Search papers, labs, and topics across Lattice.
6
0
8
13
A self-evolving memory paradigm for generative recommendation is proposed, aiming to enable effective evolution across heterogeneous behavioral patterns, and three key principles for effective self-evolving recommendation systems are identified, including isolated memorization, reinforced evolution, and scalable application.
Game solvers can teach LLMs how to make better decisions in long-horizon tasks by providing actionable turn-level feedback, leading to superior performance in complex environments.
Agent-as-a-Judge can outperform LLM-as-a-Judge in complex environments, but still struggles to reliably verify agent behavior, revealing a critical gap in current LLM-based agent evaluation.
Despite users preferring human-created videos, AI-generated content can achieve similar overall engagement on video platforms by flooding the system with sheer volume.
Generative AI could revolutionize video advertising by enabling real-time personalized creative generation, moving beyond the limitations of static, pre-produced ad inventories.
Generative recommendation gets a confidence boost: UGR leverages uncertainty to stabilize training, improve performance, and unlock risk-aware applications.
