Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper • 2511.04570 • Published Nov 6, 2025 • 239
Can Deep Research Agents Find and Organize? Evaluating the Synthesis Gap with Expert Taxonomies Paper • 2601.12369 • Published 30 days ago • 4
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Paper • 2601.14004 • Published 28 days ago • 46
OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment Paper • 2601.01576 • Published Jan 4 • 18
VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions Paper • 2509.09716 • Published Sep 9, 2025 • 12