Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published 11 days ago • 117
GMorgulis/Qwen2.5-7B-Instruct-cat_lora_sgd_lr1e-3-STEER0.910937-ft4.42 Text Generation • 8B • Updated 10 days ago • 28 • 1
electricsheepeurope/europe-owid-death-rate-from-cancer-by-sex Viewer • Updated 10 days ago • 2.05k • 61 • 1
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 17 days ago • 192
stefanocarrera/autophagycode_D_he_train-mercury_Qwen3-8B_strategy_trust_t1.25_g7_run0 Viewer • Updated 17 days ago • 164 • 115 • 2
CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage Paper • 2605.15597 • Published 30 days ago • 11
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining Paper • 2605.14747 • Published about 1 month ago • 145
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 195
GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs Paper • 2605.10762 • Published May 11 • 3