Search papers, labs, and topics across Lattice.
Affiliation:
6
0
9
0
Resource-aware LLM task graphs can achieve competitive accuracy with 3.17x less cost and latency by jointly executing and verifying subtasks, learning LLM quality online.
Short-context models can achieve superior reasoning performance by leveraging long-context teacher models through innovative token alignment and training strategies.
The traditional linear correlation between language model perplexity and ASR word error rate breaks down in modern end-to-end systems, revealing the critical role of internal language modeling.
CHAUN achieves a remarkable 25.6% improvement in QINI scores, redefining the benchmarks for uplift modeling in the presence of unobserved confounding.
Action-conditioned world model embeddings can revolutionize failure detection in long-horizon robotic tasks, achieving reliable monitoring without dense annotations.
