Search papers, labs, and topics across Lattice.
Affiliation:
7
0
10
4
Event-centric memory can boost long-video QA accuracy by over 3 points while slashing inference costs by nearly 64%.
Cognitive traps in LLM memory can lead to over 10% performance degradation, challenging the assumption that more memory always improves reasoning.
Users can now have a personal AI that remembers and retrieves daily experiences seamlessly, enhancing everyday assistance like never before.
TokenPilot slashes inference costs by up to 87% without sacrificing performance, tackling the critical trade-off between context management and cache efficiency in LLM agents.
LLM agents can achieve state-of-the-art performance in dynamic environments by treating memory as a continuously evolving graph, rather than a static repository.
LLM memory failures are systematic, stemming from operation-level issues like information loss and retrieval misalignment, and can be automatically corrected with prompt optimization guided by fine-grained error tracing.
LLMs can now reason across long conversations without breaking the bank: StructMem slashes token usage and API calls while boosting temporal reasoning.
