Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler Video-to-Video • Updated about 1 month ago • 10.3k • 123
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published Aug 26 • 57
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 94
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities Paper • 2607.13705 • Published Jul 15 • 40
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models Paper • 2607.06442 • Published Jul 7 • 5