←
CVPR News2,191 posts
CVPR News avatar

CVPR News

@CVPRConf

Computer Vision and Pattern Recognition News

◷ Joined September 2018▧ 25 Photos and videos
SanghyukChun avatar
⟳ CVPR News retweeted
SanghyukChun@SanghyukChun·Nov 15

What is the meaning of asking "did you complete a phd program" for being an author or reviewer at CVPR? 🤷

Post attachment
Shumpei Takezaki avatar
⟳ CVPR News retweeted
Shumpei Takezaki@shumpeiMaxwell·Nov 15

Dataset Distillation via Drifting TL;DR: A new dataset distillation approach that matches data distributions rather than optimizing classification losses. By combining attraction to real data and repulsion among synthetic samples in pretrained feature spaces, it improves diversity and achieves 27.0% ImageNet-1K accuracy with just 10 images/class. arxiv.org/abs/2611.16642

Siddhartha Gairola avatar
⟳ CVPR News retweeted
Siddhartha Gairola@sidgairo18·Nov 15

As of today #ICLR2027 has 37k active submissions, 3.8k withdraws and 1.7k desk rejects. For those still fighting may the force be with you 💪

AI Conference DL Countdown avatar
⟳ CVPR News retweeted
AI Conference DL Countdown@DlCountdown·Nov 14

CVPR'27 (paper): 3 days + 2h. RSS'27 (ext-abs): 21 days. IJCAI'27 (reg): 52 days. IJCAI'27 (paper): 59 days. RSS'27 (paper): 154 days.

Vincent Sitzmann avatar
⟳ CVPR News retweeted
Vincent Sitzmann@vincesitzmann·Oct 22

I have talked much about the "bitter lesson" of computer vision, arguing that many of the intermediate tasks that vision has solved traditionally - 3D reconstruction, segmentation, tracking, etc - are not necessary to build AI that understands the world through vision... (1/n)

In my recent blog post, I argue that "vision" is only well-defined as part of perception-action loops, and that the conventional view of computer vision - mapping imagery to intermediate representations (3D, flow, segmentation...) is about to go away. vincentsitzmann.com/blog/bit…

Angela Dai avatar
⟳ CVPR News retweeted
Angela Dai@angelaqdai·Oct 22

very cool team working on spatial ai :)

Thrilled to announce the @SpAItial_AI PhD Intern program. Work with a team of exceptional researchers. Build foundation models with lots of GPUs and publish the results at a top-tier conference. Incredibly happy to strengthen the connection between academia and frontier AI🤝

Yi Ma avatar
⟳ CVPR News retweeted
Yi Ma@YiMaTweets·Oct 22

The lectures of my new course "Principles of Deep Representation Learning" are now available at the Youtube site: youtube.com/playlist?list=PL… with new lectures continuing to be added there. I will open-source all the slides later in the textbook website: ma-lab-berkeley.github.io/de…

AI Conference DL Countdown avatar
⟳ CVPR News retweeted
AI Conference DL Countdown@DlCountdown·Oct 22

CVPR'27 (reg): 20 days. CVPR'27 (paper): 26 days. RSS'27 (ext-abs): 44 days. IJCAI'27 (reg): 75 days. IJCAI'27 (paper): 82 days. RSS'27 (paper): 177 days.

Hilde Kuehne avatar
⟳ CVPR News retweeted
Hilde Kuehne@HildeKuehne·Sep 25

I'm currently writing and editing ICLR submission (and yes, I'm a dinosaur. I still do this by hand, no AI, just a spell checker) and I realized that when I work on a paper, at every step I try to imagine how someone would read this. Is the information clear? Will they get the point? Do they need more information (or less)? This is how communication works ...

Vincent Sitzmann avatar
⟳ CVPR News retweeted
Vincent Sitzmann@vincesitzmann·Sep 26

This paper has been accepted at NeurIPS! Meet the team in Sydney!

We discovered that our latest Dataset Distillation project can be used to create some beautiful synthetic images based on an artist's body of work! Come see us at the @eccvconf Art Gallery starting today! Explanation and some of my favorites in thread below: 1/ (Claude Monet)

Post attachment
AI Conference DL Countdown avatar
⟳ CVPR News retweeted
AI Conference DL Countdown@DlCountdown·Sep 25

CLR'27 (paper): 1 day, good luck! AAMAS'27 (reg): 7 days. AAMAS'27 (paper): 14 days. CVPR'27 (reg): 47 days. CVPR'27 (paper): 53 days.

Irina Rish avatar
⟳ CVPR News retweeted
Irina Rish@irinarish·Sep 24

Very interesting and timely work!

Our new work on “Physics of Agents” arxiv.org/abs/2608.16578 lead by Batu El and Jinhee Paeng in collab w/ @james_y_zou The outcome of many interacting agents seems hard to reason about. Yet we were able to study the opinion dynamics of 10,000 different LLM agent communities as they communicated with each other to solve both objective and subjective questions. Remarkably, we could account for their opinion dynamics through a simple Ising model that involved minimizing an energy function corresponding to social pressure to conform. Our dynamics could explain the build up of consensus, polarization, and societal correction of initially incorrect majorities. Lots more to do on statistical mechanics of interacting agent dynamics!

Andrew Ng avatar
⟳ CVPR News retweeted
Andrew Ng@AndrewYNg·Sep 21

The loudest voices stoking fears about AI dangers have made tremendous headway in the past two weeks. AI technology has not taken some unexpected, dangerous turn, but the hype around it — propelled by what appears to be a well orchestrated PR campaign — has drummed up considerable fear. I worry that it represents a setback for our field. I have written frequently that fears of AI are overhyped. AI’s capabilities can be uncannily human-like and unpredictable, and it’s rational to worry when people who are directly involved express concerns. But I see the problems as a sign of the engineering work that ahead, rather than insurmountable barriers or the sky falling. AI technology continues to advance — which is a good thing! — but technical advances, poorly understood by the public, give those who seek to generate hype repeated opportunities to do so. First, I don’t see any step up in the risk of human extinction from AI compared to a few months ago. The theories about this remain the same fantastical, science fiction scenarios as a few months ago. The biggest change in AI risk is its cybersecurity capabilities — a topic which we should take seriously — but this, too, will not lead to the end of the world. The most notable recent event leading to increased fear was when an OpenAI team deployed an agent swarm that hacked into Hugging Face. Much of the popular press contained significant hype. For example, some publications reported that a swarm of 1,200 agents carried out the attack. While this was technically accurate, as I write this, I have about 1,300 processes running on my laptop. Yes, the ability to get large swarms of agents to work in parallel on a task is a significant technical advance, And, in computing, many processes run at the same time. So this shouldn’t be seen as some magical capability. Additionally, OpenAI’s buggy sandboxing and monitoring processes were key to enabling this incident. Fixing these bugs and putting in place improved monitoring would be appropriate fixes, not pausing AI. There are many well known ways to attack software systems. The main advantage of AI agents is that they are relentless. They will tirelessly try many tactics — and have the patience to chain vulnerabilities together — that previously would have taken an infeasible amount of human effort. But in the long term, I believe the advantage will lie with defenders (because they have more information with which to identify bugs, which they can fix), but the cyber-threat landscape has changed significantly. There are still bottlenecks to identifying and exploiting a vulnerability. AI agents still have to try a lot of things to see what works, and taking these actions takes time and might be detected by defenders. This is why, even though it is now easy to obtain versions of leading open weight models that have had their guardrails removed or weakened, so they will not refuse to try to execute cyber attacks, the world has not ended. I am also concerned about the anthropomorphization of AI in a lot of reporting, where LLMs and agents are unnecessarily treated as if they were people. If I wield a hammer, miss a nail, and accidentally dent the wall, it’s not the fault of the hammer. The problem lies in how I used the hammer. Similarly, if I prompt an agent and it hacks into someone else’s system, the responsibility lies with me, not the agent. Of course, we want to build systems that are as safe and predictable as possible. (For example, an unsafe hammer would be one whose head randomly flies off under normal use.) Today’s agentic systems are not predictable, but I see no reason why, by applying sound engineering practices, we won’t be able to make them extremely safe to use. One new element in the forecasts of AI-enabled doom is AI companies disclaiming responsibility for their own products. “I didn’t do it; my out-of-control agent did!” There’s a balance to be struck between the responsibility of the tool maker and the tool user, but when something goes wrong, let’s hold the people building and/or using the hammer responsible, rather than the hammer. (By the way, if you’re worried about AI bioweapon risk, David Bellamy has a great post on why this, too, is overhyped. Briefly, the bottleneck in building a bioweapon is not intelligence, but lab work and manufacturing.) Pausing AI progress will create much more harm than benefit. First, our adversaries will certainly not slow down. Second, engineering requires discovering problems empirically so we can fix them. If we pause AI by a decade, we will also delay finding and implementing safety engineering fixes by about the same duration. Of course, the incentive to stoke fears — for regulatory capture, to garner attention, or to make one’s technology seem more powerful — remains the same as before. Disclaiming responsibility is a new one. Taking a hard technical look at the actual risks however, I see little factual basis for the degree of fear that’s been stoked up. We still have hard research and engineering work ahead to improve AI safety, but the beneficial applications continue to vastly outweigh the risks, and we should keep building. [Original text (with links): deeplearning.ai/the-batch/is… ]

M. Alex O. Vasilescu avatar
⟳ CVPR News retweeted
M. Alex O. Vasilescu@AlexTensor·Sep 21

Never attribute to autonomous rogue AI that which is fully explained by skipped cyber security and corporate negligence. -- Hanlon's Razor with an AI twist.

The loudest voices stoking fears about AI dangers have made tremendous headway in the past two weeks. AI technology has not taken some unexpected, dangerous turn, but the hype around it — propelled by what appears to be a well orchestrated PR campaign — has drummed up considerable fear. I worry that it represents a setback for our field. I have written frequently that fears of AI are overhyped. AI’s capabilities can be uncannily human-like and unpredictable, and it’s rational to worry when people who are directly involved express concerns. But I see the problems as a sign of the engineering work that ahead, rather than insurmountable barriers or the sky falling. AI technology continues to advance — which is a good thing! — but technical advances, poorly understood by the public, give those who seek to generate hype repeated opportunities to do so. First, I don’t see any step up in the risk of human extinction from AI compared to a few months ago. The theories about this remain the same fantastical, science fiction scenarios as a few months ago. The biggest change in AI risk is its cybersecurity capabilities — a topic which we should take seriously — but this, too, will not lead to the end of the world. The most notable recent event leading to increased fear was when an OpenAI team deployed an agent swarm that hacked into Hugging Face. Much of the popular press contained significant hype. For example, some publications reported that a swarm of 1,200 agents carried out the attack. While this was technically accurate, as I write this, I have about 1,300 processes running on my laptop. Yes, the ability to get large swarms of agents to work in parallel on a task is a significant technical advance, And, in computing, many processes run at the same time. So this shouldn’t be seen as some magical capability. Additionally, OpenAI’s buggy sandboxing and monitoring processes were key to enabling this incident. Fixing these bugs and putting in place improved monitoring would be appropriate fixes, not pausing AI. There are many well known ways to attack software systems. The main advantage of AI agents is that they are relentless. They will tirelessly try many tactics — and have the patience to chain vulnerabilities together — that previously would have taken an infeasible amount of human effort. But in the long term, I believe the advantage will lie with defenders (because they have more information with which to identify bugs, which they can fix), but the cyber-threat landscape has changed significantly. There are still bottlenecks to identifying and exploiting a vulnerability. AI agents still have to try a lot of things to see what works, and taking these actions takes time and might be detected by defenders. This is why, even though it is now easy to obtain versions of leading open weight models that have had their guardrails removed or weakened, so they will not refuse to try to execute cyber attacks, the world has not ended. I am also concerned about the anthropomorphization of AI in a lot of reporting, where LLMs and agents are unnecessarily treated as if they were people. If I wield a hammer, miss a nail, and accidentally dent the wall, it’s not the fault of the hammer. The problem lies in how I used the hammer. Similarly, if I prompt an agent and it hacks into someone else’s system, the responsibility lies with me, not the agent. Of course, we want to build systems that are as safe and predictable as possible. (For example, an unsafe hammer would be one whose head randomly flies off under normal use.) Today’s agentic systems are not predictable, but I see no reason why, by applying sound engineering practices, we won’t be able to make them extremely safe to use. One new element in the forecasts of AI-enabled doom is AI companies disclaiming responsibility for their own products. “I didn’t do it; my out-of-control agent did!” There’s a balance to be struck between the responsibility of the tool maker and the tool user, but when something goes wrong, let’s hold the people building and/or using the hammer responsible, rather than the hammer. (By the way, if you’re worried about AI bioweapon risk, David Bellamy has a great post on why this, too, is overhyped. Briefly, the bottleneck in building a bioweapon is not intelligence, but lab work and manufacturing.) Pausing AI progress will create much more harm than benefit. First, our adversaries will certainly not slow down. Second, engineering requires discovering problems empirically so we can fix them. If we pause AI by a decade, we will also delay finding and implementing safety engineering fixes by about the same duration. Of course, the incentive to stoke fears — for regulatory capture, to garner attention, or to make one’s technology seem more powerful — remains the same as before. Disclaiming responsibility is a new one. Taking a hard technical look at the actual risks however, I see little factual basis for the degree of fear that’s been stoked up. We still have hard research and engineering work ahead to improve AI safety, but the beneficial applications continue to vastly outweigh the risks, and we should keep building. [Original text (with links): deeplearning.ai/the-batch/is… ]