Lightnews — Scholar-powered news

Andrei Bursuc @abursuc.bsky.social · 1d

Hear! Hear!

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 1d

Whatever you do, don’t burn out. It’s terrible and it’s hard to fully recover, like a knee injury that makes you too scared to try jumping again

5

Reposted by Andrei Bursuc

valeo.ai @valeoai.bsky.social · 2d

“Has anyone heard about DUSt3R?”
All hands and hearts up in the room.
Honored to welcome @gabrielacsurka.bsky.social today to speak about the amazing work @naverlabseurope.bsky.social towards 3D Foundation Models

1 11

Andrei Bursuc @abursuc.bsky.social · 3d

Not quite my living room, but rather my neighbor’s Louie. He has always been an expert in attracting and welcoming guests at his place(s) 🙃
In this pic it’s the ceiling of Théâtre Montansier in Versailles.

2

Andrei Bursuc @abursuc.bsky.social · 4d

1 6

Andrei Bursuc @abursuc.bsky.social · 4d

Ah, no! I was actually thinking of the value of knowing when and how to stay silent and listen to the others instead.

3 6

Andrei Bursuc @abursuc.bsky.social · 5d

The unreasonable effectiveness of mastering the skill of placing <EOS> in real life

1 5

Andrei Bursuc @abursuc.bsky.social · 6d

The outstanding reviewer award is definitely one of my favorite type of awards as good reviewing helps so much to advance our community and research forward.
Congrats to all great reviewers out there whether rewarded this time or not! #iccv2025

valeo.ai @valeoai.bsky.social · 6d

Congratulations to our lab colleagues who have been named Outstanding Reviewers at #ICCV2025 👏

Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social

@iccv.bsky.social
iccv.thecvf.com/Conferences/...

2025 ICCV Program Committee

iccv.thecvf.com

1 14

Reposted by Andrei Bursuc

valeo.ai @valeoai.bsky.social · 6d

Congratulations to our lab colleagues who have been named Outstanding Reviewers at #ICCV2025 👏

Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social

@iccv.bsky.social
iccv.thecvf.com/Conferences/...

2025 ICCV Program Committee

iccv.thecvf.com

6 18

Andrei Bursuc @abursuc.bsky.social · 6d

Some night runs seem more like sightseeing than running

24

Reposted by Andrei Bursuc

Kosta Derpanis @csprofkgd.bsky.social · 10d

Here we go again 😅 This time I’m planning to take a more senior role to help mentor the next gen of publicity chairs. Please consider volunteering!

#CVPR2026 @cvprconference.bsky.social · 10d

#CVPR2026 is looking for Publicity Chairs! The role includes working as part of a team to share conference updates across social media (X, Bluesky, etc.) and answering community questions.

Interested? Check out the self-nomination form in the thread.

4 11

Reposted by Andrei Bursuc

Michael Kirchhof (ICML) @mkirchhof.bsky.social · 7d

Many treat uncertainty = a number. At Apple, we're rethinking this: LLMs should output strings that reveal all information of their internal distributions. We find that Reasoning, SFT, CoT can't do it - yet. To get there, we introduce the SelfReflect benchmark.

arxiv.org/pdf/2505.20295

3 6 30

Reposted by Andrei Bursuc

Gilles Puy @gillespuy.bsky.social · 14d

Update: ResearchGate has investigated the case, and, as far as I can see, all the suspicious papers (~200) have now been removed. Many thanks to the @researchgate.bsky.social team!

Gilles Puy @gillespuy.bsky.social · 22d

Discovered that our RangeViT paper keeps being cited in what might be LLM-generated papers. Number of citations increased rapidly in the last weeks. Too good to be true.

Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks.
[1/]

1 2 3

Andrei Bursuc @abursuc.bsky.social · 13d

A nice side-effect of working with students every day?

1 2

Reposted by Andrei Bursuc

valeo.ai @valeoai.bsky.social · 14d

CoRL 2025 is just around the corner in Seoul, Korea!

🤖 🚗

We're excited to present our latest research and connect with the community.

#CoRL2025

1 2 5

Andrei Bursuc @abursuc.bsky.social · 14d

In my brain every time I connect to overleaf during deadline periods, I see this

6

Andrei Bursuc @abursuc.bsky.social · 18d

A new season in full swing with a winning duo: kids do hockey, dad does overleaf

4

Andrei Bursuc @abursuc.bsky.social · 18d

Parents know that this is high bar for humans too.
But we’re aiming for super-human, aren’t we? 🙃

2

Andrei Bursuc @abursuc.bsky.social · 19d

The French often mention the roundabout at Arc de Triomphe as one of the ultimate tests for a self-driving vehicle.

I would say that the equivalent for humanoid robots would be to unwrap Chupa Chups Lollipop.

Take that Embodied AI!

3 1 18

Andrei Bursuc @abursuc.bsky.social · 19d

No time to shed tears post-NeurIPS when ICLR deadline is so close ...

7

Andrei Bursuc @abursuc.bsky.social · 20d

Congrats Christian et al.!

1 1

Andrei Bursuc @abursuc.bsky.social · 20d

Big congrats! Amazing work and team!

1 1

Reposted by Andrei Bursuc

Martin Trapp @trappmartin.bsky.social · 20d

Unfortunately, our submission to #NeurIPS didn’t go through with (5,4,4,3). But because I think it’s an excellent paper, I decided to share it anyway.

We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!

📝 arxiv.org/abs/2412.06014

Post-hoc Probabilistic Vision-Language Models

Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descripti...

arxiv.org

2 14 48

Reposted by Andrei Bursuc

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 20d

Our NeurIPS submission arxiv.org/abs/2502.08938 did not get in, but it's one of my favorite papers and I think one of the better papers we've ever put out so I want to highlight it

Reevaluating Policy Gradient Methods for Imperfect-Information Games

In the past decade, motivated by the putative failure of naive self-play deep reinforcement learning (DRL) in adversarial imperfect-information games, researchers have developed numerous DRL algorithm...

arxiv.org

5 8 74

Andrei Bursuc @abursuc.bsky.social · 22d

In the last weeks we noticed that our RangeViT was getting increasingly numerous citations from unrelated papers uploaded to ResearchGate and other platforms.
Check out the investigation of @gillespuy.bsky.social on this issue that may impact other papers too.

Gilles Puy @gillespuy.bsky.social · 22d

Discovered that our RangeViT paper keeps being cited in what might be LLM-generated papers. Number of citations increased rapidly in the last weeks. Too good to be true.

Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks.
[1/]

5

Reposted by Andrei Bursuc

David Picard @davidpicard.bsky.social · 22d

If you're interested in human pose estimation and mesh recovery from LiDAR data, we have this massive survey: arxiv.org/abs/2509.12197
Salma and Nermin put a tremendous amount of work in it, there's everything: the tasks, all the methods organized, datasets, numbers, challenges and opportunities.

3D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review

In this paper, we present a comprehensive review of 3D human pose estimation and human mesh recovery from in-the-wild LiDAR point clouds. We compare existing approaches across several key dimensions, ...

arxiv.org

8 20