Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
4
3
7
4
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.
FedHUR is a federated recommendation framework for learning hierarchical utility-guided client relations that consistently outperforms existing federated recommendation baselines, demonstrating the effectiveness of hierarchical utility-guided client relation learning.
TetherMem enables video generation models to dynamically adapt scenes while keeping subjects consistent, achieving a significant leap in overall video quality and scene progression.
ID-LoRA slashes trainable parameters by up to 46% compared to standard LoRA while boosting performance across diverse benchmarks, offering a sweet spot between efficiency and effectiveness for fine-tuning LLMs.