FATE reduces normalized makespan and P95 latency in real LLM workflow DAGs to 0.675 and 0.677 by jointly preserving multiple future execution states, outperforming RoundRobin by 32.5% and the strongest baseline by 8.9%.
Sglang: Efficient execution of structured language model programs.Advances in neural information processing systems, 37: 62557–62583
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 6roles
other 1polarities
unclear 1representative citing papers
Mu-GRPO enables substantially more off-policy GRPO training for LLMs via relaxed clipping and negative-advantage veto in large staged batches, matching standard GRPO performance at ~2x training speed.
MILM fine-tunes LLMs on XML-encoded multimodal irregular time series via a two-stage process that exploits informative sampling patterns to achieve top performance on EHR classification datasets.
SceneGraphVLM generates dynamic scene graphs from video using compact VLMs, TOON serialization, and hallucination-aware RL to improve precision and achieve one-second latency.
RRCM trains an LLM to dynamically retrieve from collaborative and meta memories using group relative policy optimization driven by final top-k recommendation quality.
PBKV predicts agent invocations in dynamic LLM workflows to manage KV-cache reuse, delivering up to 1.85x speedup over LRU and 1.26x over KVFlow.
citing papers explorer
-
FATE: Future-State-Aware Scheduling for Heterogeneous LLM Workflows
FATE reduces normalized makespan and P95 latency in real LLM workflow DAGs to 0.675 and 0.677 by jointly preserving multiple future execution states, outperforming RoundRobin by 32.5% and the strongest baseline by 8.9%.
-
How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning
Mu-GRPO enables substantially more off-policy GRPO training for LLMs via relaxed clipping and negative-advantage veto in large staged batches, matching standard GRPO performance at ~2x training speed.
-
MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling
MILM fine-tunes LLMs on XML-encoded multimodal irregular time series via a two-stage process that exploits informative sampling patterns to achieve top performance on EHR classification datasets.
-
SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models
SceneGraphVLM generates dynamic scene graphs from video using compact VLMs, TOON serialization, and hallucination-aware RL to improve precision and achieve one-second latency.
-
RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
RRCM trains an LLM to dynamically retrieve from collaborative and meta memories using group relative policy optimization driven by final top-k recommendation quality.
-
Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management
PBKV predicts agent invocations in dynamic LLM workflows to manage KV-cache reuse, delivering up to 1.85x speedup over LRU and 1.26x over KVFlow.