Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
5
3
10
5
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.
Most test-time adaptations in vision-language models are either redundant or actively destructive—and skipping up to 85% of them via simple consistency checks actually boosts final accuracy.
Eliciting confidence at multiple stages reveals that the final retrieval step's uncertainty signal can dramatically enhance the reliability of AI-generated answers.
LLMs, like humans, exhibit a "frequency bias," performing better when prompted and fine-tuned with more common textual expressions.