Search papers, labs, and topics across Lattice.
6
0
7
2
CRPO effectively mitigates exposure bias in self-distillation, leading to superior performance in complex reasoning tasks.
Process evaluations reveal hidden failures in LLM reasoning, showing that lucky successes can mask critical deficiencies in agent performance.
Memory isolation fails to protect user data in LLM agents, as demonstrated by the SPORE attack, which achieves an 80% extraction rate even with limited triggers.
PhaseAware reduces rehabilitation scoring error by nearly 89% while providing interpretable cues for clinician review, bridging automation and human oversight.
Visual aimbots can be effectively countered with a system that achieves over 85% success in real-time defense while maintaining negligible overhead.
Forget brittle orchestration layers – LLMs can internalize complex reasoning as a learnable "HeavySkill" that rivals external agentic frameworks.
