TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 5 days ago • 162
electricsheepafrica/africa-ghana-greater-accra-land-survey-reference-pillars-with-coordinat-b0a9eaa8 Viewer • Updated 5 days ago • 153 • 67 • 1
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering Paper • 2603.28583 • Published 10 days ago • 17
Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports Paper • 2606.28393 • Published Jun 23 • 6
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 252
On-Policy Adversarial Flow Distillation for Autoregressive Video Generation Paper • 2605.26105 • Published May 25 • 19
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation Paper • 2605.25874 • Published May 25 • 106
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 238