Search papers, labs, and topics across Lattice.
2
0
6
6
Projector fine-tuning, commonly used for aligning MLLMs, unexpectedly introduces backdoor vulnerabilities with activation mechanisms distinct from those in text-only LLMs.
Test-time training can finally scale for large reasoning models: TEMPO unlocks sustained performance gains by interleaving policy refinement with periodic critic recalibration, boosting accuracy by over 18% on challenging benchmarks.
