Yuxuan Lou

OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling

Yuxuan Lou, Yang You

@article{lou2026orscale,
  title   = {OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling},
  author  = {Lou, Yuxuan and You, Yang},
  journal = {arXiv preprint arXiv:2605.07815},
  year    = {2026}
}

AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding

Yingxuan Ren*, Yuxuan Lou*, Yong Liu, Pengcheng Fang, Ziming Wang, Pengfei Zhou, Yang You^†

@article{ren2026asynclane,
  title   = {AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding},
  author  = {Ren, Yingxuan and Lou, Yuxuan and Liu, Yong and Fang, Pengcheng and Wang, Ziming and Zhou, Pengfei and You, Yang},
  journal = {arXiv preprint arXiv:2606.08411},
  year    = {2026}
}

ECUpcycle: Slice-Structured Expert-Choice Diffusion Language Model Upcycling

Yong Liu*, Yuxuan Lou*, Hailun Xu, Yingxuan Ren, Haoying Li, Kanchan Sarkar, Kun Xu, Yingyan Celine Lin, Cho-Jui Hsieh, Yang You

DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion

Yuxuan Lou*, Ziming Wu*, Yaochen Wang, Yong Liu, Yingxuan Ren, Fuming Lai, Shaobing Lian, Jie Tang, Yang You

@article{lou2026diffuspeech,
  title   = {DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion},
  author  = {Lou, Yuxuan and Wu, Ziming and Wang, Yaochen and Liu, Yong and Ren, Yingxuan and Lai, Fuming and Lian, Shaobing and Tang, Jie and You, Yang},
  journal = {arXiv preprint arXiv:2601.22889},
  year    = {2026}
}

MoST: Modality-Aware Mixture of Experts for Efficient Speech-Text Foundation Model

Yuxuan Lou*, Kai Yang*, Yang You

@inproceedings{lou2026most,
  title     = {MoST: Modality-Aware Mixture of Experts for Efficient Speech-Text Foundation Model},
  author    = {Lou, Yuxuan and Yang, Kai and You, Yang},
  booktitle = {International Conference on Machine Learning (ICML)},
  year      = {2026}
}

MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE

Geng Zhang, Yuxuan Han, Yuxuan Lou, Yiqi Zhang, Wangbo Zhao, Yang You

@inproceedings{zhang2026mone,
  title     = {MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE},
  author    = {Zhang, Geng and Han, Yuxuan and Lou, Yuxuan and Zhang, Yiqi and Zhao, Wangbo and You, Yang},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2026}
}

EnvBridge: Bridging Diverse Environments with Cross-Environment Knowledge Transfer for Embodied AI

Tomoyuki Kagaya*, Yuxuan Lou*, Thong Jing Yuan*, Subramanian Lakshmi*, Jayashree Karlekar, Sugiri Pranata, Natsuki Murakami, Akira Kinose, Koki Oguri, Felix Wick, Yang You

@article{kagaya2024envbridge,
  title   = {EnvBridge: Bridging Diverse Environments with Cross-Environment Knowledge Transfer for Embodied AI},
  author  = {Kagaya, Tomoyuki and Lou, Yuxuan and Yuan, Thong Jing and Lakshmi, Subramanian and Karlekar, Jayashree and Pranata, Sugiri and Murakami, Natsuki and Kinose, Akira and Oguri, Koki and Wick, Felix and You, Yang},
  journal = {arXiv preprint arXiv:2410.16919},
  year    = {2024}
}

RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents

Tomoyuki Kagaya*, Yuxuan Lou*, Thong Jing Yuan*, Subramanian Lakshmi*, Jayashree Karlekar, Sugiri Pranata, Natsuki Murakami, Akira Kinose, Koki Oguri, Felix Wick, Yang You

@article{kagaya2024rap,
  title   = {RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents},
  author  = {Kagaya, Tomoyuki and Lou, Yuxuan and Yuan, Thong Jing and Lakshmi, Subramanian and Karlekar, Jayashree and Pranata, Sugiri and Murakami, Natsuki and Kinose, Akira and Oguri, Koki and Wick, Felix and You, Yang},
  journal = {arXiv preprint arXiv:2402.03610},
  year    = {2024}
}

Cross-token Modeling with Conditional Computation

Yuxuan Lou, Fuzhao Xue, Zangwei Zheng, Yang You

@article{lou2022crosstoken,
  title   = {Cross-token Modeling with Conditional Computation},
  author  = {Lou, Yuxuan and Xue, Fuzhao and Zheng, Zangwei and You, Yang},
  journal = {arXiv preprint arXiv:2109.02008},
  year    = {2022}
}

"Pioneering the Systems Foundations for Diffusion-Based Large Language Models on TPUs", up to $100K in Google Cloud credits. Project lead under PI Prof. Yang You; resulting publications: DiffuSpeech, AsyncLane, ECUpcycle.

Developed DiffuSpeech, the first diffusion-based speech-text language model supporting both understanding and generation, introducing a "Silent Thought, Spoken Answer" paradigm where internal text reasoning informs spoken responses. Unified discrete text and tokenized speech under a single masked diffusion framework with modality-specific masking schedules. Constructed ThinkingTalk, the first speech QA dataset with paired text reasoning traces (26K samples, 319 hours), achieving state-of-the-art speech-to-speech QA accuracy (+9 points over best baseline) and best TTS quality among generative models (6.2% WER).

Developed MoST, a novel speech-text foundation model featuring a Modality-Aware Mixture of Experts (MAMOE) architecture; achieved competitive performance across multiple speech-text benchmarks using exclusively open-source data. Designed modality-specific expert routing strategies and shared-expert configurations that improve cross-modal knowledge integration while maintaining inference efficiency. MoST was accepted by ICML 2026.

Developed RAP, a multimodal planning agent leveraging past successful experiences to enhance decision-making. Developed EnvBridge, a multimodal embodied agent transferring knowledge across diverse environments. Achieved SOTA on text-only environments (ALFWorld, Webshop) and significant improvements on multimodal robotics benchmarks (Franka Kitchen, Meta-World, RLBench).

Developed large-scale vision models: Sparse-MLP, Widenet based on Mixture of Experts. Proposed a fully-MLP architecture with conditional computation in two directions and extended MoE to the spatial dimension of image representation.

Making large AI models cheaper, faster, and more accessible. A collection of parallel components for distributed training. Managed and contributed to Colossal-AI examples.

A curated collection of Mixture of Experts papers and projects.

ClawFinetune

Portable fine-tuning skill package for agent-driven workflows; generates and launches LoRA SFT runs on Tinker and the HPC-AI SDK with preflight validation and run-state tracking.

ClawTrade

Secure multi-broker trading middleware that lets AI agents operate brokerage accounts behind a containerized, guardrail-enforced HTTP API.

Working on diffusion large language models at InclusionAI, the open-source AI research arm of Ant Group.

Developed DiffuSpeech, the first diffusion-based speech-text language model supporting both understanding and generation. Collaborated on building the ThinkingTalk dataset and speech-text diffusion framework.

Colossal-AI and Colossal-AI Examples co-developer. Built an open domain dialog system with internet knowledge augmentation.

Data mining and cleaning of users' comments. Built ML models for emotion classification and deep learning abstractive text summarization.