Yuxuan Lou

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

Yuxuan Lou, Yang You

AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding

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

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

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

Yuxuan Lou*, Kai Yang*, Yang You

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

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

Cross-token Modeling with Conditional Computation

Yuxuan Lou, Fuzhao Xue, Zangwei Zheng, Yang You

"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.