Jian Luan

Orcid: 0000-0002-2383-226X

Affiliations:
  • Xiaomi, Inc
  • Microsoft Asia, Xiaoice Software Technology Center (STCA)


According to our database1, Jian Luan authored at least 142 papers between 2006 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Dasheng AudioGen: A Unified Model for Generating Coherent Audio Scenes from Text.
CoRR, May, 2026

Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation.
CoRR, May, 2026

SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking.
CoRR, May, 2026

StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video.
CoRR, May, 2026

PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media.
CoRR, May, 2026

Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment.
CoRR, May, 2026

How Mobile World Model Guides GUI Agents?
CoRR, May, 2026

TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis.
CoRR, April, 2026

ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling.
CoRR, April, 2026

Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA.
CoRR, April, 2026

Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models.
CoRR, April, 2026

Iterate to Differentiate: Enhancing Discriminability and Reliability in Zero-Shot TTS Evaluation.
CoRR, March, 2026

ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding.
CoRR, March, 2026

The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models.
CoRR, March, 2026

Borderless Long Speech Synthesis.
CoRR, March, 2026

ExPosST: Explicit Positioning with Adaptive Masking for LLM-Based Simultaneous Machine Translation.
CoRR, March, 2026

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously.
CoRR, March, 2026

IMTBench: A Multi-Scenario Cross-Modal Collaborative Evaluation Benchmark for In-Image Machine Translation.
CoRR, March, 2026

From Ideal to Real: Stable Video Object Removal under Imperfect Conditions.
CoRR, March, 2026

PatchCue: Enhancing Vision-Language Model Reasoning with Patch-Based Visual Cues.
CoRR, March, 2026

CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning.
CoRR, February, 2026

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models.
CoRR, February, 2026

DashengTokenizer: One layer is enough for unified audio understanding and generation.
CoRR, February, 2026

ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding.
CoRR, February, 2026

MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding.
CoRR, February, 2026

Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension.
CoRR, February, 2026

Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models.
CoRR, February, 2026

Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation.
CoRR, February, 2026

Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models.
CoRR, February, 2026

FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation.
CoRR, February, 2026

C<sup>2</sup>-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models.
CoRR, February, 2026

MobileBench-OL: A Comprehensive Chinese Benchmark for Evaluating Mobile GUI Agents in Real-World Environment.
CoRR, January, 2026

R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning.
CoRR, January, 2026

GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models.
CoRR, January, 2026

Federated Balanced Learning.
CoRR, January, 2026

C<sup>2</sup>-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models.
Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining, 2026

Mobile GUI Agents under Real-world Threats: Are We There Yet?
Proceedings of the 24th Annual International Conference on Mobile Systems, 2026

Doc-V^*: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

Attention Basin: Why Contextual Position Matters in Large Language Models.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

AV-Edit: Multimodal Generative Sound Effect Editing via Audio-Visual Semantic Joint Control.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Xiaomi MiMo-VL-Miloco Technical Report.
CoRR, December, 2025

LightSearcher: Efficient DeepSearch via Experiential Memory.
CoRR, December, 2025

SyncVoice: Towards Video Dubbing with Vision-Augmented Pretrained TTS Model.
CoRR, December, 2025

ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning.
CoRR, November, 2025

TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding.
CoRR, November, 2025

STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization.
CoRR, November, 2025

REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding.
CoRR, November, 2025

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models.
CoRR, November, 2025

HyperClick: Advancing Reliable GUI Grounding via Uncertainty Calibration.
CoRR, October, 2025

GUI-PRA: Process Reward Agent for GUI Tasks.
CoRR, September, 2025

Thinking in cocktail party: Chain-of-Thought and reinforcement learning for target speaker automatic speech recognition.
CoRR, September, 2025

BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent.
CoRR, September, 2025

Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle.
CoRR, August, 2025

MiDashengLM: Efficient Audio Understanding with General Audio Captions.
CoRR, August, 2025

MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks.
CoRR, July, 2025

Hijacking JARVIS: Benchmarking Mobile GUI Agents against Unprivileged Third Parties.
CoRR, July, 2025

TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation.
CoRR, June, 2025

GLAP: General contrastive audio-text pretraining across domains and languages.
CoRR, June, 2025

Heterogeneous Group-Based Reinforcement Learning for LLM-based Multi-Agent Systems.
CoRR, June, 2025

BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism.
CoRR, May, 2025

Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains.
CoRR, May, 2025

Enhance Mobile Agents Thinking Process Via Iterative Preference Learning.
CoRR, May, 2025

Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents.
CoRR, May, 2025

Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering.
CoRR, March, 2025

Direction-Aware Diagonal Autoregressive Image Generation.
CoRR, March, 2025

The ICME 2025 Audio Encoder Capability Challenge.
CoRR, January, 2025

Optimize Quantization for Large Language Models via Progressive Training.
Proceedings of the Companion Proceedings of the ACM on Web Conference 2025, 2025

DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models.
Proceedings of the Advances in Knowledge Discovery and Data Mining, 2025

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.1, 2025

X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance.
Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders.
Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

Text-Enhanced Audio Encoder for Large Language Model based Speech Recognition via Cross-Modality Pre-training with Unpaired Audio-Text Data.
Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion.
Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

GLCLAP: A Novel Contrastive Learning Pre-trained Model for Contextual Biasing in ASR.
Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization.
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025

Q-Frame: Query-Aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models.
Proceedings of the 2025 IEEE International Conference on Knowledge Graph (ICKG), 2025

LLaVA-SG: Leveraging Scene Graphs as Visual Semantic Expression in Vision-Language Models.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Let Your Car Listen to Your Respiration Contactlessly with Ubiquitous Acoustic Signals.
Proceedings of the Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing, 2025

BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

SPO: Self Preference Optimization with Self Regularization.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning.
Proceedings of the 31st International Conference on Computational Linguistics, 2025

DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2025

More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

Browsing Like Human: A Multimodal Web Agent with Experiential Fast-and-Slow Thinking.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Global Eye: Breaking the "Fixed Thinking Pattern" during the Instruction Expansion Process.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Demystifying Small Language Models for Edge Deployment.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security.
CoRR, 2024

MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Mixture of Diverse Size Experts.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024, 2024

SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM.
Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

A Comprehensive Evaluation of Quantization Strategies for Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023
CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training.
CoRR, 2023

From Indeterminacy to Determinacy: Augmenting Logical Reasoning Capabilities with Large Language Models.
CoRR, 2023

CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?
CoRR, 2023

UniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learning.
CoRR, 2023

Overview of the NLPCC 2023 Shared Task 9: User Feedback Prediction and Response Generation.
Proceedings of the Natural Language Processing and Chinese Computing, 2023

The Xiaomi AI Lab's Speech Translation Systems for IWSLT 2023 Offline Task, Simultaneous Task and Speech-to-Speech Task.
Proceedings of the 20th International Conference on Spoken Language Translation, 2023

Improving Bilingual TTS Using Language And Phonology Embedding With Embedding Strength Modulator.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

LightClone: Speaker-guided Parallel Subnet Selection for Few-shot Voice Cloning.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation.
Proceedings of the IEEE International Conference on Acoustics, 2023

Joint Training and Decoding for Multilingual End-to-End Simultaneous Speech Translation.
Proceedings of the IEEE International Conference on Acoustics, 2023

Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Exploring Better Text Image Translation with Multimodal Codebook.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

BERT-ERC: Fine-Tuning BERT Is Enough for Emotion Recognition in Conversation.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Improve Bilingual TTS Using Dynamic Language and Phonology Embedding.
CoRR, 2022

J-TranPSP: A Joint Transition-based Model for Prosodic Structure Prediction, Word Segmentation and PoS Tagging.
Proceedings of the 13th International Symposium on Chinese Spoken Language Processing, 2022

Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation.
Proceedings of the IEEE International Conference on Acoustics, 2022

MSDTRON: A High-Capability Multi-Speaker Speech Synthesis System for Diverse Data Using Characteristic Information.
Proceedings of the IEEE International Conference on Acoustics, 2022

PAMA-TTS: Progression-Aware Monotonic Attention for Stable SEQ2SEQ TTS with Accurate Phoneme Duration Control.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
Effective and Differentiated Use of Control Information for Multi-speaker Speech Synthesis.
CoRR, 2021

Noise Robust Singing Voice Synthesis Using Gaussian Mixture Variational Autoencoder.
Proceedings of the ICMI '21 Companion: Companion Publication of the 2021 International Conference on Multimodal Interaction, Montreal, QC, Canada, October 18, 2021

2020
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis.
CoRR, 2020

PPSpeech: Phrase based Parallel End-to-End TTS System.
CoRR, 2020

DeepSinger: Singing Voice Synthesis with Data Mined From the Web.
Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

Re-Weighted Interval Loss for Handling Data Imbalance Problem of End-to-End Keyword Spotting.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Adversarially Trained Multi-Singer Sequence-to-Sequence Singing Synthesizer.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Transfer Learning for Improving Singing-Voice Detection in Polyphonic Instrumental Music.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

2019
Vocal Pitch Extraction in Polyphonic Music Using Convolutional Residual Network.
Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

2012
Expand CRF to Model Long Distance Dependencies in Prosodic Break Prediction.
Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

2010
Improvement on plural unit selection and fusion.
Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

2009
The Toshiba Mandarin TTS System for the Blizzard Challenge 2009.
Proceedings of the Blizzard Challenge 2009, Edinburgh, Scotland, UK, September 4, 2009, 2009

2008
The Toshiba Mandarin TTS System for the Blizzard Challenge 2008.
Proceedings of the Blizzard Challenge 2008, 2008

2007
Codebook-Based Pseudo-Impostor Data Generation and Template Compression for Text-Dependent Speaker Verification.
IEICE Trans. Inf. Syst., 2007

2006
Template Compression and Distance Normalization for Reliable Text-dependent Speaker Verification.
Proceedings of the Odyssey 2006: The Speaker and Language Recognition Workshop, 2006

Frame-level Nonlinearity for Robust DTW-based Speaker Verification.
Proceedings of the 5th International Symposium on Chinese Spoken Language Processing, 2006


  Loading...