We have 3 of 22 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
ForkLeft, a distillation framework that resolves a fundamental mismatch between autoregressive teacher predicts from a left prefix and NTP teacher under the same context, is introduced, showing that DLMs can learn NTP-style reasoning without sacrificing native parallel generation.
From the same cold start, prompt pool, and budget, CounterCredit reaches 89.5% on V*, 80.2% on HR-Bench-4K, and 76.4% on HR-Bench-8K, and raises the spurious-call rate to 31% to 36%, the lowest among the agents evaluated.
TransMem is proposed, a lightweight inference-time parametric memory module that transforms sparse historical hidden states from a frozen LLM backbone into reusable memory representations and introduces evidence-conditioned self-distillation to learn transferable memory utilization rather than task-specific knowledge.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
