DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations Paper • 2607.19865 • Published 8 days ago • 9
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists Paper • 2607.11079 • Published 17 days ago • 10
PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection Paper • 2607.04690 • Published 24 days ago • 3
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published Jun 15 • 177
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models Paper • 2606.11324 • Published Jun 9 • 172
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published Jun 11 • 113
AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification Paper • 2606.03031 • Published Jun 2 • 6
Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models Paper • 2605.24053 • Published May 22 • 5