Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Paper • 2609.19499 • Published 8 days ago • 37
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published 17 days ago • 372
Generative Late-Interaction Embeddings For Visual Document Retrieval Paper • 2609.11808 • Published 14 days ago • 27
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs Paper • 2609.11499 • Published 14 days ago • 33
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents Paper • 2609.09153 • Published 16 days ago • 42