Search papers, labs, and topics across Lattice.
4
0
8
4
Current video generation models struggle with visual reasoning, achieving only 51% accuracy on a new benchmark designed to probe their capabilities.
Coding agents are alarmingly susceptible to malicious skill files, with exploitation rates exceeding 95% in some cases.
Agents can now make more accurate decisions by effectively compressing multimodal memory, closing the gap with human performance in complex environments.
Despite impressive visual fidelity, today's generative models still stumble on basic physical, causal, and spatial reasoning tasks, revealing a "logical desert" beneath the surface.
