Log inSign up
Image
user avatar
Mengye Ren
@mengyer
Assistant Professor of CS & DS at NYU. Machine Learning, Human-like AI, Continual Learning | Head of @agentic_ai_lab | 🇨🇦
New York
mengyeren.com
Joined July 2009
739
Following
6,136
Followers
  • Pinned
    user avatar
    Mengye Ren
    @mengyer
    Apr 8
    New preprint: The Self Requires Learning. Self-consciousness requires continual learning + world-modeling. I introduce "bounded integration" to connect perspective, identity, and self-representation — and diagnose what current AI systems have and lack.
    Image
    51K
  • user avatar
    Mengye Ren
    @mengyer
    Apr 29, 2023
    Wondering about how to train deep neural networks without backprop? Check out our ICLR 2023 paper: arxiv.org/abs/2210.03310 Forward gradient computes gradient information from forward pass. But it is slow and noisy — it computes the directional gradient along a random weight
    arXiv logo
    arxiv.org
    Scaling Forward Gradient With Local Losses
    Forward gradient learning computes a noisy directional gradient and is a biologically plausible alternative to backprop for learning deep neural networks. However, the standard forward gradient...
    290K
  • user avatar
    Mengye Ren
    @mengyer
    May 17, 2021
    Thrilled to share that I'll be joining as an assistant professor at NYU Courant CS + Center for Data Science, starting in Fall 2022! @nyuniversity @CILVRatNYU @NYUDataScience. Deeply grateful to my mentors and collaborators, esp. to @zemelgroup & @RaquelUrtasun!
  • user avatar
    Mengye Ren
    @mengyer
    Nov 3, 2021
    I am looking for incoming students at NYU Courant CS or Center for Data Sci starting fall 2022. If you have interest in working with me on topics like meta/continual/embodied/representation learning+vision, please reach out & mention me in your PhD application. Deadline is Dec 12
  • user avatar
    Mengye Ren
    @mengyer
    Oct 13, 2023
    Dalle 3 generates watches and clocks pointing at 10:10 and fails to generate other times because almost all of the product images advertise timepieces using 10:10 since it is more visually appealing. x.com/sichengzhuml/s… #dalle3 #GenAI
    Image
    Image
    Image
    user avatar
    Sicheng Zhu
    @sichengzhuml
    Oct 13, 2023
    I doubt it 🤔
    107K
  • user avatar
    Mengye Ren
    @mengyer
    Mar 20, 2024
    🔍 New LLM Research 🔍 Conventional wisdom says that deep neural networks suffer from catastrophic forgetting as we train them on a sequence of data points with distribution shifts. But conventions are meant to be challenged! In our recent paper led by @YanlaiYang, we discovered
    Image
    Image
    28K
  • user avatar
    Mengye Ren
    @mengyer
    Dec 7, 2024
    It’s almost 2025 and the US’s green card backlog for people born in China and India was still 2022 for EB-1 and 2020 for EB-2—visa categories that represent some of the most talented individuals on the planet. This is my third year since moving to America and I have not been able
    31K
  • user avatar
    Mengye Ren
    @mengyer
    Dec 14, 2024
    The comment was inappropriate and has unnecessary details. And among the hundreds of cartoon faces created with GenAI in the slides, I had a hard time spotting any East Asian faces.
    Image
    Image
    Image
    Image
    user avatar
    Zhiyu Zoey Chen
    @ZhiyuChen4
    Dec 14, 2024
    I'm shocked to see racism happening in academia again, at the best AI conference @NeurIPSConf. Targeting specific ethnic groups to describe misconduct is inappropriate and unacceptable. @NeurIPSConf must take a stand. We call on Rosalind Picard @MIT @medialab to retract and
    17K
  • user avatar
    Mengye Ren
    @mengyer
    Nov 28, 2022
    China, a country that produces one of the most papers in AI, will be underrepresented in today’s #NeurIPS in New Orleans, due to their zero-covid policy, the most draconian in the world. While I am boarding on a plane, many Chinese are still locked in their buildings for months.
  • user avatar
    Mengye Ren
    @mengyer
    Apr 20, 2025
    How can we leverage naturalistic videos for visual SSL? Naturalistic, i.e. uncurated, videos are abundant and can emulate the egocentric perspective. Our paper at ICLR 2025, PooDLe🐩, proposes a new SSL method to address the challenges of learning from naturalistic videos. 🧵
    Image
    20K
  • user avatar
    Mengye Ren
    @mengyer
    Mar 17, 2023
    Replying to @wangzhian8848
    可以查找资料、细化结构、文案润色、结合whisper做更好的字幕，翻译多种语言，gpt-4编程能力可以制作视频小工具，结合用midjourney生成图片和视频封面以及切换图画风格。
    20K
  • user avatar
    Mengye Ren
    @mengyer
    Oct 25, 2022
    ML in the past: Loss function, convergence, learning rate, generalization, complexity, gradient, variance, normalization, duality... ML today: Calling a fine-tuning API and then a completion API. Learning how APIs work to keep myself up-to-date.
  • user avatar
    Mengye Ren
    @mengyer
    Oct 12, 2021
    Although ConvNets are already translation-equivariant, we found that a general motion-equivariance objective actually guides the network to learn semantically meaningful representations. For more details, check out our latest #ICCV2021 paper:
    user avatar
    Yuwen Xiong
    @yuwen_x
    Oct 12, 2021
    Curious about self-supervised learning from raw videos in the wild? Our #ICCV2021 paper FlowE proposed a Flow-Equivariance objective that leverages moving objects, useful for segmentation/detection. Check out paper+video for detail: arxiv.org/abs/2101.06553 @RaquelUrtasun @mengyer
    Image
    00:00
  • user avatar
    Mengye Ren
    @mengyer
    Nov 29, 2022
    See y’all tmr
    Image