Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning Paper • 2512.07461 • Published Dec 8, 2025 • 79
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis Paper • 2506.04142 • Published Jun 4, 2025 • 27
MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos Paper • 2506.04141 • Published Jun 4, 2025 • 30
