Search papers, labs, and topics across Lattice.
Affiliation:
8
0
14
Current state-of-the-art world models struggle to maintain spatial consistency and reliable state evolution over long-horizon interactions, as revealed by the new PlayWorld benchmark.
TELLER achieves over 80% trace length reduction while maintaining high diagnostic accuracy, revolutionizing root-cause analysis for LLM inference.
Mobile agents can now navigate complex GUIs with unprecedented efficiency, thanks to a novel data-environment co-scaling framework.
Task success rates for agentic phone use soar from 36.67% to 45.33% through a novel combination of real and mock environments in training.
Achieving superior accuracy-efficiency trade-offs, ParetoPO redefines how tool-integrated agents can be optimized for real-world applications.
Reliable phone automation hinges on mixed-action capabilities, with agents achieving a 75% success rate in real-world workflows.
Attention-guided denoising can dramatically enhance reasoning performance in diffusion language models, outperforming traditional post-training methods.
Current agents are alarmingly susceptible to skill-based attacks, with success rates reaching over 86%, exposing a critical vulnerability in AI safety.
