RLVR training.
Region4Web: Enhancing Web Agents with Functional Regions
Discover how Region4Web improves web agents by using functional region granularity for better page understanding and task success.
ChatGPT Adoption Growth in Early 2026: Key Trends
Discover how ChatGPT adoption surged in early 2026, driven by older users, improved features, and growing AI acceptance across demographics.