Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
3
3
6
0
Inspired by human cognition, CRCD reformulates the task as counterfactual latent change captioning to bypass affirmation bias, and contrasts a synthesized safe expectation with reality to identify semantic omissions.
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.
This work defines the task of safety as a highly pragmatic and critical cognitive dimension, and proposes the Cognitive Expected Scene Graph (CESG) Score, a structure-grounded, polarity-aware evaluation metric.