Latency + Coding Metric Papers

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 20 papers for Latency + Coding Metric Papers. Dominant protocol signals include automatic metrics, simulation environments, with frequent benchmark focus on MATH, AIME 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.

• InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models

  Sayed Mohammadreza Tayaranian Hosseini, Amir Ardakani, Warren J. Gross · Feb 26, 2026

  Automatic Metrics MathCoding

  Our evaluation experiments on Llama models shows that InnerQ maintains a few-shot GSM8K performance comparable to non-quantized KV caches and surpasses prior KV cache quantization methods.

• 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.

• Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

  Zhengyang Su, Isay Katsman, Yueqi Wang, Ruining He, Lukasz Heldt · Feb 26, 2026

  Automatic Metrics Coding

  In addition, evaluation on academic benchmarks demonstrates that STATIC can considerably improve cold-start performance for generative retrieval.

• 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.

• HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders

  Kun Yuan, Junyu Bi, Daixuan Cheng, Changfa Wu, Shuwen Xiao · Feb 24, 2026

  Automatic Metrics Coding

  Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints.

• 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

• 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.

• Query as Anchor: Scenario-Adaptive User Representation via Large Language Model

  Jiahao Yuan, Yike Xu, Jinyong Wen, Baokun Wang, Ziyi Gao · Feb 16, 2026

  Automatic Metrics Coding

  Evaluations on 10 Alipay industrial benchmarks show consistent SOTA performance, strong scalability, and efficient deployment.

• 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.

• Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts

  Wenhao Li, Daohai Yu, Gen Luo, Yuxin Zhang, Fei Chao · Feb 2, 2026

  Automatic Metrics Coding

  Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time.

• CDLM: Consistency Diffusion Language Models For Faster Sampling

  Minseo Kim, Chenfeng Xu, Coleman Hooper, Harman Singh, Ben Athiwaratkun · Nov 24, 2025

  Automatic Metrics MathCoding

  The full training and evaluation code is available at https://github.com/SqueezeAILab/CDLM.

• 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.

• Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models

  Yinrong Hong, Zhiquan Tan, Kai Hu · Oct 30, 2025

  Automatic Metrics Coding

  Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size.

• ATTS: Asynchronous Test-Time Scaling via Conformal Prediction

  Jing Xiong, Qiujiang Chen, Fanghua Ye, Zhongwei Wan, Chuanyang Zheng · Sep 18, 2025

  Automatic Metrics MathCoding

  Large language models (LLMs) benefit from test-time scaling but are often hampered by high inference latency.

• SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML

  Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui, Ibrahim Ouahbi, Yassine Maleh · Aug 18, 2025

  Automatic Metrics Coding

  Reliable uncertainty estimation is a key missing piece for on-device monitoring in TinyML: microcontrollers must detect failures, distribution shift, or accuracy drops under strict flash/latency budgets, yet common uncertainty approaches (d

Other Metric Hubs