MixSD: Mixed Contextual Self-Distillation for Knowledge Injection Paper • 2605.16865 • Published 6 days ago • 5
HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization Paper • 2506.07972 • Published Jun 9, 2025 • 1
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance Paper • 2506.06444 • Published Jun 6, 2025 • 73