When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models Paper • 2609.19671 • Published 8 days ago • 50
Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection Paper • 2609.07670 • Published 18 days ago • 18
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration Paper • 2609.01072 • Published 23 days ago • 13
TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity Paper • 2608.15767 • Published Aug 16 • 9
Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion Paper • 2608.13947 • Published Aug 14 • 15
How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review Paper • 2608.08975 • Published Aug 10 • 48
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 265
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF Image-Text-to-Text • 27B • Updated 8 days ago • 709k • 2.38k