Search papers, labs, and topics across Lattice.
5
0
8
9
Princigram achieves a new standard in scientific diagram generation, ensuring physical accuracy through a structured reasoning framework that traditional models lack.
Sparse rewards can be effectively optimized without losing the advantages of fine-grained feedback through a novel two-stage training approach.
Even the best audio-video generators struggle with basic acoustic principles, revealing a critical gap in their performance.
Visual reasoning in multimodal models is highly variable, with accuracy plummeting over 10 points when feedback is corrupted, revealing hidden dependencies on visual states.
Skill-SP not only pushes the performance ceiling of LLMs but also transforms initially misaligned models into high-performing agents through dynamic skill evolution.
