Latency In CS.AI Papers

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 21 papers for Latency In CS.AI Papers. Dominant protocol signals include automatic metrics, simulation environments, with frequent benchmark focus on Retrieval, BrowseComp and metric focus on latency, accuracy. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.

Top Papers Reporting This Metric

• Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

  Pengxiang Li, Dilxat Muhtar, Lu Yin, Tianlong Chen, Shiwei Liu · Feb 26, 2026

  Automatic Metrics MathMedicine

  Across math reasoning benchmarks, NAP yields stronger performance under parallel decoding than DLMs trained on standard long CoT data, with gains growing as parallelism increases.

• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching

  Roy Miles, Aysim Toker, Andreea-Maria Oncescu, Songcen Xu, Jiankang Deng · Feb 26, 2026

  Automatic Metrics MathCoding

  This modular pipeline separates exploration (diffusion) from evaluation and solution synthesis, avoiding monolithic unified hybrids while preserving broad search.

• Ruyi2 Technical Report

  Huan Song, Shuyu Tian, Junyi Hao, Minxiu Xu, Hongjun An · Feb 26, 2026

  Automatic Metrics General

  Large Language Models (LLMs) face significant challenges regarding deployment costs and latency, necessitating adaptive computing strategies.

• SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents

  Patrick Tser Jern Kon, Archana Pradeep, Ang Chen, Alexander P. Ellis, Warren Hunt · Feb 25, 2026

  Automatic Metrics Coding

  Our approach combines supervised fine-tuning on expert-augmented trajectories with agentic reinforcement learning that explicitly discourages degenerative looping and unproductive expert collaboration.

• Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training

  Anas Barakat, Souradip Chakraborty, Khushbu Pahwa, Amrit Singh Bedi · Feb 24, 2026

  Automatic Metrics MathCoding

  Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning.

• HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG

  Yuqi Huang, Ning Liao, Kai Yang, Anning Hu, Shengchao Hu · Feb 24, 2026

  Automatic Metrics General

  Extensive experiments demonstrate that HELP achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$\times$ speedup over leading Graph-based RAG baselines.

• CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference

  Chao Fei, Guozhong Li, Chenxi Liu, Panos Kalnis · Feb 24, 2026

  Automatic Metrics Coding

  Extensive evaluations demonstrate that CHESS surpasses Full-KV quality using only \textbf{1\%} of the KV cache, delivers low-latency stable inference with up to \textbf{4.56$\times$} higher throughput, and consistently outperforms other str

• Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference

  Arindam Khaled · Feb 23, 2026

  Automatic Metrics Math

  In this work, we propose "Pyramid MoA", a hierarchical Mixture-of-Agents architecture that uses a lightweight Router to dynamically escalate queries only when necessary.

• Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations

  Dongming Jiang, Yi Li, Songtao Wei, Jinxin Yang, Ayushi Kishore · Feb 22, 2026

  Automatic Metrics General

  Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows.

• Luna-2: Scalable Single-Token Evaluation with Small Language Models

  Vatsal Goel, Rishon Dsouza, Nikhil Ega, Amey Ramesh Rambatla, Rob Friel · Feb 20, 2026

  Automatic Metrics Coding

  Real-time guardrails require evaluation that is accurate, cheap, and fast - yet today's default, LLM-as-a-judge (LLMAJ), is slow, expensive, and operationally non-deterministic due to multi-token generation.

• From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design

  Sha Li, Stefano Petrangeli, Yu Shen, Xiang Chen · Feb 14, 2026

  Simulation Env Coding

  We introduce LaySPA, a reinforcement learning framework that equips large language models (LLMs) with explicit and interpretable spatial reasoning for content-aware graphic layout design.

• Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

  Lai Wei, Liangbo He, Jun Lan, Lingzhong Dong, Yutong Cai · Feb 12, 2026

  Automatic Metrics Coding

  To address this, we propose Region-to-Image Distillation, which transforms zooming from an inference-time tool into a training-time primitive, thereby internalizing the benefits of agentic zooming into a single forward pass of an MLLM.

• Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

  Ailin Huang, Ang Li, Aobo Kong, Bin Wang, Binxing Jiao · Feb 11, 2026

  Simulation Env MathCoding

  We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency.

• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering

  Yuzhu Cai, Zexi Liu, Xinyu Zhu, Cheng Wang, Siheng Chen · Feb 8, 2026

  Automatic Metrics Coding

  Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons.

• Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

  Chi-Pin Huang, Yunze Man, Zhiding Yu, Min-Hung Chen, Jan Kautz · Jan 14, 2026

  Simulation Env General

  Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher, driven by a preference-guided objective to align manipulation trajectories that transfers both linguistic and visual planning capabilities for embodie

• Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

  Jon Saad-Falcon, Avanika Narayan, Hakki Orhun Akengin, J. Wes Griffin, Herumb Shandilya · Nov 11, 2025

  Automatic Metrics General

  Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure.

• OckBench: Measuring the Efficiency of LLM Reasoning

  Zheng Du, Hao Kang, Song Han, Tushar Krishna, Ligeng Zhu · Nov 7, 2025

  Automatic Metrics Coding

  Yet current benchmarks emphasize accuracy and output quality, neglecting a critical dimension: efficiency of token usage.

• RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA

  Ruiyi Yang, Hao Xue, Imran Razzak, Hakim Hacid, Flora D. Salim · Oct 23, 2025

  Automatic Metrics General

  A Head Agent provides guidance that leads retrieval, while an Iteration Agent selects and expands HSeq via structure-respecting actions (e.g., parent/child hops, table row/column neighbors, KG relations); Finally the head agent composes can

• On the Inference (In-)Security of Vertical Federated Learning: Efficient Auditing against Inference Tampering Attack

  Chung-ju Huang, Ziqi Zhang, Yinggui Wang, Binghui Wang, Tao Wei · Jul 3, 2025

  Automatic MetricsSimulation Env General

  Vertical Federated Learning (VFL) is an emerging distributed learning paradigm for cross-silo collaboration without accessing participants' data.

• $\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts

  Mert Cemri, Nived Rajaraman, Rishabh Tiwari, Xiaoxuan Liu, Kurt Keutzer · Jun 15, 2025

  Automatic Metrics Math

  Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration.

• Intermittent Semi-Working Mask: A New Masking Paradigm for LLMs

  HaoYuan Hu, Mingcong Lu, Di Luo, XinYa Wu, Jiangcai Zhu · Aug 1, 2024

  Automatic Metrics Math

  Across extensive evaluations, ISM outperforms causal baselines not only on multi-turn dialogue, but also on context-intensive tasks like mathematical reasoning.

Other Metric Hubs