Beyond Overparameterization: Provable Learning of Input-Convex Multi-Layer Polynomial Networks with Active Queries
Research
Research News
New papers, breakthroughs and academic AI research
CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs
Research
StageVLN: Spatial and Trajectory Auxiliary Guidance for Efficient Vision-Language Navigation
Research
Operational Abstractions of Neural Network Concepts via Topological Representations
Research
Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries
Research
Normality Constraint Learning: Adapting Foundation Models for Time Series Anomaly Detection
Research
AI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation
Research
Capability-Driven Self-Evolution of Agent Memory
Research
From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models
Research
DPNL: A DPLL-based Algorithm for Probabilistic Neurosymbolic Learning
Research
What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents
Research
CRAFTER: Causality-based Self-adaptation for Autonomous IoT Systems
Research