LW

Lemeng Wu

cs.CVcs.LGcs.AIstat.MLcs.CLcs.DCmath.OCcs.NE

On Valency

published · living versions

W_macrk6t4·v1 · currentpublished

InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

with Qinsi Wang, Wei Wen, Chong Zhou, Saksham Suri +5

1 version

Preprints & journals

31 papers in the corpus · 2018–2026

Small Vision-Language Models are Smart Compressors for Long Video Understanding2604.08120v1 · Junjie Fei, Jun Chen, Zechun Liu et al.2026 · 0 citationsarXiv

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models2603.18806v2 · Wenxuan Zhang, Lemeng Wu, Changsheng Zhao et al.2026 · 0 citationsarXiv

MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment2603.15954v2 · Hanxian Huang, Igor Fedorov, Andrey Gromov et al.2026 · 0 citationsarXiv

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice2601.05175v2 · Shuming Liu, Mingchen Zhuge, Changsheng Zhao et al.2026 · 0 citationsarXiv

Steepest Descent Density Control for Compact 3D Gaussian Splatting2505.05587v1 · Peihao Wang, Yuehao Wang, Dilin Wang et al.2025 · 5 citationsarXiv

EdgeTAM: On-Device Track Anything Model2501.07256v1 · Chong Zhou, Chenchen Zhu, Yunyang Xiong et al.2025 · 13 citationsarXiv

Efficient Track Anything2411.18933v1 · Yunyang Xiong, Chong Zhou, Xiaoyu Xiang et al.2024 · 5 citationsarXiv

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations2411.17713v1 · Igor Fedorov, Kate Plawiak, Lemeng Wu et al.2024 · 0 citationsarXiv

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding2410.17434v1 · Xiaoqian Shen, Yunyang Xiong, Changsheng Zhao et al.2024 · 0 citationsarXiv

InverseMeetInsert: Robust Real Image Editing via Geometric Accumulation Inversion in Guided Diffusion Models2409.11734v1 · Yan Zheng, Lemeng Wu2024 · 1 citationarXiv

Longhorn: State Space Models are Amortized Online Learners2407.14207v5 · Bo Liu, Rui Wang, Lemeng Wu et al.2024 · 0 citationsarXiv

Communication Efficient Distributed Training with Distributed Lion2404.00438v1 · Bo Liu, Lemeng Wu, Lizhang Chen et al.2024 · 1 citationarXiv

Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows2403.16995v1 · Shujian Zhang, Lemeng Wu, Chengyue Gong et al.2024 · 0 citationsarXiv

SqueezeSAM: User friendly mobile interactive segmentation2312.06736v3 · Balakrishnan Varadarajan, Bilge Soran, Forrest Iandola et al.2023 · 0 citationsarXiv

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything2312.00863v1 · Yunyang Xiong, Bala Varadarajan, Lemeng Wu et al.2023 · 283 citationsarXiv

AutoML-GPT: Automatic Machine Learning with GPT2305.02499v1 · Shujian Zhang, Chengyue Gong, Lemeng Wu et al.2023 · 26 citationsarXiv

PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion2212.06244v3 · Lemeng Wu, Dilin Wang, Meng Li et al.2022 · 4 citationsarXiv

Fast Point Cloud Generation with Straight Flows2212.01747v1 · Lemeng Wu, Dilin Wang, Chengyue Gong et al.2022 · 37 citationsarXiv

Neural Volumetric Mesh Generator2210.03158v1 · Yan Zheng, Lemeng Wu, Xingchao Liu et al.2022 · 5 citationsarXiv

First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data2209.01170v2 · Mao Ye, Lemeng Wu, Qiang Liu2022 · 6 citationsarXiv

Let us Build Bridges: Understanding and Extending Diffusion Generative Models2208.14699v1 · Xingchao Liu, Lemeng Wu, Mao Ye et al.2022 · 6 citationsarXiv

Residual Mixture of Experts2204.09636v3 · Lemeng Wu, Mengchen Liu, Yinpeng Chen et al.2022 · 8 citationsarXiv

How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity2202.08376v1 · Chengyue Gong, Lemeng Wu, Qiang Liu2022 · 1 citationarXiv

FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization2112.01573v1 · Xingchao Liu, Chengyue Gong, Lemeng Wu et al.2021 · 37 citationsarXiv

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks2102.08574v2 · Lemeng Wu, Bo Liu, Peter Stone et al.2021 · 30 citationsarXiv

Centroid Transformers: Learning to Abstract with Attention2102.08606v2 · Lemeng Wu, Xingchao Liu, Qiang Liu2021 · 21 citationsarXiv

Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough2010.15969v1 · Mao Ye, Lemeng Wu, Qiang Liu2020 · 7 citationsNeurIPS 2020

Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting2003.10392v5 · Lemeng Wu, Mao Ye, Qi Lei et al.2020 · 4 citationsarXiv

Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent1910.03103v3 · Dilin Wang, Meng Li, Lemeng Wu et al.2019 · 8 citationsarXiv

Splitting Steepest Descent for Growing Neural Architectures1910.02366v3 · Qiang Liu, Lemeng Wu, Dilin Wang2019 · 25 citationsarXiv

Path-Invariant Map Networks1812.11647v3 · Zaiwei Zhang, Zhenxiao Liang, Lemeng Wu et al.2018 · 12 citationsarXiv

Career total: 36 works. 31 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.