tihon-nth/vivit-vit-fc-loss-8-10-epochs-5_class_1_p0_full_splited-1789276477.0016897 Video Classification • 88.7M • Updated 5 days ago • 83 • 2
When Models Edit Too Much: On the Fidelity of Minimal Code Edits Paper • 2609.04061 • Published 16 days ago • 9
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling Paper • 2608.30821 • Published 19 days ago • 66
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published Aug 17 • 121
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Paper • 2608.16072 • Published Aug 17 • 50
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published Aug 10 • 176