Search papers, labs, and topics across Lattice.
6
0
9
0
ReOPD turns the costly process of agent-environment interaction into a reusable offline resource, achieving faster training while preserving accuracy.
LLMs struggle with Office automation, scoring only 36.6% on a standardized proficiency exam, revealing a critical gap in their capabilities.
Achieving up to 7.6x faster decoding and 17.1x greater throughput, CLSA redefines efficiency in long-context LLMs without compromising accuracy.
Forget scaling model size: RefineRL shows that incentivizing self-refinement in smaller LLMs lets them punch *way* above their weight, rivaling models 10x larger on competitive programming tasks.
By cleverly combining YOCO's efficient attention with recursive computation, YOCO-U achieves a capability-efficiency sweet spot that neither technique can reach on its own.
Language models can learn directly from real-world user interactions, boosting performance without human annotations or simulated environments.
