The PokeAgent Challenge: Competitive and Long-Context Learning at Scale Paper β’ 2603.15563 β’ Published Mar 16 β’ 10
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation Paper β’ 2603.16871 β’ Published Mar 17 β’ 60
VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent Collaboration Paper β’ 2602.04587 β’ Published Feb 4
CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents Paper β’ 2511.20216 β’ Published Nov 25, 2025
Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification Paper β’ 2507.11004 β’ Published Jul 15, 2025 β’ 1
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI Paper β’ 2510.05684 β’ Published Oct 7, 2025 β’ 146
Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks Paper β’ 2505.11881 β’ Published May 17, 2025 β’ 4