Search papers, labs, and topics across Lattice.
6
0
7
VLMs struggle with raw medical data, achieving only a 48.6% success rate in standardization, revealing a critical gap in their clinical applicability.
Memory management emerges as a high-leverage skill that can double or quadruple the performance of LLMs in complex tasks without altering their core action behaviors.
Learning from failures can boost agent success rates by over 6% without extra training, reshaping how we approach agent improvement.
High artifact detection rates in VLMs mask significant failures in contextual understanding, with top models misidentifying visual cues in over 46% of cases.
ELBO-based reinforcement learning, previously dismissed for visual generation, can actually outperform MDP-based methods for aligning denoising generative models with human preferences.
MLLMs are surprisingly robust to catastrophic forgetting during fine-tuning, needing only simple regularization or data-hybrid training to maintain performance.
