Search papers, labs, and topics across Lattice.
PayPal
7
0
11
PACE achieves a flawless safety record in DeFi transactions, eliminating unsafe executions while leveraging LLMs for complex financial operations.
Traditional loss functions can silently degrade recommendation quality, but the new Cardinality-Decomposed Loss reveals how to optimize for diverse relational structures effectively.
Rhetor achieves near-perfect synchronization in live software demos, enabling real-time voice interaction that adapts dynamically to user questions.
StateGen achieves a remarkable 9.66/10 score in tool-call hallucination reduction, setting a new standard for synthetic data generation in multi-agent LLM training.
LLMs can slash token usage by 80% and "thinking rate" by 95% without sacrificing accuracy, simply by learning when *not* to reason.
Ditch the deterministic databases: this LLM-driven simulation framework evaluates tool-calling agents with surprisingly reliable proxy states, offering a scalable alternative to costly benchmarks.
LLM agents blindly trust third-party tools, but MCPShield adds a "security cognition" layer that learns to spot malicious servers before they can do damage.
