Publications

Stable Deep Reinforcement Learning via Isotropic Gaussian Representations
Ali Saheb Pasand
Johan Obando-Ceron
Aaron Courville
Pouya Bashivan
Pablo Samuel Castro
Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data… (voir plus) distributions evolve over time. We show that under non-stationary targets, isotropic Gaussian embeddings are provably advantageous. In particular, they induce stable tracking of time-varying targets for linear readouts, achieve maximal entropy under a fixed variance budget, and encourage a balanced use of all representational dimensions--all of which enable agents to be more adaptive and stable. Building on this insight, we propose the use of Sketched Isotropic Gaussian Regularization for shaping representations toward an isotropic Gaussian distribution during training. We demonstrate empirically, over a variety of domains, that this simple and computationally inexpensive method improves performance under non-stationarity while reducing representation collapse, neuron dormancy, and training instability.
2026-02-21
arXiv (prépublication)
doi.org
openreview.net
VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing
Juan Rodriguez
Haotian Zhang
Abhay Puri
Tianyang Zhang
Rishav Pramanik
Meng Lin
Xiaoqing Xie
Marco Terral
Darsh Kaushik
Aly Shariff
Perouz Taslakian
Spandana Gella
Sai Rajeswar
David Vázquez
Christopher Pal
Marco Pedersoli
We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, com… (voir plus)plex editing, and visual understanding. VectorGym addresses the lack of realistic, challenging benchmarks aligned with professional design workflows. Our benchmark comprises four tasks with expert human-authored annotations: the novel Sketch2SVG task (VG-Sketch); a new SVG editing dataset (VG-Edit) featuring complex, multi-step edits with higher-order primitives; Text2SVG generation (VG-Text); and SVG captioning (VG-Cap). Unlike prior benchmarks that rely on synthetic edits, VectorGym provides gold-standard human annotations that require semantic understanding and design intent. We also propose a multi-task reinforcement learning approach that jointly optimizes across all four tasks using rendering-based rewards. Our method, built on GRPO with curriculum learning, trains a Qwen3-VL 8B model that achieves state-of-the-art performance among open-source models, surpassing much larger models including Qwen3-VL 235B and matching GPT-4o. We also introduce a VLM-as-a-Judge metric for SVG generation, validated through human correlation studies. Our evaluation of frontier VLMs reveals significant performance gaps, positioning VectorGym as a rigorous framework for advancing visual code generation. VectorGym is publicly available on huggingface.co/datasets/ServiceNow/VectorGym.
2026-02-21
arXiv (prépublication)
doi.org
arxiv.org
EEG-based quantification of chronic pain in cats: A proof-of-concept study using the Piq algorithm
Aliénor Delsart
Colince Segning
Aude Castel
Colombe Otis
Guillaume Dumas
Maxim Moreau
Bertrand Lussier
Rubens Da Silva
Karen Barros Parron Fernandes
Johanne Martel-Pelletier
Jean-Pierre Pelletier
Eric Troncy
Suzy Ngomo
While chronic pain assessment in household pets remains challenging, the use of non-invasive electroencephalography (EEG) in cats has shown … (voir plus)promise to identify pain more objectively in this species. A novel EEG-based algorithm - Pain identification and quantification (Piq) - was originally developed in humans to quantify pain intensity. In this proof-of-concept study, the objective was to evaluate whether the Piq algorithm could be explored for feasibility to identify and quantify chronic osteoarthritic (OA) pain in cats. Adult neutered cats (n = 5 including n = 2 with osteoarthritis, OA) were assessed for their functional impairment (Montreal instrument for cat arthritis testing for use by veterinarians, MI-CAT(V)) and neuro-sensitization at both peripheral (Paw Withdrawal Threshold, PWT) and spinal (response to mechanical temporal summation, RMTS) levels. Resting-state EEG recordings were acquired from Cz, C3/C4 under conscious and sedated conditions. The first five minutes of EEG data were analyzed using the Piq algorithm, with Piq scores ≥ 10 % used as an exploratory threshold transferred from human studies. Pain-free cats showed gamma frequency band Piq scores  10 % while OA cats exceeded 10 % in both conscious and sedated conditions at Cz. Piq scores were negatively correlated with PWT, sug
2026-02-20
Veterinary Journal (publié)
doi.org
Give Users the Wheel: Towards Promptable Recommendation Paradigm
Fuyuan Lyu
Chenglin Luo
Qiyuan Zhang
Yupeng Hou
Haolun Wu
Xing Tang
Xue Liu
Jin L.C. Guo
xiuqiang He
Conventional sequential recommendation models have achieved remarkable success in mining implicit behavioral patterns. However, these archit… (voir plus)ectures remain structurally blind to explicit user intent: they struggle to adapt when a user's immediate goal (e.g., expressed via a natural language prompt) deviates from their historical habits. While Large Language Models (LLMs) offer the semantic reasoning to interpret such intent, existing integration paradigms force a dilemma: LLM-as-a-recommender paradigm sacrifices the efficiency and collaborative precision of ID-based retrieval, while Reranking methods are inherently bottlenecked by the recall capabilities of the underlying model. In this paper, we propose Decoupled Promptable Sequential Recommendation (DPR), a model-agnostic framework that empowers conventional sequential backbones to natively support Promptable Recommendation, the ability to dynamically steer the retrieval process using natural language without abandoning collaborative signals. DPR modulates the latent user representation directly within the retrieval space. To achieve this, we introduce a Fusion module to align the collaborative and semantic signals, a Mixture-of-Experts (MoE) architecture that disentangles the conflicting gradients from positive and negative steering, and a three-stage training strategy that progressively aligns the semantic space of prompts with the collaborative space. Extensive experiments on real-world datasets demonstrate that DPR significantly outperforms state-of-the-art baselines in prompt-guided tasks while maintaining competitive performance in standard sequential recommendation scenarios.
2026-02-20
arXiv (prépublication)
doi.org
arxiv.org
Sociodynamics of Reinforcement Learning
Yann Bouteiller
Karthik Soma
Giovanni Beltrame
Reinforcement Learning (RL) has emerged as a core algorithmic paradigm explicitly driving innovation in a growing number of industrial appli… (voir plus)cations, including large language models and quantitative finance. Furthermore, computational neuroscience has long found evidence of natural forms of RL in biological brains. Therefore, it is crucial for the study of social dynamics to develop a scientific understanding of how RL shapes population behaviors. We leverage the framework of Evolutionary Game Theory (EGT) to provide building blocks and insights toward this objective. We propose a methodology that enables simulating large populations of RL agents in simple game theoretic interaction models. More specifically, we derive fast and parallelizable implementations of two fundamental revision protocols from multi-agent RL - Policy Gradient (PG) and Opponent-Learning Awareness (LOLA) - tailored for population simulations of random pairwise interactions in stateless normal-form games. Our methodology enables us to simulate large populations of 200,000 independent co-learning agents, yielding compelling insights into how non-stationarity-aware learners affect social dynamics. In particular, we find that LOLA learners promote cooperation in the Stag Hunt model, delay cooperative outcomes in the Hawk-Dove model, and reduce strategy diversity in the Rock-Paper-Scissors model.
2026-02-20
Transactions on Machine Learning Research (accepté)
openreview.net
openreview.net
Anisotropic local law for non-separable sample covariance matrices
Fan Zhou
Renyuan Ma
Elliot Paquette
Zhichao Wang
Zhou Fan
We establish local laws for sample covariance matrices …
2026-02-19
arXiv (prépublication)
doi.org
arxiv.org
Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems
Tomas Gonzalez
Cristobal Guzman
Courtney Paquette
2026-02-19
SIAM Journal on Optimization (publié)
doi.org
arxiv.org
On the Adversarial Robustness of Discrete Image Tokenizers
Rishika Bhagwatkar
Irina Rish
Nicolas Flammarion
Francesco Croce
Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal syst… (voir plus)ems, including encoder-only, encoder-decoder, and decoder-only models. However, unlike CLIP encoders, their vulnerability to adversarial attacks has not been explored. Ours being the first work studying this topic, we first formulate attacks that aim to perturb the features extracted by discrete tokenizers, and thus change the extracted tokens. These attacks are computationally efficient, application-agnostic, and effective across classification, multimodal retrieval, and captioning tasks. Second, to defend against this vulnerability, inspired by recent work on robust CLIP encoders, we fine-tune popular tokenizers with unsupervised adversarial training, keeping all other components frozen. While unsupervised and task-agnostic, our approach significantly improves robustness to both unsupervised and end-to-end supervised attacks and generalizes well to unseen tasks and data. Unlike supervised adversarial training, our approach can leverage unlabeled images, making it more versatile. Overall, our work highlights the critical role of tokenizer robustness in downstream tasks and presents an important step in the development of safe multimodal foundation models.
2026-02-19
arXiv (prépublication)
doi.org
arxiv.org
Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
Angelo Porrello
Pietro Buzzega
Felix Dangel
Thomas Sommariva
Riccardo Salami
Lorenzo Bonicelli
Simone Calderara
Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task … (voir plus)interference, causing representation drift and degraded performance. Representation drift regularization provides a natural remedy to disentangle task vectors; however, existing approaches typically require external task data, conflicting with modularity and data availability constraints (e.g., privacy requirements). We propose a dataless approach by framing regularization against representation drift as a curvature matrix approximation problem. This allows us to leverage well-established techniques; in particular, we adopt Kronecker-Factored Approximate Curvature and obtain a practical regularizer that achieves state-of-the-art results in task addition and negation. Our method has constant complexity in the number of tasks and promotes robustness to task vector rescaling, eliminating the need for held-out tuning.
2026-02-18
Open MIND (prépublication)
doi.org
arxiv.org
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
Ye Zhu
Kaleb S. Newman
Johannes F. Lutzeyer
Adriana Romero
Michal Drozdzal
Olga Russakovsky
2026-02-18
ArXiv (prépublication)
arxiv.org
arxiv.org
GeneZip: Region-Aware Compression for Long Context DNA Modeling
Jianan Zhao
Xixian Liu
Zhihao Zhan
Xinyu Yuan
Hongyu Guo
Jian Tang
Genomic sequences span billions of base pairs (bp), posing a fundamental challenge for genome-scale foundation models. Existing approaches l… (voir plus)argely sidestep this barrier by either scaling relatively small models to long contexts or relying on heavy multi-GPU parallelism. Here we introduce GeneZip, a DNA compression model that leverages a key biological prior: genomic information is highly imbalanced. Coding regions comprise only a small fraction (about 2 percent) yet are information-dense, whereas most non-coding sequence is comparatively information-sparse. GeneZip couples HNet-style dynamic routing with a region-aware compression-ratio objective, enabling adaptive allocation of representation budget across genomic regions. As a result, GeneZip learns region-aware compression and achieves 137.6x compression with only 0.31 perplexity increase. On downstream long-context benchmarks, GeneZip achieves comparable or better performance on contact map prediction, expression quantitative trait loci prediction, and enhancer-target gene prediction. By reducing effective sequence length, GeneZip unlocks simultaneous scaling of context and capacity: compared to the prior state-of-the-art model JanusDNA, it enables training models 82.6x larger at 1M-bp context, supporting a 636M-parameter GeneZip model at 1M-bp context. All experiments in this paper can be trained on a single A100 80GB GPU.
2026-02-18
arXiv (prépublication)
doi.org
openreview.net
Offline-Online Retail Collaboration via Pickup Partnership
Zahra Jalali
Maxime C. Cohen
Necati Ertekin
Mehmet Gümüş
We study a growing retail strategy called pickup partnership, where online retailers partner with physical stores to offer in-store pickup s… (voir plus)ervices. In practice, two main policies are used in these partnerships: (i) a fixed fee policy, where the retailer pays the offline partner a set fee per pickup order, and (ii) a coupon policy, where customers receive a coupon for use at the offline partner’s store with each pickup order. Our goal is to evaluate these policies and determine which is most beneficial for online retailers. We develop a stylized model that captures the essential dynamics of pickup partnerships. We find that although the coupon policy allows the online retailer to gain greater market coverage compared with the fixed fee policy, it does not always lead to higher profits for the online retailer. The coupon policy is preferred when in-store fulfillment and pickup handling costs are low and direct-delivery costs are high, whereas the fixed fee policy is favored when these costs are moderate. We also find that both policies entail inefficiencies when the incentives of the two parties are not aligned. To alleviate such inefficiencies, we propose a new policy designed to better align incentives and improve partnership efficiency. This paper offers the first theoretical analysis of the in-store pickup partnership model and provides practical guidance for online retailers seeking to implement it. Our proposed policy aims to enhance the effectiveness and profitability of these partnerships beyond current industry practices. Supplemental Material: The online appendix is available at https://doi.org/10.1287/serv.2025.0118 .
2026-02-18
Service Science (publié)
doi.org