Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
3
3
7
3
The DeepSeek-V4.1-Flash model, a multimodal Mixture-of-Experts model with 552B backbone parameters and support for contexts of up to one million tokens, is introduced, substantially improving cost efficiency for agentic workloads and pushing the limits of KV cache compression.
Even without retraining, a simple dual-system approach can significantly boost the performance of self-supervised talking head forgery detectors by refining the ordering of uncertain samples.
Existing synthetic image detectors fail to generalize because they're trained on biased data, but HiMix overcomes this with artifact-aware representations and mixup augmentation, achieving state-of-the-art generalization to unseen generators.