Tag
TRACE is a training-free framework that optimizes GUI agent efficiency by ranking visual evidence based on utility and diversity, reducing latency and memory usage through adaptive token management and KV contraction.
Set Diffusion introduces a new class of language models that interpolates between autoregressive and diffusion models by factorizing token generation over flexible-position, flexible-length token sets. This enables faster decoding and flexible token ordering, achieving better speed-quality tradeoffs on reasoning, summarization, and unconditional generation tasks.