Search papers, labs, and topics across Lattice.
4
0
6
ActSafeGuard is introduced, a differentiable and training-aligned safeguard layer for flow-matching based policies that integrates hard action feasibility into policy learning, not merely treating safety as an inference-time external component.
Transforming scientific papers into multi-turn generation trajectories not only doubles the training data but also boosts academic writing benchmarks while maintaining reasoning skills.
Even state-of-the-art MLLMs fail to accurately reconstruct academic documents, revealing a critical gap in machine understanding of scientific knowledge.
Hyper-M2RAG redefines multimodal retrieval by capturing complex relationships in a hypergraph structure, achieving superior performance with less computational overhead.
