XZ

Xiangyu Zhang

0000-0003-2138-4608

cs.CVcs.LGcs.AIcs.CLcs.SDeess.AScs.ROstat.MLcs.HCcs.SE

On Valency

published · living versions

AMARA: Compiler-Driven Accelerator Architecture Design for Graphical Probabilistic Sampling

with Zhan Chen, Yihan Fu, Wenshuo Yue, Daijing Shi +4

1 version

W_tp3rwekzv1 · current

Hy ASR 3.0 Technical Report

W_hnc4x8h2v1

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

W_35dzxcxpv1

Object Detection Networks on Convolutional Feature Maps

W_trhn2s23v1

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

W_xbsdm36xv1

Deep Residual Learning for Image Recognition

W_u8tsejq2v1

Preprints & journals

191 papers in the corpus · 2014–2026

KITE: KV-Invariant Transformer Expansion for Efficient Agentic LLM Scaling

Zhiheng Hu, Yixun Wei, Jian Zhou et al.

0 citations

2609.27294v12026arXiv

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

Lei Yang, Mengyin Liu, Jia Wang et al.

0 citations

2609.24983v12026arXiv

OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning

Xu Xu, Jinxiu Liu, Zhangbo Qiao et al.

0 citations

2609.16057v12026arXiv

StepAudio 3 Realtime Technical Report

Bin Lin, Bo Zhao, Boyang Zhang et al.

0 citations

2609.14005v32026arXiv

StepAudio 3 Gen Technical Report

Bin Lin, Bo Zhao, Boyang Wang et al.

0 citations

2609.12945v12026arXiv

StepAudio 3 Music Technical Report

Chengli Feng, Zhiyue Wu, Jiahao Song et al.

0 citations

2609.16034v12026arXiv

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

NeoHorse Team, Guoliang Cao, Guohao Dai et al.

0 citations

2609.08183v22026arXiv

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition

Qingjian Lin, Yuxin Li, Haoyang Zhang et al.

0 citations

2607.29279v12026arXiv

MentalThink: Shaping Thoughts in Mental SVG World

Kangheng Lin, Jisheng Yin, Dingming Li et al.

0 citations

2607.03530v12026arXiv

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Yana Wei, Hongbo Peng, Yanlin Lai et al.

0 citations

2606.28322v22026arXiv

Skill-Guided Continuation Distillation for GUI Agents

Zhimin Fan, Hongwei Yu, Yeqing Shen et al.

0 citations

2606.18890v12026arXiv

MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models

Hao Shi, Weiye Li, Bin Xie et al.

0 citations

2606.09827v12026arXiv

AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications

Yifan Sui, Xin Huang, Hongbing Li et al.

0 citations

2605.27761v12026arXiv

StepAudio 2.5 Technical Report

Bin Lin, Bo Zhao, Boyong Wu et al.

0 citations

2605.23463v12026arXiv

Vision Foundation Models as Generalist Tokenizers for Image Generation

Anlin Zheng, Qi Han, Xin Wen et al.

0 citations

2605.18390v12026arXiv

Step-Audio-R1.5 Technical Report

Yuxin Zhang, Xiangyu Tony Zhang, Daijiao Liu et al.

0 citations

2604.25719v22026arXiv

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

Dinging Li, Yingxiu Zhao, Xinrui Cheng et al.

0 citations

2604.14144v12026arXiv

WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics

Yuhong Dai, Yanlin Lai, Mitt Huang et al.

0 citations

2603.13391v12026arXiv

DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI

En Yu, Haoran Lv, Jianjian Sun et al.

0 citations

2602.14974v12026arXiv

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering

Xiangfeng Wang, Hangyu Guo, Yanlin Lai et al.

0 citations

2602.11570v12026arXiv

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

Ailin Huang, Ang Li, Aobo Kong et al.

0 citations

2602.10604v22026arXiv

GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments

Haodong Li, Jingwei Wu, Quan Sun et al.

0 citations

2602.09007v32026arXiv

R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging

Yanlin Lai, Mitt Huang, Hangyu Guo et al.

0 citations

2602.06763v12026arXiv

DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder

Jiaran Zhang, Luck Ma, Fanqi Wan et al.

0 citations

2602.00592v22026arXiv

STEP3-VL-10B Technical Report

Ailin Huang, Chengyuan Yao, Chunrui Han et al.

0 citations

2601.09668v22026arXiv

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

Jingcheng Hu, Yinmin Zhang, Shijie Shang et al.

0 citations

2601.05593v12026arXiv

Step-DeepResearch Technical Report

Chen Hu, Haikuo Du, Heng Wang et al.

0 citations

2512.20491v42025arXiv

Step-GUI Technical Report

Haolong Yan, Jia Wang, Xin Huang et al.

0 citations

2512.15431v22025arXiv

GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

Haolong Yan, Yeqing Shen, Xin Huang et al.

0 citations

2512.02423v12025arXiv

Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction

Bao Shu, Yan Cai, Jianjian Sun et al.

0 citations

2511.23476v12025arXiv

ReasonEdit: Towards Reasoning-Enhanced Image Editing Models

Fukun Yin, Shiyu Liu, Yucheng Han et al.

0 citations

2511.22625v22025arXiv

Step-Audio-R1 Technical Report

Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang et al.

0 citations

2511.15848v22025arXiv

SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation

Hao Shi, Bin Xie, Yingfei Liu et al.

1 citation

2511.09555v22025arXiv

Step-Audio-EditX Technical Report

Chao Yan, Boyong Wu, Peng Yang et al.

0 citations

2511.03601v22025arXiv

MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models

Yayue Deng, Guoqiang Hu, Haiyang Sun et al.

1 citation

2511.00850v12025arXiv

Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models

Donghang Wu, Haoyang Zhang, Jun Chen et al.

1 citation

2510.09592v22025arXiv

WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling

Jiacheng Li, Jianchao Tan, Zhidong Yang et al.

0 citations

2508.16676v22025arXiv

RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models

Jianhao Chen, Mayi Xu, Haoyang Chen et al.

0 citations

2508.12897v22025arXiv

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

NextStep Team: Chunrui Han, Guopeng Li, Jingwei Wu et al.

0 citations

2508.10711v22025arXiv

Bootstrap Masked Visual Modeling via Hard Patch Mining.

Wang, Haochen, Fan, Junsong, Wang, Yuxi et al.

4 citations

402028752025IEEE transactions on pattern analysis and machine intelligence. 2025;47(8):6200-6214

StepFun-Prover Preview: Let's Think and Verify Step by Step

Shijie Shang, Ruosi Wan, Yue Peng et al.

0 citations

2507.20199v32025arXiv

Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding

StepFun: Bin Wang, Bojun Wang, Changyi Wan et al.

0 citations

2507.19427v12025arXiv

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Anlin Zheng, Xin Wen, Xuanyang Zhang et al.

0 citations

2507.08441v22025arXiv

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Yana Wei, Liang Zhao, Jianjian Sun et al.

3 citations

2507.05255v22025arXiv

Hita: Holistic Tokenizer for Autoregressive Image Generation

Anlin Zheng, Haochen Wang, Yucheng Zhao et al.

0 citations

2507.02358v42025arXiv

Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource

Houyi Li, Ka Man Lo, Shijie Xuyang et al.

2 citations

2506.12119v22025arXiv

Predictable Scale: Part II, Farseer: A Refined Scaling Law in Large Language Models

Houyi Li, Wenzhen Zheng, Qiufeng Wang et al.

0 citations

2506.10972v32025arXiv

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model

Ailin Huang, Bingxin Li, Bruce Wang et al.

0 citations

2506.08967v22025arXiv

TAI3: Testing Agent Integrity in Interpreting User Intent

Shiwei Feng, Xiangzhe Xu, Xuan Chen et al.

0 citations

2506.07524v32025arXiv

Continuous Semi-Implicit Models

Longlin Yu, Jiajun Zha, Tong Yang et al.

0 citations

2506.06778v12025arXiv

Career total: 237 works. 191 are in this corpus.Showing the 50 most recent.

Profile built from the corpus for this byline.

237

works

329K

citations

76

h-index

Corpus papers per year

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.