Goto

Collaborating Authors

 France


American tennis star Danielle Collins accuses cameraman of 'wildly inappropriate' behavior

FOX News

PongBot is an artificial intelligence-powered tennis robot. American tennis player Danielle Collins had some choice words for the cameraman during her Internationaux de Strasbourg match against Emma Raducanu on Wednesday afternoon. Collins was in the middle of a changeover when she felt the cameraman's hovering was a bit too close for comfort in the middle of the third and defining set. She got off the bench and made the point clear. Danielle Collins celebrates during her match against Madison Keys in the third round of the women's singles at the 2025 Australian Open at Melbourne Park in Melbourne, Australia, on Jan. 18, 2025.


ColdGANs: Taming Language GANs with Cautious Sampling Strategies Thomas Scialom, Paul-Alexis Dray

Neural Information Processing Systems

Training regimes based on Maximum Likelihood Estimation (MLE) suffer from known limitations, often leading to poorly generated text sequences. At the root of these limitations is the mismatch between training and inference, i.e. the so-called exposure bias, exacerbated by considering only the reference texts as correct, while in practice several alternative formulations could be as good. Generative Adversarial Networks (GANs) can mitigate those limitations but the discrete nature of text has hindered their application to language generation: the approaches proposed so far, based on Reinforcement Learning, have been shown to underperform MLE. Departing from previous works, we analyze the exploration step in GANs applied to text generation, and show how classical sampling results in unstable training. We propose to consider alternative exploration strategies in a GAN framework that we name ColdGANs, where we force the sampling to be close to the distribution modes to get smoother learning dynamics. For the first time, to the best of our knowledge, the proposed language GANs compare favorably to MLE, and obtain improvements over the state-of-the-art on three generative tasks, namely unconditional text generation, question generation, and abstractive summarization.


Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild

Neural Information Processing Systems

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established adaptor modules like LoRA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the out-of-distribution concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The aesthetics score and concept-matching score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric.


Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification - supplementary material Francesca Mignacco

Neural Information Processing Systems

The derivation of the self-consistent stochastic process discussed in the main text can be obtained using tools of statistical physics of disordered systems. In particular, it has been done very recently for a related model, the spherical perceptron with random labels, in [1]. Our derivation extends the known DMFT equations by including structure in the data; a stochastic version of gradient descent as discussed in the main text; the relaxation of the spherical constraint over the weights and the introduction of a Ridge regularization term. There are at least two ways to write the DMFT equations. One is by using field theoretical techniques; otherwise one can employ a dynamical version of the so-called cavity method [2].


Your eyes can reveal the accuracy of your memories

Popular Science

Breakthroughs, discoveries, and DIY tips sent every weekday. We like to think our brains are reliable recorders--but reality says otherwise. From misremembered childhood moments to mistakenly "recalling" that you took your pills when you didn't, false memories are surprisingly common. And in high-stakes situations like courtroom testimony, these errors can have devastating consequences. Wouldn't it be amazing if there were an objective way to measure just how accurate someone's memory really is? New research suggests we might be able to do just that--by watching the eyes.


Munchausen Reinforcement Learning

Neural Information Processing Systems

Bootstrapping is a core mechanism in Reinforcement Learning (RL). Most algorithms, based on temporal differences, replace the true value of a transiting state by their current estimate of this value. Yet, another estimate could be leveraged to bootstrap RL: the current policy. Our core contribution stands in a very simple idea: adding the scaled log-policy to the immediate reward. We show that slightly modifying Deep Q-Network (DQN) in that way provides an agent that is competitive with distributional methods on Atari games, without making use of distributional RL, n-step returns or prioritized replay. To demonstrate the versatility of this idea, we also use it together with an Implicit Quantile Network (IQN). The resulting agent outperforms Rainbow on Atari, installing a new State of the Art with very little modifications to the original algorithm. To add to this empirical study, we provide strong theoretical insights on what happens under the hood - implicit Kullback-Leibler regularization and increase of the action-gap.


Factcheck: Was cocaine on the table in Macron video with Starmer, Merz?

Al Jazeera

Conspiracy theorist Alex Jones seized on a May 9 video of a train car meeting among three European leaders to claim they had used drugs and were trying to hide it. The video showed French President Emmanuel Macron sitting at a table with German Chancellor Friedrich Merz and United Kingdom Prime Minister Keir Starmer. On the table before them were two blue folders, two drinking glasses and a small white object. The three men smiled for photographers who had gathered. Just as the shutter clicks started, Macron removed the crumpled white object from the tabletop and held it in his fist.


Terrifying brain glitch discovered that instantly leaves millions of people feeling lost and confused

Daily Mail - Science & tech

Scientists have discovered a new brain glitch that is the exact opposite of deja vu. While deja vu is the unsettling sense that you've lived a moment before, jamais vu is when something familiar suddenly feels alien -- like encountering it for the very first time. You've likely felt it: walking through your hometown and suddenly feeling lost, or repeating a common word until it sounds strange and meaningless. Repetition is often the trigger. The brain, overloaded by familiarity, short-circuits, making the ordinary feel bizarre.


Identifying Obfuscated Code through Graph-Based Semantic Analysis of Binary Code

arXiv.org Machine Learning

Protecting sensitive program content is a critical issue in various situations, ranging from legitimate use cases to unethical contexts. Obfuscation is one of the most used techniques to ensure such protection. Consequently, attackers must first detect and characterize obfuscation before launching any attack against it. This paper investigates the problem of function-level obfuscation detection using graph-based approaches, comparing algorithms, from elementary baselines to promising techniques like GNN (Graph Neural Networks), on different feature choices. We consider various obfuscation types and obfuscators, resulting in two complex datasets. Our findings demonstrate that GNNs need meaningful features that capture aspects of function semantics to outperform baselines. Our approach shows satisfactory results, especially in a challenging 11-class classification task and in a practical malware analysis example.


The Download: generative AI therapy, and the future of 23andMe's genetic data

MIT Technology Review

June 2022 Across the world, video cameras have become an accepted feature of urban life. Many cities in China now have dense networks of them, and London and New Delhi aren't far behind. Now France is playing catch-up. Concerns have been raised throughout the country. But the surveillance rollout has met special resistance in Marseille, France's second-biggest city. It's unsurprising, perhaps, that activists are fighting back against the cameras, highlighting the surveillance system's overreach and underperformance.