University of Texas at Austin · 9 records

dateidtitleauthorsvenue↑
2026-11-102611.10987Horizon-Scalable Q-LearningHaoran Xu et al.arXiv1
2026-11-012611.01860Advances in Agentic Computer GraphicsHengyu Liu et al.arXiv134
2026-10-072610.05954MEND: RL For Flow Models via Proximal Velocity MatchingShreshth Saini et al.arXiv3
2026-09-292609.32913Allspark: Weak to Strong Transfer via Alternating Chain of ThoughtKaizhao Liang et al.arXiv3
2026-08-142608.02870Maglev: Sliding Recurrent MemoryBo Liu et al.arXiv7
2026-07-222607.19331ISO: An RLVR-Native Optimization StackHanqing Zhu et al.arXiv7
2026-07-172607.14106Token Time Continuous Diffusion for Language ModelingParikshit Bansal et al.arXiv4
2026-06-232606.21777CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive TasksAshwin Vinod et al.arXiv5
2026-06-152606.13044No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only RevisionsXu Yang et al.arXiv10