PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces Paper • 2610.15208 • Published 12 days ago • 8
PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos Paper • 2609.38377 • Published 23 days ago • 17
S-Space: Exploring Spatial Workspace in Multimodal Language Models Paper • 2610.13527 • Published 12 days ago • 271
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 14 days ago • 244
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering Paper • 2607.28568 • Published Jul 30 • 193
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories Paper • 2606.11176 • Published Jun 9 • 134
Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization Paper • 2604.12290 • Published Apr 14 • 17