YW

Yi Wu

cs.AIcs.ROcs.CLcs.CVbioinformaticscs.DCcs.IRcs.LGq-bio.QM

On Valency

published · living versions

W_2m4cjw2n·v1 · currentpublished

RegimeFormer: A Large Protein Model of Global Perturbation Regimes

with Siyuan Ma, Yi Chai, Qixin Zhang, Yajing Yuan +10

1 version

Preprints & journals

10 papers in the corpus · 2026

RegimeFormer: A Large Protein Model of Global Perturbation Regimes2608.26586v1 · Siyuan Ma, Yi Chai, Yi Wu et al.2026 · 0 citationsarXivon Valency

Multi-Image Visual Token Pruning in Large Visual Language Models2608.26806v2 · Rongyang Zhang, Chengqiang Lu, Cong Li et al.2026 · 0 citationsarXiv

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection2608.01630v1 · Shicheng Xu, Liang Pang, Liyi Chen et al.2026 · 0 citationsarXiv

Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents2608.02097v1 · Qi Liu, Yiqun Chen, Zidan Chen et al.2026 · 0 citationsarXiv

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation2607.14586v1 · Yi Wu, Junjie An, Xiao Liu et al.2026 · 0 citationsarXiv

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models2607.14635v1 · Yufeng Ji, Wenhao Tang, Haoyi Niu et al.2026 · 0 citationsarXiv

NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation2607.14643v1 · Junjie An, Yi Wu, Xiao Liu et al.2026 · 0 citationsarXiv

Building Multi-Task Agentic LLMs via Two-Phase Distillation2606.30044v1 · Huaijie Wang, Shusheng Xu, Yi Wu et al.2026 · 0 citationsarXiv

ReaLB: Real-Time Load Balancing for Multimodal MoE Inference2604.19503v3 · Yingping Wang, Yi Wu, Xiangyu Wu et al.2026 · 0 citationsarXiv

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents2601.22607v3 · Jiaxuan Gao, Jiaao Chen, Chuyi He et al.2026 · 0 citationsarXiv

Career total: 11 works. 10 are in this corpus.

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.