DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos Paper • 2602.06949 • Published Feb 6 • 35
SWE-Universe: Scale Real-World Verifiable Environments to Millions Paper • 2602.02361 • Published Feb 2 • 60
daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently Paper • 2602.02619 • Published Feb 2 • 50
PaperBanana: Automating Academic Illustration for AI Scientists Paper • 2601.23265 • Published Jan 30 • 218
SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents Paper • 2601.16746 • Published Jan 23 • 89
daVinci-Dev: Agent-native Mid-training for Software Engineering Paper • 2601.18418 • Published Jan 26 • 126
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts Paper • 2601.11044 • Published Jan 16 • 34
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation Paper • 2512.23576 • Published Dec 29, 2025 • 65
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling Paper • 2506.20512 • Published Jun 25, 2025 • 47