Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
This work proposes Vid-PRE (Video Prompt Reasoner and Enhancer), a model-agnostic prompt rewriter that offloads the cognitive burden of reasoning to a dedicated VLM, and introduces VWG-Bench, a comprehensive benchmark spanning 9 reasoning dimensions and 38 fine-grained tasks.
Mainstream video models consistently falter in fine-grained understanding, revealing critical vulnerabilities in their hallucination capabilities.
Discovering exploitable library vulnerabilities in client code doesn't require proof-of-concept exploits anymore, thanks to a new fuzzing technique.
