Persona Dosing: Calibrated Activation Steering for Graded Trait Control Paper • 2609.36388 • Published 11 days ago • 54
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL Paper • 2609.37200 • Published 10 days ago • 138
Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue Paper • 2609.31948 • Published 14 days ago • 89
gradients-io-tournaments/tournament-exp-s1-1f57709d-e05a-4105-8247-9cde3d6d3889-5Exp9668 1B • Updated 28 days ago • 23 • 1
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published about 1 month ago • 328
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published Sep 1 • 569
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published Aug 26 • 60
TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting Paper • 2607.28261 • Published Jul 30 • 18