Lightnews — Scholar-powered news

Reposted by Mengye Ren

NeurIPS Conference @neuripsconf.bsky.social · 19d

Be part of #NeurIPS2025 in Mexico City! Submit your proposals:

📅 Deadlines
Tutorials: Sept 26 👉 neurips.cc/Conferences/...
Workshops: Sept 30 👉 neurips.cc/Conferences/...
Socials: Oct 1 👉 neurips.cc/Conferences/...
Startup Pitch: Oct 15 👉 neurips.cc/Conferences/...

3 5

Reposted by Mengye Ren

NeurIPS Conference @neuripsconf.bsky.social · 23d

Pitch your AI startup at NeurIPS 2025 in Mexico City! The application deadline is just a month away on October 15th.

Learn more and apply now: neurips.cc/Conferences/...

NeurIPS 2025 Mexico City - Call for Startup Pitch

We’re thrilled to announce the Startup Pitch Competition at the Mexico City satellite location of NeurIPS 2025! This competition offers early-stage AI startups a chance to showcase their innovations…

neurips.cc

3 8

Reposted by Mengye Ren

NYU Center for Data Science @nyudatascience.bsky.social · 28d

Watch this new video of work by CDS Asst. Prof. Mengye Ren (@mengyer.bsky.social) and colleagues, who built PooDLe, an algorithm that helps AI systems learn from complex environments like busy streets.

The method mimics how humans process cluttered scenes.

www.nyu.edu/about/news-p...

1 1 5

Reposted by Mengye Ren

NeurIPS Conference @neuripsconf.bsky.social · Jul 16

We're excited to announce a second physical location for NeurIPS 2025, in Mexico City, which we hope will address concerns around skyrocketing attendance and difficulties in travel visas that some attendees have experienced in previous years.

Read more in our blog:
blog.neurips.cc/2025/07/16/n...

1 21 45

Reposted by Mengye Ren

NeurIPS Conference @neuripsconf.bsky.social · Jul 16

NeurIPS is endorsing EurIPS, an independently-organized meeting which will offer researchers an opportunity to additionally present NeurIPS work in Europe concurrently with NeurIPS.

Read more in our blog post and on the EurIPS website:
blog.neurips.cc/2025/07/16/n...
eurips.cc

eurips.cc

A NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark

eurips.cc

2 38 120

Reposted by Mengye Ren

NeurIPS Conference @neuripsconf.bsky.social · Jul 2

NeurIPS is seeking additional ethics reviewers this year. If you are able and willing to participate in the review process, please sign up at the form in the link:
neurips.cc/Conferences/...
Please share this call with your colleagues!

2025 Call For Ethics Reviewers

If you are able and willing to participate in the review process, please sign up at this form. Feel free to share this call with your colleagues.

neurips.cc

8 11

Reposted by Mengye Ren

NYU Center for Data Science @nyudatascience.bsky.social · Jun 11

CDS Asst. Prof. @mengyer.bsky.social, Courant PhD students Alex N. Wang and Christopher Hoang, and @ylecun.bsky.social introduce PooDLe: a self-supervised learning method enhancing AI vision in real-world videos by improving small object detection.

nyudatascience.medium.com/learning-to-...

Learning to See Like Animals: How Small Objects in Dense Video Scenes Challenge AI Vision

PooDLe enhances AI vision in real-world videos by improving small object detection.

nyudatascience.medium.com

1 2

Reposted by Mengye Ren

NeurIPS Conference @neuripsconf.bsky.social · May 21

The NeurIPS Position Track is seeking additional reviewers this year. If you'd like to serve or nominate a colleague, please complete our nomination form! docs.google.com/forms/d/e/1F...

NeurIPS 2025 Position Paper Track Reviewer Nomination Form

Does this form look suspicious? Report

docs.google.com

4 3

Mengye Ren @mengyer.bsky.social · May 17

Source: www.nbcnews.com/news/latino/...

Republicans want to tax remittances sent by migrants, visa holders to their home countries

House Republicans want to tax remittances, which would cover over 40 million people in the U.S., including green card and visa holders who send money to families.

www.nbcnews.com

Mengye Ren @mengyer.bsky.social · May 17

The proposed 5% remittance tax on non-citizens is another blatant attack on foreign workers, who've contributed tremendously to the U.S. economy, have little path to citizenship, no birthright for their kids, and will face double taxation on their hard-earned dollars.

1

Mengye Ren @mengyer.bsky.social · Apr 20

10/ This @agentic-ai-lab.bsky.social project was led by
Alex Wang @alexnwang.bsky.social and Chris Hoang @choang.bsky.social , together with Yuwen Xiong, @yann-lecun.bsky.social and @mengyer.bsky.social.

Mengye Ren @mengyer.bsky.social · Apr 20

9/ For more details, please check out our paper and website, or stop by our poster (Fri 10 AM, Hall 3 + Hall 2B #336) at ICLR!
Paper: arxiv.org/abs/2408.11208
Website: agenticlearning.ai/poodle/

PooDLe: Pooled and dense self-supervised learning from naturalistic videos

Self-supervised learning has driven significant progress in learning from single-subject, iconic images. However, there are still unanswered questions about the use of minimally-curated, naturalistic ...

arxiv.org

1

Mengye Ren @mengyer.bsky.social · Apr 20

8/ We also study how data augmentation choices like crop scale, input resolution, and time between sampled frames can have a large impact on video pretraining.

1

Mengye Ren @mengyer.bsky.social · Apr 20

7/ These performance differences manifest visually too! IN1K has noisy segmentations and FlowE misses small objects, while PooDLe avoids both problems.

1

Mengye Ren @mengyer.bsky.social · Apr 20

6/ Interestingly, we find that dense SSL performance is driven by large classes whereas ImageNet pretraining does well on small, foreground classes.
PooDLe is able to perform well on both small and large classes!

1

Mengye Ren @mengyer.bsky.social · Apr 20

5/ PooDLe, pretrained on BDD100K and Walking Tours, outperforms prior iconic and dense SSL methods on semantic segmentation and object detection!
We also release WT-Sem, an in-distribution semantic segmentation task for Walking Tours.

1

Mengye Ren @mengyer.bsky.social · Apr 20

4/ We also propose a spatial decoder module to upsample the top-level features to higher resolution for the dense loss. The top-level features act as an information bottleneck that both satisfies the high-level invariance loss and is compatible with upsampling for the dense loss.

1

Mengye Ren @mengyer.bsky.social · Apr 20

3/ PooDLe addresses these challenges by unifying a dense, flow equivariance objective over global crops and a view invariance objective over smaller subcrops that serve as pseudo-iconic views. Crops are sampled from pairs of video frames, with motion as a natural augmentation.

1

Mengye Ren @mengyer.bsky.social · Apr 20

2/ Dense SSL methods account for multiple subjects by computing losses over corresponding spatial regions. However, we identify a new problem – spatial imbalance! Larger background regions like the sky are prioritized over smaller foreground objects like pedestrians.

1

Mengye Ren @mengyer.bsky.social · Apr 20

1/ Many SSL methods revolve around ImageNet, iconic images with single subjects and balanced classes, and rely on invariance losses between augmented views. These methods can struggle on naturalistic videos, which contain multiple subjects of varying size and imbalanced classes.

1

Mengye Ren @mengyer.bsky.social · Apr 20

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. 🧵

1 1

Mengye Ren @mengyer.bsky.social · Apr 8

A single man's decision wiped out 20% of the global wealth and still going...

Mengye Ren @mengyer.bsky.social · Apr 5

America will become a T-shirt manufacturing superpower!

2

Mengye Ren @mengyer.bsky.social · Apr 3

Love that stock market crashing...

Mengye Ren @mengyer.bsky.social · Mar 20

"A French scientist was denied entry to the US after immigration officers at an airport searched his phone and found messages in which he had expressed criticism of the Trump administration." --- So much for freedom of speech.

1