Search papers, labs, and topics across Lattice.
6
0
12
5
Multimodal unlearning could revolutionize how we handle sensitive data in AI, enabling targeted removal without sacrificing model performance.
Transforming off-policy tokens into on-policy ones could be the key to unlocking more robust and efficient alignment for large language models.
Fingerprint spoofing allows adversarial providers to masquerade weak models as premium LLMs, undermining user trust in model verification processes.
Stop retraining your diffusion models for every device: OFA-Diffusion lets you extract the right-sized model in a single training run.
K-means, previously relegated to offline processing, gets a 17.9x speed boost on modern GPUs thanks to Flash-KMeans' clever IO and contention optimizations.
Models are substantially better at pairwise self-verification than independent scoring, unlocking a more efficient and accurate approach to test-time scaling for complex reasoning.
