Search papers, labs, and topics across Lattice.
3
0
6
1
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.
Deobfuscation just got a whole lot easier: PUSHAN cracks virtualization-obfuscated binaries without relying on brittle trace analysis or expensive symbolic execution.
A surprisingly simple autoregressive model rivals specialized architectures in multi-modal understanding, generation, and editing.
