Search papers, labs, and topics across Lattice.
Affiliation:, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences
3
0
7
20
Multi-Tool Image Editing Attribution reveals that existing methods fail to keep pace with the complexity of modern image edits, but a new approach can accurately identify multiple tools at work.
LLMs' own self-judgments, when logically linked to their response features, can significantly improve hallucination detection.
FactGuard's agentic framework substantially boosts video misinformation detection by strategically using external tools and reinforcement learning to overcome the inherent limitations of relying solely on internal MLLM reasoning.
