V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning Paper • 2603.14482 • Published Mar 15 • 36
CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production Paper • 2603.01973 • Published Mar 2 • 7
Detecting Hallucinated Content in Conditional Neural Sequence Generation Paper • 2011.02593 • Published Nov 5, 2020
Improving Chain-of-Thought Efficiency for Autoregressive Image Generation Paper • 2510.05593 • Published Oct 7, 2025
TV2TV: A Unified Framework for Interleaved Language and Video Generation Paper • 2512.05103 • Published Dec 4, 2025 • 20
Bridging Offline and Online Reinforcement Learning for LLMs Paper • 2506.21495 • Published Jun 26, 2025 • 3
CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks Paper • 2507.23751 • Published Jul 31, 2025 • 4
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs Paper • 2508.13141 • Published Aug 18, 2025
SPICE: Self-Play In Corpus Environments Improves Reasoning Paper • 2510.24684 • Published Oct 28, 2025 • 18
Jointly Reinforcing Diversity and Quality in Language Model Generations Paper • 2509.02534 • Published Sep 2, 2025 • 25