Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization Paper • 2607.10169 • Published 27 days ago • 14
Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget Paper • 2607.13125 • Published 20 days ago • 138
Steve0927/qwen3-embedding-0.6b-lrat-trajectory-graph-adjudicated-positive-expansion-v1 0.6B • Updated 19 days ago • 23 • 1
Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue Paper • 2606.31719 • Published Jun 30 • 7
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising Paper • 2606.30968 • Published Jun 29 • 28
InterleaveThinker: Reinforcing Agentic Interleaved Generation Paper • 2606.13679 • Published Jun 11 • 84
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 253
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents Paper • 2605.22608 • Published May 21 • 8
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm Paper • 2604.20665 • Published May 21 • 7