Search papers, labs, and topics across Lattice.
6
1
10
8
LLMs struggle to navigate the complex, multi-turn justification and response dynamics of real-world patent examination, revealing critical gaps in legal reasoning and technical novelty judgment.
Today's best multimodal agents still fall into "blind execution" traps when building websites from ambiguous, non-expert user instructions, highlighting a critical gap in intent recognition and adaptive interaction.
Optimal Transport offers a surprisingly effective and theoretically grounded approach to preference learning, outperforming existing methods in aligning LLMs with human values and reasoning abilities.
Escape the echo chamber: FlowPIE's flow-guided literature exploration and evolutionary idea generation produces more novel, feasible, and diverse scientific ideas than static retrieval-based LLMs.
Current LLMs struggle with biologically complex tasks in single-cell biology, particularly those requiring mechanistic or causal understanding, highlighting the need for more biology-aligned foundation models.
ToolRMs drastically improve tool-use accuracy in LLMs, outperforming existing models by up to 17.94%, while also reducing output token usage by over 66% through efficient inference-time scaling.
