Portail HAL de Télécom Paris
Not a member yet
14191 research outputs found
Sort by
SPOT: An Annotated French Corpus and Benchmark for Detecting Critical Interventions in Online Conversations
No full textInternational audienceWe introduce SPOT (Stopping Points in Online Threads), the first annotated corpus translating the sociological concept of stopping point into a reproducible NLP task. Stopping points are ordinary critical interventions that pause or redirect online discussions through a range of forms (irony, subtle doubt or fragmentary arguments) that frameworks like counterspeech or social correction often overlook. We operationalize this concept as a binary classification task and provide reliable annotation guidelines. The corpus contains 43,305 manually annotated French Facebook comments linked to URLs flagged as false information by social media users, enriched with contextual metadata (article, post, parent comment, page or group, and source). We benchmark fine-tuned encoder models (CamemBERT) and instruction-tuned LLMs under various prompting strategies. Results show that fine-tuned encoders outperform prompted LLMs in F1 score by more than 10 percentage points, confirming the importance of supervised learning for emerging non-English social media tasks. Incorporating contextual metadata further improves encoder models F1 scores from 0.75 to 0.78. We release the anonymized dataset, along with the annotation guidelines and code in our code repository, to foster transparency and reproducible research
RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting
No full textInternational audienceRecent advances in neural scene representations have transformed immersive multimedia, with 3D Gaussian Splatting (3DGS) enabling real-time photorealistic rendering. Despite its efficiency, 3DGS suffers from large memory requirements and costly training procedures, motivating efforts toward compression. Existing approaches, however, operate at fixed rates, limiting adaptability to varying bandwidth and device constraints. In this work, we propose a flexible compression scheme for 3DGS that supports interpolation at any rate between predefined bounds. Our method is computationally lightweight, requires no retraining for any rate, and preserves rendering quality across a broad range of operating points. Experiments demonstrate that the approach achieves efficient, high-quality compression while offering dynamic rate control, making it suitable for practical deployment in immersive applications. The code is available at https://github.com/inspiros/RAVE.</div
Residual Tokens Enhance Masked Autoencoders For Speech Modeling
No full textSubmitted to ICASSP 2026 (accepted)Recent speech modeling relies on explicit attributes such as pitch, content, and speaker identity, but these alone cannot capture the full richness of natural speech. We introduce RT-MAE, a novel masked autoencoder framework that augments the supervised attributes-based modeling with unsupervised residual trainable tokens, designed to encode the information not explained by explicit labeled factors (e.g., timbre variations, noise, emotion etc). Experiments show that RT-MAE improves reconstruction quality, preserving content and speaker similarity while enhancing expressivity. We further demonstrate its applicability to speech enhancement, removing noise at inference while maintaining controllability and naturalness
Structure preserving adversarial diffusion for unpaired medical image synthesis
No full textInternational audienc
Adaptive gradient domain normalization for one-sided unsupervised medical image synthesis
No full textInternational audienc
SIRUP: A DIFFUSION-BASED VIRTUAL UPMIXER OF STEERING VECTORS FOR HIGHLY-DIRECTIVE SPATIALIZATION WITH FIRST-ORDER AMBISONICS
No full textInternational audienceThis paper presents virtual upmixing of steering vectors captured by a fewer-channel spherical microphone array. This challenge has conventionally been addressed by recovering the directions and signals of sound sources from first-order ambisonics (FOA) data, and then rendering the higher-order ambisonics (HOA) data using a physics-based acoustic simulator. This approach, however, struggles to handle the mutual dependency between the spatial directivity of source estimation and the spatial resolution of FOA ambisonics data. Our method, named SIRUP, employs a latent diffusion model architecture. Specifically, a variational autoencoder (VAE) is used to learn a compact encoding of the HOA data in a latent space and a diffusion model is then trained to generate the HOA embeddings, conditioned by the FOA data. Experimental results showed that SIRUP achieved a significant improvement compared to FOA systems for steering vector upmixing, source localization, and speech denoising.</div
Du réseau des Micro-Folies à un potentiel « patrimoine en réseau »Discussion d’une initiative étatique par une approche multiscalaire
No full textInternational audienc
What can we do in a symmetry-constrained perspective? The importance of the total charge's status in quantum reference frame frameworks
No full text25+6 pages. Comments are welcome!The study of quantum reference frames has received renewed interest over the lastyears, leading to the parallel development of non-equivalent frameworks by different com-munities. We clarify the differences between these frameworks. At the mathematical level,they mainly differ in the kind of symmetry (either weak or strong) employed to constrainthe system. We show that this mathematical difference corresponds to a fundamentalphysical question: whether the global charge associated to the symmetry group is acces-sible to symmetry-constrained observers. In this context, we formulate a definition of aperspective in terms of operational capacities, or lack thereof. Turning to consequences ofadopting either approach, we discuss how adopting the weak approach induces an ambi-guity in the momenta included in each perspective and bars from defining reversible QRFtransformations. We then review and analyze the existing arguments motivating eachapproach, and show how they bear upon the problem of charge accessibility. Finally, weintroduce a simple operational scenario in which upholding two reasonable physical pos-tulates leads to the conclusion that internal observers could measure the global charge by1/ performing a relativized interference measurement and 2/ classically communicating
Convergence of the Cumulant Expansion and Polynomial-Time Algorithm for Weakly Interacting Fermions
No full textWe propose a randomized algorithm to compute the log-partition function of weakly interacting fermions with polynomial runtime in both the system size and precision. Although weakly interacting fermionic systems are considered tractable for many computational methods such as the diagrammatic quantum Monte Carlo, a mathematically rigorous proof of polynomial runtime has been lacking. In this work we first extend the proof techniques developed in previous works for proving the convergence of the cumulant expansion in periodic systems to the non-periodic case. A key equation used to analyze the sum of connected Feynman diagrams, which we call the tree-determinant expansion, reveals an underlying tree structure in the summation. This enables us to design a new randomized algorithm to compute the log-partition function through importance sampling augmented by belief propagation. This approach differs from the traditional method based on Markov chain Monte Carlo, whose efficiency is hard to guarantee, and enables us to obtain a algorithm with provable polynomial runtime