ClaimsPeople

Yann LeCun

Yann LeCun is a computer scientist who shared the 2018 ACM Turing Award, is a Jacob T. Schwartz Professor at NYU's Courant Institute, was Meta's Chief AI Scientist and founding director of FAIR, and is Executive Chairman of AMI Labs.

1,175 claims collected, 197 researched, 84 resolved. Report of 4 November 2026, method 0.1.0+c876030c.

Scores by kind of claim

Each kind of claim is scored on its own, out of 100: the share that held up, with the range it likely falls in. Fewer resolved claims give a wider range.

  • Factual claims

    Statements about the present or the past, checked against the record: did they hold up?

    78 72 83

    High confidence, 79 factual claims resolved. From 16 documents, 2006 to 2026; 19 documents sampled from 33 candidates found.

    Not scored: 43 unresolvable.

  • Predictions

    Statements about events outside the person's control, checked once they fell due: did they come true?

    64 43 83

    Low confidence, 5 predictions resolved. From 4 documents, 2010 to 2024; 19 documents sampled from 33 candidates found.

    Not scored: 66 unresolvable. 3 more fall due later.

    Does not yet allow for how likely each prediction was when made.

  • Promises

    Commitments to the person's or organisation's own future action, with something to deliver: was it delivered?

    Insufficient record: 0 promises resolved, 5 needed for a score.

    Not scored: 1 unresolvable.

All types combined: 77 (likely 71 to 82, high confidence), from 84 claims: 79 factual claims, 5 predictions. It mixes kinds of claim in different proportions for different people, so compare people kind by kind.

Yann LeCun's claims

1,175 claims, sorted by newest said. Choose a claim to read it in full.
VerdictKindSaidClaimTopic
Resolved true Factual Jun 2023 LeCun's proposed AI architecture consists of multiple interconnected modules. Factual · Jun 2023 AI capabilities
Not checkable Not checkable Jun 2023 Therefore, latent variables enable multiple predictions instead of just one. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 So, we can recast the regularized AE as jointly Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 A promising approach is to combine masked AEs with transformers for images [57]. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 An important thing to note is that the energy function discussed here is used only for inference, not learning. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Thus, they give us a way of handling real-world uncertainty. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Finally, we need to minimize or limit the information content of the latent variable to prevent the model from, e.g., relying solely on… Not checkable · Jun 2023
Unresolvable Prediction Jun 2023 Contrastive methods are unlikely to lead to future autonomous intelligence because of their unfavorable scaling with data dimension. Prediction · Jun 2023 AI timelines and forecasting
Mostly true Factual Jun 2023 With probabilistic models, training is confined to loss functions derived from the negative log-likelihood, such as cross entropy. Factual · Jun 2023 AI capabilities
Not checkable Not checkable Jun 2023 However, for other architectures, such training may lead to the collapse of the energy function, i.e., given an x the energy landscape… Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Therefore, the path to fully autonomous human-like intelligence has three main challenges: Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Low energies should be assigned to compatible pairs of x and y (e.g., slow driving when snow is present) and high energies to incompatible… Not checkable · Jun 2023
Not researched Factual Jun 2023 For energy-based models with a continuous y domain, the energy function is smooth and differentiable, allowing gradient-based inference. Factual · Jun 2023 AI capabilities
Not checkable Not checkable Jun 2023 Here we summarized the main ideas of LeCun from Ref. [6] that address those limitations. Not checkable · Jun 2023
Not researched Factual Jun 2023 The lecture notes summarize the main ideas of the autonomous intelligence architecture proposed by Yann LeCun. Factual · Jun 2023 Their own work or organisation
Not checkable Not checkable Jun 2023 In reality, humans imagine most of the outcomes instead of trying them all. Not checkable · Jun 2023
Not researched Factual Jun 2023 SSL works very well for text, but for images, models trained to make a single prediction predict the average of all possible predictions. Factual · Jun 2023 AI capabilities
Not researched Citation Jun 2023 The method for maximizing information content of learned representations is called variance-invariance-covariance regularization (VICReg), per reference [58]. Citation · Jun 2023 AI capabilities
Not checkable Not checkable Jun 2023 The proposed solution to tackle multimodality is latent variable models with joint embeddings, and we discuss them in the next section. Not checkable · Jun 2023
Not researched Factual Jun 2023 Computing a partition function is very challenging, so probabilistic models in continuous high-dimensional domains are intractable. Factual · Jun 2023 AI capabilities
Not checkable Not checkable Jun 2023 The main principle of training an EBM is to sculpt the energy landscape such that data points that are probable or compatible have low… Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 The global task of this architecture is to take action that minimizes the cost or, even better, minimizes the expected cost in the future. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Such a hierarchical structure allows for multi-level representations of the world and, more Not checkable · Jun 2023
Not researched Factual Jun 2023 Some regularized autoencoders learn interpretable features that mirror existing hand-crafted data compression approaches. Factual · Jun 2023 AI capabilities
Not checkable Not checkable Jun 2023 The possible approach is designing reasoning and planning as energy minimization. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Finally, latent variables are useful in so-called structured prediction problems. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 The changes of the critic module model the external influence that is provided by culture, norms, and other people. Not checkable · Jun 2023
Not researched Factual Jun 2023 A major technique for detecting blacklisted content is nearest-neighbor search against that content. Factual · Jun 2023 AI capabilities
Not checkable Not checkable Jun 2023 In other words, this term decorrelates the representation components, encouraging the learning of different input data aspects. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Therefore, there is no need to use a probabilistic framework, as you just need scores for each situation (word/move, etc.), which in… Not checkable · Jun 2023
Mostly true Factual Jun 2023 All modules of the proposed architecture are fully differentiable. Factual · Jun 2023 AI capabilities
Not checkable Not checkable Jun 2023 If we train our model only to minimize the distance between the outputs of encoders, then the two encoders are likely to ignore inputs… Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Note that the marginal distribution is equivalent to Eq. (A1) in which the energy function has merely been redefined Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 In such high-dimensional and multi-modal real-world setups, we may need to give up the idea of representing probability distributions over… Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 Maximum likelihood needs to be then regularized, e.g., with Bayesian prior or by limiting values of model parameters. Not checkable · Jun 2023
Not researched Factual Jun 2023 Current self-driving models need thousands of footage to learn, while humans can learn to drive in about twenty hours. Factual · Jun 2023 AI capabilities
Unresolvable Prediction Jun 2023 Probabilistic models may also fail on the path to autonomous intelligence. Prediction · Jun 2023 AI timelines and forecasting
Not checkable Not checkable Jun 2023 Such an energy-guided model only needs to assign the lowest energy to the correct answer and larger energies to the incorrect ones. Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 In particular, precise predictions of the state of the world, based on the limited percepts of the environment, are possible Not checkable · Jun 2023
Not checkable Not checkable Jun 2023 EBMs, which do not have an immediate probabilistic interpretation, give much more flexibility in the choice of the training setup and, in… Not checkable · Jun 2023
Unresolvable Prediction 4 Mar 2021 Researchers may never develop techniques to represent suitable probability distributions over high-dimensional continuous spaces such as all possible video frames. Prediction · 4 Mar 2021 AI capabilities
Unresolvable Factual 4 Mar 2021 The Siamese network / joint embedding idea goes back to papers from Geoff Hinton's lab and Yann LeCun's group in the early 1990s. Factual · 4 Mar 2021 AI capabilities
Not checkable Not checkable 4 Mar 2021 We believe that self-supervised learning (SSL) is one of the most promising ways to build such background knowledge and approximate a form… Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Self-supervised learning enables AI systems to learn from orders of magnitude more data, which is important to recognize and understand… Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Without a specific way to do so, the two networks could happily ignore their inputs and always produce identical output embeddings. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Long-term progress will be cumulative. Not checkable · 4 Mar 2021
Resolved true Factual 4 Mar 2021 Language models pretrained with self-supervised learning achieve considerably higher performance than models trained solely in a supervised manner. Factual · 4 Mar 2021 AI capabilities
Mostly true Factual 4 Mar 2021 Facebook has deployed XLM-R, a model based on its RoBERTa architecture, to improve hate speech classifiers in multiple languages across Facebook and Instagram. Factual · 4 Mar 2021 AI capabilities
Not checkable Not checkable 4 Mar 2021 We cannot list all possible video frames and associate a score to each of them, because there is an infinite number of them. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Unsupervised learning is an ill-defined and misleading term that suggests that the learning uses no supervision at all. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Practically speaking, it’s impossible to label everything in the world. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Non-contrastive methods applied to joint embedding architectures is possibly the hottest topic in SSL for vision at the moment. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 The short answer is that humans rely on their previously acquired background knowledge of how the world works. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Unfortunately, there’s a limit to how far the field of AI can go with supervised learning alone. Not checkable · 4 Mar 2021
Unresolvable Prediction 4 Mar 2021 Perhaps, in the long run, non-contrastive methods with latent-variable predictive models will prove a better alternative. Prediction · 4 Mar 2021 AI capabilities
Mostly true Factual 4 Mar 2021 LeCun said Facebook AI had created and open sourced SEER, a billion-parameter self-supervised computer vision model that he described as proven to work efficiently with complex, high-dimensional image data. Factual · 4 Mar 2021 AI capabilities
Not checkable Not checkable 4 Mar 2021 In a way, common sense is the dark matter of artificial intelligence. Not checkable · 4 Mar 2021
Mostly true Factual 4 Mar 2021 As of March 2021, self-supervised learning had not yet brought computer vision the same improvements it has brought to natural language processing. Factual · 4 Mar 2021 AI capabilities
Not checkable Not checkable 4 Mar 2021 Latent-variable models can be trained with contrastive methods. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 No perfect recipe seems to exist to limit the capacity of latent variables. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Part one is simple, but part two is where the difficulty lies. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 In fact, self-supervised learning is not unsupervised, as it uses far more feedback signals than standard supervised and reinforcement… Not checkable · 4 Mar 2021
Mostly true Factual 4 Mar 2021 The Barlow Twins method tries to minimize redundancy between the individual components of the embedding vectors. Factual · 4 Mar 2021 AI capabilities
Not checkable Not checkable 4 Mar 2021 There is a way to think about SSL within the unified framework of an energy-based model (EBM). Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 A working hypothesis is that generalized knowledge about the world, or common sense, forms the bulk of biological intelligence in both… Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 These results show that we can bring the self-supervised learning paradigm shift to computer vision. Not checkable · 4 Mar 2021
Resolved true Factual 4 Mar 2021 After pretraining on a billion unlabeled Instagram images and fine-tuning on ImageNet, SEER outperformed state-of-the-art self-supervised systems, reaching 84.2 percent top-1 accuracy on ImageNet. Factual · 4 Mar 2021 AI capabilities
Not checkable Not checkable 4 Mar 2021 If the energy is low, x and y are deemed compatible; if it is high, they are deemed incompatible. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 The main reason is that it is considerably more difficult to represent uncertainty in the prediction for images than it is for words. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 But contrastive methods have a major issue: They are very inefficient to train. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Supervised learning is a bottleneck for building more intelligent generalist models that can do multiple tasks and acquire new skills… Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 This progress demonstrates that self-supervised learning can excel at CV tasks in complex, real-world settings as well. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 The method used to train NLP systems by masking or substituting some input words belongs to the category of contrastive methods. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 A particular well-suited deep learning architecture to do so is the so-called Siamese networks or joint embedding architecture. Not checkable · 4 Mar 2021
Not checkable Not checkable 4 Mar 2021 Self-supervision is one step on the path to human-level intelligence, but there are surely many steps that lie behind this one. Not checkable · 4 Mar 2021
Not checkable Not checkable 2021 But curiosity just makes the process faster. Not checkable · 2021
Not researched Factual 2021 Contrastive learning with positive and negative pairs does not work when the representation is high-dimensional, because there are too many ways for two things to be different. Factual · 2021 AI capabilities
Not researched Factual 2021 In MIT experiments where a baby ferret's optic nerve is connected to the auditory cortex, the auditory cortex becomes essentially a visual cortex. Factual · 2021 Science and research methods
Not checkable Not checkable 2021 You have to have somewhere representing a sort of infinite number of plausible continuations of multiple frames in a high dimensional… Not checkable · 2021
Not checkable Not checkable 2021 I think it's integrated. Not checkable · 2021
Not checkable Not checkable 2021 That's called a collapse. Not checkable · 2021
Not researched Factual 2021 In the first months of life, babies learn how the world works mostly by observation because they can hardly act in the world. Factual · 2021 Philosophy, ethics and society
Not researched Factual 2021 Across AI sub-fields there has been a continuous evolution from less hand-crafting to more learning. Factual · 2021 AI capabilities
Not checkable Not checkable 2021 It is, but we're not there yet. Not checkable · 2021
Not checkable Not checkable 2021 So it's easier to learn when your objective is intrinsic. Not checkable · 2021
Not checkable Not checkable 2021 So that has to be hardwired. Not checkable · 2021
Not researched Factual 2021 People have used data augmentation on MNIST digits since the 1990s. Factual · 2021 AI capabilities
Not researched Factual 2021 Geoffrey Hinton proposed, in the early 1990s with his student Sue Becker, the idea of maximizing mutual information between the outputs of two systems. Factual · 2021 AI capabilities
Not checkable Not checkable 2021 Supervised learning requires many samples for learning anything. Not checkable · 2021
Not checkable Not checkable 2021 I don't know how to make logic-based reasoning Not checkable · 2021
Not checkable Not checkable 2021 It doesn't tell us how to feed ourselves. Not checkable · 2021
Not researched Factual 2021 After self-supervised representation learning, recognizing handwritten digits on top of it requires only a few labeled samples. Factual · 2021 AI capabilities
Not checkable Not checkable 2021 It's not platonic because eventually I want the stuff to get used, but it's okay if it takes five or 10 years for the community to realize… Not checkable · 2021
Not researched Factual 2021 The difference between human and chimp genomes involved in human intelligence is less than 1% of the genome. Factual · 2021 Science and research methods
Not checkable Not checkable 2021 I have kind of an orthodox folk speculative hypothesis about consciousness. Not checkable · 2021
Not researched Factual 2021 The system under discussion worked, but they ended up not using it. Factual · 2021 Technology
Not researched Factual 2021 LeCun used to call the two-identical-copies network architecture a Siamese network. Factual · 2021 AI capabilities
Not checkable Not checkable 2021 I mean, it's a superficial understanding, obviously. Not checkable · 2021
Not researched Factual 2021 With a differentiable world model such as a neural net, one can do gradient-based model predictive control by backpropagating through it. Factual · 2021 AI capabilities
Unresolvable Prediction 2021 Training systems on video prediction with self-supervised techniques will provide a path towards some level of physical common sense in machines. Prediction · 2021 AI capabilities
Back to the list

Yann LeCun

Open its page

Not checkable

“These results show that we can bring the self-supervised learning paradigm shift to computer vision.”

Yann LeCun 4 March 2021 Self-supervised learning: The dark matter of intelligence (Meta AI)

These results show that we can bring the self-supervised learning paradigm shift to computer vision.

Not checkable An opinion, value judgement or statement with nothing to check.

Cite this claim

Yann LeCun, “These results show that we can bring the self-supervised learning paradigm shift to computer vision.” (said 4 March 2021). Verdict: not checkable. Reliability API, claim c_b5b56711b1fe, method 0.1.0+c876030c. https://epistacklabs.com/claims/c_b5b56711b1fe

Claims without a verdict

Is a verdict here wrong, or do you speak for Yann LeCun? Reply on the claim's own page, with the form at its foot (how replies work). Verdicts are made automatically; how verdicts and scores are made.