distribution-aware

This paper introduces a distribution-aware, prediction-free scheduling framework for LLM inference that replaces explicit length prediction with soft priority boosting using statistical signals. The method co-optimizes scheduling and cache-aware preemption to reduce tail latency, achieving up to 35-50% reduction in P99 TTLT compared to SRPT with perfect length knowledge.

This paper proposes DARS, a framework that constructs routing supervision from a distributional view of model behavior to address the unreliability of single-shot labels in LLM routing.

This paper introduces CurveRL, a principled distribution-aware prompt reweighting approach for reinforcement learning with verifiable rewards (RLVR) that improves LLM reasoning by assigning weights based on the rank and density of pass rates rather than their absolute values, consistently outperforming GRPO and other baselines.

This paper introduces a framework for distribution-aware algorithm design where LLM agents learn to generate solver code specialized to target distributions, achieving high solution quality and significant speedups over standard solvers.

This paper introduces a distribution-aware reinforcement learning framework that enhances MLLM performance in long-tailed numerical regression tasks using batch-level comparison-based supervision.