BY
Binhang Yuan
cs.LGcs.DCcs.AIcs.CLcs.DBcs.CVcs.CRcs.PLstat.MLcs.IR
On Valency
published · living versionsW_ajdq8vfr·v1 · currentpublished
Introducing Cluster Efficiency to LLM Serving: Pooling Economical Accelerators over Fast Interconnects
with Youhe Jiang, Pavle Glušac, Eiko Yoneki
1 version
W_zpx5t7w5·v1published
Preprints & journals
86 papers in the corpus · 2017–2026AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement2610.18083v1 · Wenhao Zhou, Jiajun Song, Haitao Wang et al.2026 · 0 citationsarXiv
Coda: Exploiting Admission Flexibility for Coding-Agent Serving2610.03088v1 · Youhe Jiang, Fangcheng Fu, Binhang Yuan et al.2026 · 0 citationsarXiv
AFORE: Attention-FFN Disaggregation with Overlapped Reconfiguration of Experts2610.03203v1 · Wenshuang Li, Youhe Jiang, You Peng et al.2026 · 0 citationsarXiv
D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?2610.03226v1 · Daifeng Li, Huiqiang Jiang, Chengruidong Zhang et al.2026 · 0 citationsarXiv
ePACT: Energy-Performance-Aware Commitment Tracking for LLM Serving2610.01784v1 · You Peng, Youhe Jiang, Chen Wang et al.2026 · 0 citationsarXiv
Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Serving2610.00499v1 · Haoyu Zheng, Fangcheng Fu, Binhang Yuan et al.2026 · 0 citationsarXiv
AReaL-TIK: Stateful Agentic Optimization of Unified RL Kernels through an Optimization IR2609.35140v1 · Ran Yan, Youhe Jiang, Jiayi Nie et al.2026 · 0 citationsarXiv
GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development2609.21293v1 · Xiuhui Zhang, Yi Chen, Shusheng Xu et al.2026 · 0 citationsarXiv
RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation2609.18703v1 · Xiaochen Ma, Zimo Meng, Junzhu Liang et al.2026 · 0 citationsarXiv
From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems2608.15127v1 · Chaokun Chang, Yukun Zhou, Kaihua Fu et al.2026 · 0 citationsarXiv
AReaL-DTE: Sparse Policy-Weight Transfer for Online Agentic Reinforcement Learning2608.00455v1 · Yingqi Peng, Jiawei Zhang, Wenhao Zhou et al.2026 · 0 citationsarXiv
Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents2607.01120v2 · Ran Yan, Wei Fu, Jiale Li et al.2026 · 0 citationsarXiv
RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation2607.02584v2 · Yaofu Liu, Wanli Lan, Jinxi Li et al.2026 · 0 citationsarXiv
D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models2606.04446v1 · Liyuan Zhang, Jiarui Zhang, Jinwei Yao et al.2026 · 0 citationsarXiv
PrefixFlow: Training-Time KV Caching for Schedule-Level Prefix Reuse in LLM RL Training2606.01143v4 · Pengbo Li, Feiyuan Zhang, Guangming Sheng et al.2026 · 0 citationsarXiv
TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization2605.20150v2 · Chonghao Zhong, Linfeng Shi, Hua Chen et al.2026 · 0 citationsarXiv
HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling2605.16637v1 · You Peng, Youhe Jiang, Wenshuang Li et al.2026 · 0 citationsarXiv
HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware2605.07569v1 · Yan Liang, Youhe Jiang, Ran Yan et al.2026 · 0 citationsarXiv
Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management2605.06472v1 · Haoyu Zheng, Fangcheng Fu, Jia Wu et al.2026 · 0 citationsarXiv
Ave: Guiding Agentic GPU Optimization Using Data-Flow Invariants2604.18616v2 · Haohui Mai, Xiaoyan Guo, Xiangyun Ding et al.2026 · 0 citationsarXiv
Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics2604.07144v1 · Youhe Jiang, Ran Yan, You Peng et al.2026 · 0 citationsarXiv
Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes2603.23507v1 · Fangyu Ding, Ding Ding, Sijin Chen et al.2026 · 0 citationsarXiv
V3DB: Audit-on-Demand Zero-Knowledge Proofs for Verifiable Vector Search over Committed Snapshots2603.03065v2 · Zipeng Qiu, Wenjie Qu, Jiaheng Zhang et al.2026 · 0 citationsarXiv
Trident: Adaptive Scheduling for Heterogeneous Multimodal Data Pipelines2603.02075v1 · Ding Pan, Zhuangzhuang Zhou, Long Qian et al.2026 · 0 citationsarXiv
IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation2602.22700v1 · Yanpei Guo, Wenjie Qu, Linyu Wu et al.2026 · 0 citationsarXiv
Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code2602.18745v1 · Haobo Lin, Tianyi Bai, Chen Chen et al.2026 · 0 citationsarXiv
S2SServiceBench: A Multimodal Benchmark for Last-Mile S2S Climate Services2602.14017v1 · Chenyue Li, Wen Deng, Zhuotao Sun et al.2026 · 0 citationsarXiv
AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models2602.00482v2 · Jiarui Zhang, Yuchen Yang, Ran Yan et al.2026 · 0 citationsarXiv
CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows2511.20109v2 · Chenyue Li, Hyeonjae Kim, Wen Deng et al.2025 · 0 citationsarXiv
VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL2511.18902v1 · Zengjie Hu, Jiantao Qiu, Tianyi Bai et al.2025 · 0 citationsarXiv
AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs2511.00796v1 · Ran Yan, Youhe Jiang, Tianyuan Wu et al.2025 · 0 citationsarXiv
UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models2510.10481v1 · Guangxin He, Shen Nie, Fengqi Zhu et al.2025 · 0 citationsarXiv
VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code2510.06296v3 · Lingfei Zeng, Fengdi Che, Xuhan Huang et al.2025 · 0 citationsarXiv
Parallax: Efficient LLM Inference Service over Decentralized Environment2509.26182v1 · Chris Tong, Youhe Jiang, Gufeng Chen et al.2025 · 0 citationsarXiv
Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification2509.23061v1 · Xu Xu, Xin Li, Xingwei Qu et al.2025 · 0 citationsarXiv
Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs2509.15940v1 · Guoliang He, Youhe Jiang, Wencong Xiao et al.2025 · 2 citationsarXiv
FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel2508.18224v3 · Ran Yan, Youhe Jiang, Zhuoming Chen et al.2025 · 0 citationsarXiv
Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny2507.16331v4 · Chuanhao Yan, Fengdi Che, Xuhan Huang et al.2025 · 0 citationsarXiv
Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning2506.07227v1 · Tianyi Bai, Yuxuan Fan, Jiantao Qiu et al.2025 · 3 citationsarXiv
Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification2506.07235v1 · Tianyi Bai, Zengjie Hu, Fupeng Sun et al.2025 · 2 citationsarXiv
Cascadia: An Efficient Cascade Serving System for Large Language Models2506.04203v2 · Youhe Jiang, Fangcheng Fu, Wanru Zhao et al.2025 · 0 citationsarXiv
TAH-QUANT: Effective Activation Quantization in Pipeline Parallelism over Slow Network2506.01352v2 · Guangxin He, Yuan Cao, Yutong He et al.2025 · 0 citationsarXiv
AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning2505.24298v5 · Wei Fu, Jiaxuan Gao, Xujie Shen et al.2025 · 4 citationsarXiv
HEXGEN-FLOW: Optimizing LLM Inference Request Scheduling for Agentic Text-to-SQL2505.05286v3 · You Peng, Youhe Jiang, Wenqi Jiang et al.2025 · 0 citationsarXiv
MLKV: Efficiently Scaling up Large Embedding Model Training with Disk-based Key-Value Storage2504.01506v1 · Yongjun He, Roger Waleffe, Zhichao Han et al.2025 · 1 citationarXiv
Prompt Inversion Attack against Collaborative Inference of Large Language Models2503.09022v3 · Wenjie Qu, Yuguang Zhou, Yongji Wu et al.2025 · 10 citationsarXiv
HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment2502.07903v1 · Youhe Jiang, Ran Yan, Binhang Yuan2025 · 0 citationsarXiv
AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science2502.01159v3 · Chenyue Li, Wen Deng, Mengqian Lu et al.2025 · 4 citationsarXiv
CE-LoRA: Computation-Efficient LoRA Fine-Tuning for Language Models2502.01378v1 · Guanduo Chen, Yutong He, Yipeng Hu et al.2025 · 2 citationsarXiv
Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs2502.00722v2 · Youhe Jiang, Fangcheng Fu, Xiaozhe Yao et al.2025 · 0 citationsarXiv
Career total: 129 works. 86 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.