Search papers, labs, and topics across Lattice.
7
1
10
15
Organized memory can halve retrieval costs, but without a strong management agent, LLMs struggle to maintain effective organization and answer quality.
Self-looping reasoning in LLMs can be effectively mitigated through targeted hidden-state interventions, leading to improved reasoning quality and efficiency.
AutoSIFT allows for precise control over speech styles, enabling users to modify attributes like emotion while preserving the nuanced prosody of the original voice.
LLM agents can be significantly improved by *removing* redundant and outdated skills from their skill banks, not just adding more.
LLMs are revolutionizing conversational AI research, and this survey offers a structured guide to navigating the rapidly evolving landscape of LLM-powered user simulation.
Rollout design in LLM reinforcement learning is more than just sampling trajectories – it's a modular pipeline you can optimize for reliability, coverage, and cost.
Existing music editing systems often compromise on preserving key musical elements, but MuseCPEval provides a robust framework to ensure these facets remain intact during editing.
