MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Paper • 2510.08540 • Published 5 days ago • 102
SPARK: Synergistic Policy And Reward Co-Evolving Framework Paper • 2509.22624 • Published 18 days ago • 16
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning Paper • 2509.22647 • Published 18 days ago • 31
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning Paper • 2509.22647 • Published 18 days ago • 31 • 2
SIM-CoT: Supervised Implicit Chain-of-Thought Collection Official checkpoint repository of "SIM-CoT: Supervised Implicit Chain-of-Thought" • 6 items • Updated 17 days ago • 2
CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning Paper • 2508.20096 • Published Aug 27 • 36
Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity Paper • 2508.05609 • Published Aug 7 • 29
SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience Paper • 2508.04700 • Published Aug 6 • 52
Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models Paper • 2508.00819 • Published Aug 1 • 62
SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction Paper • 2507.15852 • Published Jul 21 • 38
ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Paper • 2506.19848 • Published Jun 24 • 26