François Fleuret

FAIR CodeGen team, Jade Copet, Quentin Carbonneaux et al. · meta-ai

We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can be learned from training on static code alone, we mid-train CWM on a large amount of observation-action trajectories from Python interpreter and agentic Docker environments, and perform extensive multi-task reasoning RL in verifiable coding, math, and multi-turn software engineering environments. With CWM, we provide a strong testbed for researchers to explore the opportunities world modeling affords for improving code generation with reasoning and planning in computational environments. We present first steps of how world models can benefit agentic coding, enable step-by-step simulation of Python code execution, and show early results of how reasoning can benefit from the latter. CWM is a dense, decoder-only LLM trained with a context size of up to 131k tokens. Independent of its world modeling capabilities, CWM offers strong performance on general coding and math tasks: it reaches pass@1 scores of 65.8% on SWE-bench Verified (with test-time scaling), 68.6% on LiveCodeBench, 96.6% on Math-500, and 76.0% on AIME 2024. To support further research on code world modeling, we release model checkpoints after mid-training, SFT, and RL.

Vincent Micheli, Eloi Alonso, François Fleuret

Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been designed to address this issue, with learning in the imagination of a world model being one of the most prominent approaches. However, while virtually unlimited interaction with a simulated environment sounds appealing, the world model has to be accurate over extended periods of time. Motivated by the success of Transformers in sequence modeling tasks, we introduce IRIS, a data-efficient agent that learns in a world model composed of a discrete autoencoder and an autoregressive Transformer. With the equivalent of only two hours of gameplay in the Atari 100k benchmark, IRIS achieves a mean human normalized score of 1.046, and outperforms humans on 10 out of 26 games, setting a new state of the art for methods without lookahead search. To foster future research on Transformers and world models for sample-efficient reinforcement learning, we release our code and models at https://github.com/eloialonso/iris.

Nikolaos Dimitriadis, Pascal Frossard, François Fleuret

In Multi-Task Learning (MTL), tasks may compete and limit the performance achieved on each other, rather than guiding the optimization to a solution, superior to all its single-task trained counterparts. Since there is often not a unique solution optimal for all tasks, practitioners have to balance tradeoffs between tasks' performance, and resort to optimality in the Pareto sense. Most MTL methodologies either completely neglect this aspect, and instead of aiming at learning a Pareto Front, produce one solution predefined by their optimization schemes, or produce diverse but discrete solutions. Recent approaches parameterize the Pareto Front via neural networks, leading to complex mappings from tradeoff to objective space. In this paper, we conjecture that the Pareto Front admits a linear parameterization in parameter space, which leads us to propose \textit{Pareto Manifold Learning}, an ensembling method in weight space. Our approach produces a continuous Pareto Front in a single training run, that allows to modulate the performance on each task during inference. Experiments on multi-task learning benchmarks, ranging from image classification to tabular datasets and scene understanding, show that \textit{Pareto Manifold Learning} outperforms state-of-the-art single-point algorithms, while learning a better Pareto parameterization than multi-point baselines.

Matteo Pagliardini, Daniele Paliotta, Martin Jaggi et al.

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t. the sequence length -- becomes a central concern. While many works have proposed schemes to sparsify the attention patterns and reduce the computational overhead of self-attention, those are often limited by implementations concerns and end up imposing a simple and static structure over the attention matrix. Conversely, implementing more dynamic sparse attentions often results in runtimes significantly slower than computing the full attention using the Flash implementation from Dao et al. (2022). We extend FlashAttention to accommodate a large class of attention sparsity patterns that, in particular, encompass key/query dropping and hashing-based attention. This leads to implementations with no computational complexity overhead and a multi-fold runtime speedup on top of FlashAttention. Even with relatively low degrees of sparsity, our method improves visibly upon FlashAttention as the sequence length increases. Without sacrificing perplexity, we increase the training speed of a transformer language model by $2.0\times$ and $3.3\times$ for sequences of respectively $8k$ and $16k$ tokens.

Bálint Máté, Samuel Klein, Tobias Golling et al.

The two key characteristics of a normalizing flow is that it is invertible (in particular, dimension preserving) and that it monitors the amount by which it changes the likelihood of data points as samples are propagated along the network. Recently, multiple generalizations of normalizing flows have been introduced that relax these two conditions. On the other hand, neural networks only perform a forward pass on the input, there is neither a notion of an inverse of a neural network nor is there one of its likelihood contribution. In this paper we argue that certain neural network architectures can be enriched with a stochastic inverse pass and that their likelihood contribution can be monitored in a way that they fall under the generalized notion of a normalizing flow mentioned above. We term this enrichment flowification. We prove that neural networks only containing linear layers, convolutional layers and invertible activations such as LeakyReLU can be flowified and evaluate them in the generative setting on image datasets.

Mohammad Mahdi Johari, Camilla Carta, François Fleuret

We present ESLAM, an efficient implicit neural representation method for Simultaneous Localization and Mapping (SLAM). ESLAM reads RGB-D frames with unknown camera poses in a sequential manner and incrementally reconstructs the scene representation while estimating the current camera position in the scene. We incorporate the latest advances in Neural Radiance Fields (NeRF) into a SLAM system, resulting in an efficient and accurate dense visual SLAM method. Our scene representation consists of multi-scale axis-aligned perpendicular feature planes and shallow decoders that, for each point in the continuous space, decode the interpolated features into Truncated Signed Distance Field (TSDF) and RGB values. Our extensive experiments on three standard datasets, Replica, ScanNet, and TUM RGB-D show that ESLAM improves the accuracy of 3D reconstruction and camera localization of state-of-the-art dense visual SLAM methods by more than 50%, while it runs up to 10 times faster and does not require any pre-training.

Evann Courdier, Prabhu Teja Sivaprasad, François Fleuret

We study the problem of improving the efficiency of segmentation transformers by using disparate amounts of computation for different parts of the image. Our method, PAUMER, accomplishes this by pausing computation for patches that are deemed to not need any more computation before the final decoder. We use the entropy of predictions computed from intermediate activations as the pausing criterion, and find this aligns well with semantics of the image. Our method has a unique advantage that a single network trained with the proposed strategy can be effortlessly adapted at inference to various run-time requirements by modulating its pausing parameters. On two standard segmentation datasets, Cityscapes and ADE20K, we show that our method operates with about a $50\%$ higher throughput with an mIoU drop of about $0.65\%$ and $4.6\%$ respectively.

Bálint Máté, François Fleuret

We introduce a training objective for continuous normalizing flows that can be used in the absence of samples but in the presence of an energy function. Our method relies on either a prescribed or a learnt interpolation $f_t$ of energy functions between the target energy $f_1$ and the energy function of a generalized Gaussian $f_0(x) = ||x/σ||_p^p$. The interpolation of energy functions induces an interpolation of Boltzmann densities $p_t \propto e^{-f_t}$ and we aim to find a time-dependent vector field $V_t$ that transports samples along the family $p_t$ of densities. The condition of transporting samples along the family $p_t$ is equivalent to satisfying the continuity equation with $V_t$ and $p_t = Z_t^{-1}e^{-f_t}$. Consequently, we optimize $V_t$ and $f_t$ to satisfy this partial differential equation. We experimentally compare the proposed training objective to the reverse KL-divergence on Gaussian mixtures and on the Boltzmann density of a quantum mechanical particle in a double-well potential.

Arnaud Pannatier, Kyle Matoba, François Fleuret

Real-world problems often involve complex and unstructured sets of measurements, which occur when sensors are sparsely placed in either space or time. Being able to model this irregular spatiotemporal data and extract meaningful forecasts is crucial. Deep learning architectures capable of processing sets of measurements with positions varying from set to set, and extracting readouts anywhere are methodologically difficult. Current state-of-the-art models are graph neural networks and require domain-specific knowledge for proper setup. We propose an attention-based model focused on robustness and practical applicability, with two key design contributions. First, we adopt a ViT-like transformer that takes both context points and read-out positions as inputs, eliminating the need for an encoder-decoder structure. Second, we use a unified method for encoding both context and read-out positions. This approach is intentionally straightforward and integrates well with other systems. Compared to existing approaches, our model is simpler, requires less specialized knowledge, and does not suffer from a problematic bottleneck effect, all of which contribute to superior performance. We conduct in-depth ablation studies that characterize this problematic bottleneck in the latent representations of alternative models that inhibit information utilization and impede training efficiency. We also perform experiments across various problem domains, including high-altitude wind nowcasting, two-day weather forecasting, fluid dynamics, and heat diffusion. Our attention-based model consistently outperforms state-of-the-art models in handling irregularly sampled data. Notably, our model reduces the root mean square error (RMSE) for wind nowcasting from 9.24 to 7.98 and for heat diffusion tasks from 0.126 to 0.084.

Daniele Paliotta, Mathieu Alain, Bálint Máté et al.

We present the Graph Forward-Forward (GFF) algorithm, an extension of the Forward-Forward procedure to graphs, able to handle features distributed over a graph's nodes. This allows training graph neural networks with forward passes only, without backpropagation. Our method is agnostic to the message-passing scheme, and provides a more biologically plausible learning scheme than backpropagation, while also carrying computational advantages. With GFF, graph neural networks are trained greedily layer by layer, using both positive and negative samples. We run experiments on 11 standard graph property prediction tasks, showing how GFF provides an effective alternative to backpropagation for training graph neural networks. This shows in particular that this procedure is remarkably efficient in spite of combining the per-layer training with the locality of the processing in a GNN.

Kyle Matoba, Nikolaos Dimitriadis, François Fleuret

Over the decade since deep neural networks became state of the art image classifiers there has been a tendency towards less use of max pooling: the function that takes the largest of nearby pixels in an image. Since max pooling featured prominently in earlier generations of image classifiers, we wish to understand this trend, and whether it is justified. We develop a theoretical framework analyzing ReLU based approximations to max pooling, and prove a sense in which max pooling cannot be efficiently replicated using ReLU activations. We analyze the error of a class of optimal approximations, and find that whilst the error can be made exponentially small in the kernel size, doing so requires an exponentially complex approximation. Our work gives a theoretical basis for understanding the trend away from max pooling in newer architectures. We conclude that the main cause of a difference between max pooling and an optimal approximation, a prevalent large difference between the max and other values within pools, can be overcome with other architectural decisions, or is not prevalent in natural images.

Bálint Máté, François Fleuret

Consider a one-parameter family of Boltzmann distributions $p_t(x) = \tfrac{1}{Z_t}e^{-S_t(x)}$. This work studies the problem of sampling from $p_{t_0}$ by first sampling from $p_{t_1}$ and then applying a transformation $Ψ_{t_1}^{t_0}$ so that the transformed samples follow $p_{t_0}$. We derive an equation relating $Ψ$ and the corresponding family of unnormalized log-likelihoods $S_t$. The utility of this idea is demonstrated on the $φ^4$ lattice field theory by extending its defining action $S_0$ to a family of actions $S_t$ and finding a $τ$ such that normalizing flows perform better at learning the Boltzmann distribution $p_τ$ than at learning $p_0$.

Ramón Calvo-González, François Fleuret

Recent work has shown that diffusion models can generate high-quality images by operating directly on SSL patch features rather than pixel-space latents. However, the dense patch grids from encoders like DINOv2 contain significant redundancy, making diffusion needlessly expensive. We introduce FlatDINO, a variational autoencoder that compresses this representation into a one-dimensional sequence of just 32 continuous tokens -an 8x reduction in sequence length and 48x compression in total dimensionality. On ImageNet 256x256, a DiT-XL trained on FlatDINO latents achieves a gFID of 1.80 with classifier-free guidance while requiring 8x fewer FLOPs per forward pass and up to 4.5x fewer FLOPs per training step compared to diffusion on uncompressed DINOv2 features. These are preliminary results and this work is in progress.

Eloi Alonso, Adam Jelley, Vincent Micheli et al.

World models constitute a promising approach for training reinforcement learning agents in a safe and sample-efficient manner. Recent world models predominantly operate on sequences of discrete latent variables to model environment dynamics. However, this compression into a compact discrete representation may ignore visual details that are important for reinforcement learning. Concurrently, diffusion models have become a dominant approach for image generation, challenging well-established methods modeling discrete latents. Motivated by this paradigm shift, we introduce DIAMOND (DIffusion As a Model Of eNvironment Dreams), a reinforcement learning agent trained in a diffusion world model. We analyze the key design choices that are required to make diffusion suitable for world modeling, and demonstrate how improved visual details can lead to improved agent performance. DIAMOND achieves a mean human normalized score of 1.46 on the competitive Atari 100k benchmark; a new best for agents trained entirely within a world model. We further demonstrate that DIAMOND's diffusion world model can stand alone as an interactive neural game engine by training on static Counter-Strike: Global Offensive gameplay. To foster future research on diffusion for world modeling, we release our code, agents, videos and playable world models at https://diamond-wm.github.io.

Vincent Micheli, Eloi Alonso, François Fleuret

Scaling up deep Reinforcement Learning (RL) methods presents a significant challenge. Following developments in generative modelling, model-based RL positions itself as a strong contender. Recent advances in sequence modelling have led to effective transformer-based world models, albeit at the price of heavy computations due to the long sequences of tokens required to accurately simulate environments. In this work, we propose $Δ$-IRIS, a new agent with a world model architecture composed of a discrete autoencoder that encodes stochastic deltas between time steps and an autoregressive transformer that predicts future deltas by summarizing the current state of the world with continuous tokens. In the Crafter benchmark, $Δ$-IRIS sets a new state of the art at multiple frame budgets, while being an order of magnitude faster to train than previous attention-based approaches. We release our code and models at https://github.com/vmicheli/delta-iris.

Atul Kumar Sinha, Daniele Paliotta, Bálint Máté et al.

Deep learning methods have gained popularity in high energy physics for fast modeling of particle showers in detectors. Detailed simulation frameworks such as the gold standard Geant4 are computationally intensive, and current deep generative architectures work on discretized, lower resolution versions of the detailed simulation. The development of models that work at higher spatial resolutions is currently hindered by the complexity of the full simulation data, and by the lack of simpler, more interpretable benchmarks. Our contribution is SUPA, the SUrrogate PArticle propagation simulator, an algorithm and software package for generating data by simulating simplified particle propagation, scattering and shower development in matter. The generation is extremely fast and easy to use compared to Geant4, but still exhibits the key characteristics and challenges of the detailed simulation. We support this claim experimentally by showing that performance of generative models on data from our simulator reflects the performance on a dataset generated with Geant4. The proposed simulator generates thousands of particle showers per second on a desktop machine, a speed up of up to 6 orders of magnitudes over Geant4, and stores detailed geometric information about the shower propagation. SUPA provides much greater flexibility for setting initial conditions and defining multiple benchmarks for the development of models. Moreover, interpreting particle showers as point clouds creates a connection to geometric machine learning and provides challenging and fundamentally new datasets for the field. The code for SUPA is available at https://github.com/itsdaniele/SUPA.

Mohammad Mahdi Johari, Yann Lepoittevin, François Fleuret

We present GeoNeRF, a generalizable photorealistic novel view synthesis method based on neural radiance fields. Our approach consists of two main stages: a geometry reasoner and a renderer. To render a novel view, the geometry reasoner first constructs cascaded cost volumes for each nearby source view. Then, using a Transformer-based attention mechanism and the cascaded cost volumes, the renderer infers geometry and appearance, and renders detailed images via classical volume rendering techniques. This architecture, in particular, allows sophisticated occlusion reasoning, gathering information from consistent source views. Moreover, our method can easily be fine-tuned on a single scene, and renders competitive results with per-scene optimized neural rendering methods with a fraction of computational cost. Experiments show that GeoNeRF outperforms state-of-the-art generalizable neural rendering models on various synthetic and real datasets. Lastly, with a slight modification to the geometry reasoner, we also propose an alternative model that adapts to RGBD images. This model directly exploits the depth information often available thanks to depth sensors. The implementation code is available at https://www.idiap.ch/paper/geonerf.

Tatjana Chavdarova, François Fleuret

This paper addresses the problem of multi-view people occupancy map estimation. Existing solutions for this problem either operate per-view, or rely on a background subtraction pre-processing. Both approaches lessen the detection performance as scenes become more crowded. The former does not exploit joint information, whereas the latter deals with ambiguous input due to the foreground blobs becoming more and more interconnected as the number of targets increases. Although deep learning algorithms have proven to excel on remarkably numerous computer vision tasks, such a method has not been applied yet to this problem. In large part this is due to the lack of large-scale multi-camera data-set. The core of our method is an architecture which makes use of monocular pedestrian data-set, available at larger scale then the multi-view ones, applies parallel processing to the multiple video streams, and jointly utilises it. Our end-to-end deep learning method outperforms existing methods by large margins on the commonly used PETS 2009 data-set. Furthermore, we make publicly available a new three-camera HD data-set. Our source code and trained models will be made available under an open-source license.

Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez et al.

Model merging and task arithmetic have emerged as promising scalable approaches to merge multiple single-task checkpoints to one multi-task model, but their applicability is reduced by significant performance loss. Previous works have linked these drops to interference in the weight space and erasure of important task-specific features. Instead, in this work we show that the information required to solve each task is still preserved after merging as different tasks mostly use non-overlapping sets of weights. We propose TALL-masks, a method to identify these task supports given a collection of task vectors and show that one can retrieve >99% of the single task accuracy by applying our masks to the multi-task vector, effectively compressing the individual checkpoints. We study the statistics of intersections among constructed masks and reveal the existence of selfish and catastrophic weights, i.e., parameters that are important exclusively to one task and irrelevant to all tasks but detrimental to multi-task fusion. For this reason, we propose Consensus Merging, an algorithm that eliminates such weights and improves the general performance of existing model merging approaches. Our experiments in vision and NLP benchmarks with up to 20 tasks, show that Consensus Merging consistently improves existing approaches. Furthermore, our proposed compression scheme reduces storage from 57Gb to 8.2Gb while retaining 99.7% of original performance.

Youssef Saied, François Fleuret

Normalization Equivariance (NE), equivariance to global contrast and brightness transforms, improves robustness to distribution shift in image-to-image prediction. Existing methods enforce this prior by constraining internal layers to NE-compatible families, limiting compatibility with standard components such as attention and LayerNorm, and adding runtime cost. We characterize the full NE function class: a function is NE if and only if it admits a normalize-process-denormalize factorization. This turns exact NE enforcement, for the ideal wrapper, from an internal architectural constraint into an input-output parameterization problem, allowing a parameter-free wrapper (WNE) to enforce NE around any backbone, including transformers. In a single-noise mismatch diagnostic for blind denoising, the wrapper improves CNN and transformer robustness with no measurable GPU overhead; architectural NE baselines incur up to a 1.6x slowdown.

Arnaud Pannatier, Evann Courdier, François Fleuret

Autoregressive models, such as the GPT family, use a fixed order, usually left-to-right, to generate sequences. However, this is not a necessity. In this paper, we challenge this assumption and show that by simply adding a positional encoding for the output, this order can be modulated on-the-fly per-sample which offers key advantageous properties. It allows for the sampling of and conditioning on arbitrary subsets of tokens, and it also allows sampling in one shot multiple tokens dynamically according to a rejection strategy, leading to a sub-linear number of model evaluations. We evaluate our method across various domains, including language modeling, path-solving, and aircraft vertical rate prediction, decreasing the number of steps required for generation by an order of magnitude.

Daniele Paliotta, Junxiong Wang, Matteo Pagliardini et al.

Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common strategy involves generating multiple Chain-of-Thought (CoT) trajectories and aggregating their outputs through various selection mechanisms. This raises a fundamental question: can models with lower complexity leverage their superior generation throughput to outperform similarly sized Transformers for a fixed computational budget? To address this question and overcome the lack of strong subquadratic reasoners, we distill pure and hybrid Mamba models from pretrained Transformers. Trained on only 8 billion tokens, our distilled models show strong performance and scaling on mathematical reasoning datasets while being much faster at inference for large batches and long sequences. Despite the zero-shot performance hit due to distillation, both pure and hybrid Mamba models can scale their coverage and accuracy performance past their Transformer teacher models under fixed time budgets, opening a new direction for scaling inference compute.

Bálint Máté, François Fleuret, Tristan Bereau

We present a method for computing free-energy differences using thermodynamic integration with a neural network potential that interpolates between two target Hamiltonians. The interpolation is defined at the sample distribution level, and the neural network potential is optimized to match the corresponding equilibrium potential at every intermediate time-step. Once the interpolating potentials and samples are well-aligned, the free-energy difference can be estimated using (neural) thermodynamic integration. To target molecular systems, we simultaneously couple Lennard-Jones and electrostatic interactions and model the rigid-body rotation of molecules. We report accurate results for several benchmark systems: a Lennard-Jones particle in a Lennard-Jones fluid, as well as the insertion of both water and methane solutes in a water solvent at atomistic resolution using a simple three-body neural-network potential.

Ramón Calvo González, Daniele Paliotta, Matteo Pagliardini et al.

Large Language Models (LLMs) demonstrate remarkable capabilities at the cost of high compute requirements. Recent studies have demonstrated that intermediate layers in LLMs can be removed or reordered without substantial accuracy loss; however, this insight has not yet been exploited to improve inference efficiency. Leveraging observed layer independence, we propose a novel method that groups consecutive layers into pairs evaluated in parallel, effectively restructuring the computational graph to enhance parallelism. Without requiring retraining or fine-tuning, this approach achieves an inference throughput improvement of 1.05x-1.20x on standard benchmarks, retaining 95\%-99\% of the original model accuracy. Empirical results demonstrate the practicality of this method in significantly reducing inference cost for large-scale LLM deployment. Additionally, we demonstrate that modest performance degradation can be substantially mitigated through lightweight fine-tuning, further enhancing the method's applicability.

Bálint Máté, François Fleuret

We consider the problem of sampling lattice field configurations on a lattice from the Boltzmann distribution corresponding to some action. Since such densities arise as approximationw of an underlying functional density, we frame the task as an instance of operator learning. We propose to approximate a time-dependent neural operator whose time integral provides a mapping between the functional distributions of the free and target theories. Once a particular lattice is chosen, the neural operator can be discretized to a finite-dimensional, time-dependent vector field which in turn induces a continuous normalizing flow between finite dimensional distributions over the chosen lattice. This flow can then be trained to be a diffeormorphism between the discretized free and target theories on the chosen lattice, and, by construction, can be evaluated on different discretizations of spacetime. We experimentally validate the proposal on the 2-dimensional $φ^4$-theory to explore to what extent such operator-based flow architectures generalize to lattice sizes they were not trained on, and show that pretraining on smaller lattices can lead to a speedup over training directly on the target lattice size.

François Fleuret

We propose an extension of the decoder Transformer that conditions its generative process on random latent variables which are learned without supervision thanks to a variational procedure. Experimental evaluations show that allowing such a conditioning translates into substantial improvements on downstream tasks.

Bálint Máté, François Fleuret, Tristan Bereau

Thermodynamic integration (TI) offers a rigorous method for estimating free-energy differences by integrating over a sequence of interpolating conformational ensembles. However, TI calculations are computationally expensive and typically limited to coupling a small number of degrees of freedom due to the need to sample numerous intermediate ensembles with sufficient conformational-space overlap. In this work, we propose to perform TI along an alchemical pathway represented by a trainable neural network, which we term Neural TI. Critically, we parametrize a time-dependent Hamiltonian interpolating between the interacting and non-interacting systems, and optimize its gradient using a score matching objective. The ability of the resulting energy-based diffusion model to sample all intermediate ensembles allows us to perform TI from a single reference calculation. We apply our method to Lennard-Jones fluids, where we report accurate calculations of the excess chemical potential, demonstrating that Neural TI reproduces the underlying changes in free energy without the need for simulations at interpolating Hamiltonians.

Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas et al.

Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more broadly applicable methods, organizers need to enforce the use of general techniques, the use of sample-efficient methods, and the reproducibility of the results. While beneficial for the research community, these restrictions come at a cost -- increased difficulty. If the barrier for entry is too high, many potential participants are demoralized. With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers. With this track and more extensive tutorials and support, we saw an increased number of submissions. The participants of this easier track were able to obtain a diamond, and the participants of the harder track progressed the generalizable solutions in the same task.

Evann Courdier, François Fleuret

Semantic segmentation is a well-addressed topic in the computer vision literature, but the design of fast and accurate video processing networks remains challenging. In addition, to run on embedded hardware, computer vision models often have to make compromises on accuracy to run at the required speed, so that a latency/accuracy trade-off is usually at the heart of these real-time systems' design. For the specific case of videos, models have the additional possibility to make use of computations made for previous frames to mitigate the accuracy loss while being real-time. In this work, we propose to tackle the task of fast future video segmentation prediction through the use of convolutional layers with time-dependent channel masking. This technique only updates a chosen subset of the feature maps at each time-step, bringing simultaneously less computation and latency, and allowing the network to leverage previously computed features. We apply this technique to several fast architectures and experimentally confirm its benefits for the future prediction subtask.

Matteo Pagliardini, Martin Jaggi, François Fleuret et al.

Gradient-based learning algorithms have an implicit simplicity bias which in effect can limit the diversity of predictors being sampled by the learning procedure. This behavior can hinder the transferability of trained models by (i) favoring the learning of simpler but spurious features -- present in the training data but absent from the test data -- and (ii) by only leveraging a small subset of predictive features. Such an effect is especially magnified when the test distribution does not exactly match the train distribution -- referred to as the Out of Distribution (OOD) generalization problem. However, given only the training data, it is not always possible to apriori assess if a given feature is spurious or transferable. Instead, we advocate for learning an ensemble of models which capture a diverse set of predictive features. Towards this, we propose a new algorithm D-BAT (Diversity-By-disAgreement Training), which enforces agreement among the models on the training data, but disagreement on the OOD data. We show how D-BAT naturally emerges from the notion of generalized discrepancy, as well as demonstrate in multiple experiments how the proposed method can mitigate shortcut-learning, enhance uncertainty and OOD detection, as well as improve transferability.

Arnaud Pannatier, Ricardo Picatoste, François Fleuret

This paper proposes a simple yet efficient high-altitude wind nowcasting pipeline. It processes efficiently a vast amount of live data recorded by airplanes over the whole airspace and reconstructs the wind field with good accuracy. It creates a unique context for each point in the dataset and then extrapolates from it. As creating such context is computationally intensive, this paper proposes a novel algorithm that reduces the time and memory cost by efficiently fetching nearest neighbors in a data set whose elements are organized along smooth trajectories that can be approximated with piece-wise linear structures. We introduce an efficient and exact strategy implemented through algebraic tensorial operations, which is well-suited to modern GPU-based computing infrastructure. This method employs a scalable Euclidean metric and allows masking data points along one dimension. When applied, this method is more efficient than plain Euclidean k-NN and other well-known data selection methods such as KDTrees and provides a several-fold speedup. We provide an implementation in PyTorch and a novel data set to allow the replication of empirical results.

Prabhu Teja Sivaprasad, François Fleuret

Data samples generated by several real world processes are dynamic in nature \textit{i.e.}, their characteristics vary with time. Thus it is not possible to train and tackle all possible distributional shifts between training and inference, using the host of transfer learning methods in literature. In this paper, we tackle this problem of adapting to domain shift at inference time \textit{i.e.}, we do not change the training process, but quickly adapt the model at test-time to handle any domain shift. For this, we propose to enforce consistency of predictions of data sampled in the vicinity of test sample on the image manifold. On a host of test scenarios like dealing with corruptions (CIFAR-10-C and CIFAR-100-C), and domain adaptation (VisDA-C), our method is at par or significantly outperforms previous methods.

Bálint Máté, François Fleuret

We introduce primed-PCA (pPCA), a two-step algorithm for speeding up the approximation of principal components. This algorithm first runs any approximate-PCA method to get an initial estimate of the principal components (priming), and then applies an exact PCA in the subspace they span. Since this subspace is of small dimension in any practical use, the second step is extremely cheap computationally. Nonetheless, it improves accuracy significantly for a given computational budget across datasets. In this setup, the purpose of the priming is to narrow down the search space, and prepare the data for the second step, an exact calculation. We show formally that pPCA improves upon the priming algorithm under very mild conditions, and we provide experimental validation on both synthetic and real large-scale datasets showing that it systematically translates to improved performance. In our experiments we prime pPCA by several approximate algorithms and report an average speedup by a factor of 7.2 over Oja's rule, and a factor of 10.5 over EigenGame.

Vincent Micheli, François Fleuret

Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language understanding and generative capabilities are essential. Nonetheless, collecting expert demonstrations in such environments is a time-consuming endeavour. We introduce a two-stage procedure to learn from a small set of demonstrations and further improve by interacting with an environment. We show that language models fine-tuned with only 1.2% of the expert demonstrations and a simple reinforcement learning algorithm achieve a 51% absolute improvement in success rate over existing methods in the ALFWorld environment.

Vincent Micheli, Quentin Heinrich, François Fleuret et al.

Attention is a key component of the now ubiquitous pre-trained language models. By learning to focus on relevant pieces of information, these Transformer-based architectures have proven capable of tackling several tasks at once and sometimes even surpass their single-task counterparts. To better understand this phenomenon, we conduct a structural analysis of a new all-purpose question answering model that we introduce. Surprisingly, this model retains single-task performance even in the absence of a strong transfer effect between tasks. Through attention head importance scoring, we observe that attention heads specialize in a particular task and that some heads are more conducive to learning than others in both the multi-task and single-task settings.

Karthigan Sinnathamby, Chang-Yu Hou, Lalitha Venkataramanan et al.

Following the work of arXiv:2101.09512, we are interested in clustering a given multi-variate series in an unsupervised manner. We would like to segment and cluster the series such that the resulting blocks present in each cluster are coherent with respect to a predefined model structure (e.g. a physics model with a functional form defined by a number of parameters). However, such approach might have its limitation, partly because there may exist multiple models that describe the same data, and partly because the exact model behind the data may not immediately known. Hence, it is useful to establish a general framework that enables the integration of plausible models and also accommodates data-driven approach into one approximated model to assist the clustering task. Hence, in this work, we investigate the use of neural processes to build the approximated model while yielding the same assumptions required by the algorithm presented in arXiv:2101.09512.

Karthigan Sinnathamby, Chang-Yu Hou, Lalitha Venkataramanan et al.

We are interested in clustering parts of a given single multi-variate series in an unsupervised manner. We would like to segment and cluster the series such that the resulting blocks present in each cluster are coherent with respect to a known model (e.g. physics model). Data points are said to be coherent if they can be described using this model with the same parameters. We have designed an algorithm based on dynamic programming with constraints on the number of clusters, the number of transitions as well as the minimal size of a block such that the clusters are coherent with this process. We present an use-case: clustering of petrophysical series using the Waxman-Smits equation.

Vincent Micheli, Martin d'Hoffschmidt, François Fleuret

Recent advances in language modeling have led to computationally intensive and resource-demanding state-of-the-art models. In an effort towards sustainable practices, we study the impact of pre-training data volume on compact language models. Multiple BERT-based models are trained on gradually increasing amounts of French text. Through fine-tuning on the French Question Answering Dataset (FQuAD), we observe that well-performing models are obtained with as little as 100 MB of text. In addition, we show that past critically low amounts of pre-training data, an intermediate pre-training step on the task-specific corpus does not yield substantial improvements.

Apoorv Vyas, Angelos Katharopoulos, François Fleuret

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making them prohibitively expensive for large sequences. To address this, we propose clustered attention, which instead of computing the attention for every query, groups queries into clusters and computes attention just for the centroids. To further improve this approximation, we use the computed clusters to identify the keys with the highest attention per query and compute the exact key/query dot products. This results in a model with linear complexity with respect to the sequence length for a fixed number of clusters. We evaluate our approach on two automatic speech recognition datasets and show that our model consistently outperforms vanilla transformers for a given computational budget. Finally, we demonstrate that our model can approximate arbitrarily complex attention distributions with a minimal number of clusters by approximating a pretrained BERT model on GLUE and SQuAD benchmarks with only 25 clusters and no loss in performance.

Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas et al.

Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the self-attention as a linear dot-product of kernel feature maps and make use of the associativity property of matrix products to reduce the complexity from $\mathcal{O}\left(N^2\right)$ to $\mathcal{O}\left(N\right)$, where $N$ is the sequence length. We show that this formulation permits an iterative implementation that dramatically accelerates autoregressive transformers and reveals their relationship to recurrent neural networks. Our linear transformers achieve similar performance to vanilla transformers and they are up to 4000x faster on autoregressive prediction of very long sequences.

Vincent Micheli, Karthigan Sinnathamby, François Fleuret

We introduce a new reinforcement learning approach combining a planning quasi-metric (PQM) that estimates the number of steps required to go from any state to another, with task-specific "aimers" that compute a target state to reach a given goal. This decomposition allows the sharing across tasks of a task-agnostic model of the quasi-metric that captures the environment's dynamics and can be learned in a dense and unsupervised manner. We achieve multiple-fold training speed-up compared to recently published methods on the standard bit-flip problem and in the MuJoCo robotic arm simulator.

Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels et al.

The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration. The efficacy of optimizers is often studied under near-optimal problem-specific hyperparameters, and finding these settings may be prohibitively costly for practitioners. In this work, we argue that a fair assessment of optimizers' performance must take the computational cost of hyperparameter tuning into account, i.e., how easy it is to find good hyperparameter configurations using an automatic hyperparameter search. Evaluating a variety of optimizers on an extensive set of standard datasets and architectures, our results indicate that Adam is the most practical solution, particularly in low-budget scenarios.

Angelos Katharopoulos, François Fleuret

Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and processes only a fraction of the full resolution input image. The locations to process are sampled from an attention distribution computed from a low resolution view of the input. We refer to our method as attention sampling and it can process images of several megapixels with a standard single GPU setup. We show that sampling from the attention distribution results in an unbiased estimator of the full model with minimal variance, and we derive an unbiased estimator of the gradient that we use to train our model end-to-end with a normal SGD procedure. This new method is evaluated on three classification tasks, where we show that it allows to reduce computation and memory footprint by an order of magnitude for the same accuracy as classical architectures. We also show the consistency of the sampling that indeed focuses on informative parts of the input images.

Tatjana Chavdarova, Gauthier Gidel, François Fleuret et al.

We study the effect of the stochastic gradient noise on the training of generative adversarial networks (GANs) and show that it can prevent the convergence of standard game optimization methods, while the batch version converges. We address this issue with a novel stochastic variance-reduced extragradient (SVRE) optimization algorithm, which for a large class of games improves upon the previous convergence rates proposed in the literature. We observe empirically that SVRE performs similarly to a batch method on MNIST while being computationally cheaper, and that SVRE yields more stable GAN training on standard datasets.

Angelos Katharopoulos, François Fleuret

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled importance sampling scheme that focuses computation on "informative" examples, and reduces the variance of the stochastic gradients during training. Our contribution is twofold: first, we derive a tractable upper bound to the per-sample gradient norm, and second we derive an estimator of the variance reduction achieved with importance sampling, which enables us to switch it on when it will result in an actual speedup. The resulting scheme can be used by changing a few lines of code in a standard SGD procedure, and we demonstrate experimentally, on image classification, CNN fine-tuning, and RNN training, that for a fixed wall-clock time budget, it provides a reduction of the train losses of up to an order of magnitude and a relative improvement of test errors between 5% and 17%.

Tatjana Chavdarova, François Fleuret

The Generative Adversarial Networks (GANs) have demonstrated impressive performance for data synthesis, and are now used in a wide range of computer vision tasks. In spite of this success, they gained a reputation for being difficult to train, what results in a time-consuming and human-involved development process to use them. We consider an alternative training process, named SGAN, in which several adversarial "local" pairs of networks are trained independently so that a "global" supervising pair of networks can be trained against them. The goal is to train the global pair with the corresponding ensemble opponent for improved performances in terms of mode coverage. This approach aims at increasing the chances that learning will not stop for the global pair, preventing both to be trapped in an unsatisfactory local minimum, or to face oscillations often observed in practice. To guarantee the latter, the global pair never affects the local ones. The rules of SGAN training are thus as follows: the global generator and discriminator are trained using the local discriminators and generators, respectively, whereas the local networks are trained with their fixed local opponent. Experimental results on both toy and real-world problems demonstrate that this approach outperforms standard training in terms of better mitigating mode collapse, stability while converging and that it surprisingly, increases the convergence speed as well.

Tatjana Chavdarova, Pierre Baqué, Stéphane Bouquet et al.

People detection methods are highly sensitive to the perpetual occlusions among the targets. As multi-camera set-ups become more frequently encountered, joint exploitation of the across views information would allow for improved detection performances. We provide a large-scale HD dataset named WILDTRACK which finally makes advanced deep learning methods applicable to this problem. The seven-static-camera set-up captures realistic and challenging scenarios of walking people. Notably, its camera calibration with jointly high-precision projection widens the range of algorithms which may make use of this dataset. In aim to help accelerate the research on automatic camera calibration, such annotations also accompany this dataset. Furthermore, the rich-in-appearance visual context of the pedestrian class makes this dataset attractive for monocular pedestrian detection as well, since: the HD cameras are placed relatively close to the people, and the size of the dataset further increases seven-fold. In summary, we overview existing multi-camera datasets and detection methods, enumerate details of our dataset, and we benchmark multi-camera state of the art detectors on this new dataset.

Angelos Katharopoulos, François Fleuret

Importance sampling has been successfully used to accelerate stochastic optimization in many convex problems. However, the lack of an efficient way to calculate the importance still hinders its application to Deep Learning. In this paper, we show that the loss value can be used as an alternative importance metric, and propose a way to efficiently approximate it for a deep model, using a small model trained for that purpose in parallel. This method allows in particular to utilize a biased gradient estimate that implicitly optimizes a soft max-loss, and leads to better generalization performance. While such method suffers from a prohibitively high variance of the gradient estimate when using a standard stochastic optimizer, we show that when it is combined with our sampling mechanism, it results in a reliable procedure. We showcase the generality of our method by testing it on both image classification and language modeling tasks using deep convolutional and recurrent neural networks. In particular, our method results in 30% faster training of a CNN for CIFAR10 than when using uniform sampling.

Pierre Baqué, François Fleuret, Pascal Fua

People detection in single 2D images has improved greatly in recent years. However, comparatively little of this progress has percolated into multi-camera multi-people tracking algorithms, whose performance still degrades severely when scenes become very crowded. In this work, we introduce a new architecture that combines Convolutional Neural Nets and Conditional Random Fields to explicitly model those ambiguities. One of its key ingredients are high-order CRF terms that model potential occlusions and give our approach its robustness even when many people are present. Our model is trained end-to-end and we show that it outperforms several state-of-art algorithms on challenging scenes.

Timur Bagautdinov, Alexandre Alahi, François Fleuret et al.

We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and estimates the collective actions with a single feed-forward pass through a neural network. We propose a single architecture that does not rely on external detection algorithms but rather is trained end-to-end to generate dense proposal maps that are refined via a novel inference scheme. The temporal consistency is handled via a person-level matching Recurrent Neural Network. The complete model takes as input a sequence of frames and outputs detections along with the estimates of individual actions and collective activities. We demonstrate state-of-the-art performance of our algorithm on multiple publicly available benchmarks.