Publications

PreSumm: Predicting Summarization Performance Without Summarizing
Steven Koniaev
Ori Ernst
Jackie Chi Kit Cheung
2024-12-31
Findings of the Association for Computational Linguistics: ACL (publié)
doi.org
Proceedings of the 18th Workshop on Building and Using Comparable Corpora (BUCC)
Serge Sharoff
Ayla Rigouts Terryn
Pierre Zweigenbaum
Reinhard Rapp
2024-12-31
COLING Workshops (publié)
dblp.uni-trier.de
A protocol for trustworthy EEG decoding with neural networks
Davide Borra
Elisa Magosso
Mirco Ravanelli
2024-12-31
Neural Networks (publié)
doi.org
Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy
Brice Rauby
Paul Xing
Jonathan Porée
Maxime Gasse
Jean Provost
Ultrasound Localization Microscopy (ULM) is a non-invasive technique that allows for the imaging of micro-vessels in vivo, at depth and with… (voir plus) a resolution on the order of ten microns. ULM is based on the sub-resolution localization of individual microbubbles injected in the bloodstream. Mapping the whole angioarchitecture requires the accumulation of microbubbles trajectories from thousands of frames, typically acquired over a few minutes. ULM acquisition times can be reduced by increasing the microbubble concentration, but requires more advanced algorithms to detect them individually. Several deep learning approaches have been proposed for this task, but they remain limited to 2D imaging, in part due to the associated large memory requirements. Herein, we propose to use sparse tensor neural networks to reduce memory usage in 2D and to improve the scaling of the memory requirement for the extension of deep learning architecture to 3D. We study several approaches to efficiently convert ultrasound data into a sparse format and study the impact of the associated loss of information. When applied in 2D, the sparse formulation reduces the memory requirements by a factor 2 at the cost of a small reduction of performance when compared against dense networks. In 3D, the proposed approach reduces memory requirements by two order of magnitude while largely outperforming conventional ULM in high concentration settings. We show that Sparse Tensor Neural Networks in 3D ULM allow for the same benefits as dense deep learning based method in 2D ULM i.e. the use of higher concentration in silico and reduced acquisition time.
2024-12-31
IEEE Transactions on Image Processing (inconnu)
doi.org
arxiv.org
R3Design: deep tertiary structure-based RNA sequence design and beyond
Cheng Tan
Yijie Zhang
Zhangyang Gao
Hanqun Cao
Siyuan Li
Siqi Ma
Mathieu Blanchette
Stan Z. Li
The rational design of Ribonucleic acid (RNA) molecules is crucial for advancing therapeutic applications, synthetic biology, and understand… (voir plus)ing the fundamental principles of life. Traditional RNA design methods have predominantly focused on secondary structure-based sequence design, often neglecting the intricate and essential tertiary interactions. We introduce R3Design, a tertiary structure-based RNA sequence design method that shifts the paradigm to prioritize tertiary structure in the RNA sequence design. R3Design significantly enhances sequence design on native RNA backbones, achieving high sequence recovery and Macro-F1 score, and outperforming traditional secondary structure-based approaches by substantial margins. We demonstrate that R3Design can design RNA sequences that fold into the desired tertiary structures by validating these predictions using advanced structure prediction models. This method, which is available through standalone software, provides a comprehensive toolkit for designing, folding, and evaluating RNA at the tertiary level. Our findings demonstrate R3Design’s superior capability in designing RNA sequences, which achieves around \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document}
2024-12-31
Briefings in Bioinformatics (publié)
doi.org
Real-time fine finger motion decoding for transradial amputees with surface electromyography
Zihan Weng
Yang Xiao
Peiyang Li
Chanlin Yi
Pouya Bashivan
Hailin Ma
Guang Yao
Yuan Lin
Fali Li
Dezhong Yao 0001
Jingming Hou
Yangsong Zhang
Peng Xu
2024-12-31
Neural Networks (publié)
doi.org
REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
Le Zhang
Bo Wang
Xipeng Qiu
Siva Reddy
Aishwarya Agrawal
We present REARANK, a large language model (LLM)-based listwise reasoning reranking agent. REARANK explicitly reasons before reranking, sign… (voir plus)ificantly improving both performance and interpretability. Leveraging reinforcement learning and data augmentation, REARANK achieves substantial improvements over baseline models across popular information retrieval benchmarks, notably requiring only 179 annotated samples. Built on top of Qwen2.5-7B, our REARANK-7B demonstrates performance comparable to GPT-4 on both in-domain and out-of-domain benchmarks and even surpasses GPT-4 on reasoning-intensive BRIGHT benchmarks. These results underscore the effectiveness of our approach and highlight how reinforcement learning can enhance LLM reasoning capabilities in reranking.
2024-12-31
EMNLP (publié)
doi.org
arxiv.org
Reassessing Speech Translation for Low-Resource Languages: Do LLMs Redefine the State-of-the-Art Against Cascaded Models?
Jonah Dauvet
Min Ma
Jessica Ojo
David Ifeoluwa Adelani
2024-12-31
Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025) (publié)
doi.org
Recovering Dantzig–Wolfe Bounds by Cutting Planes
Ying Chen
Oktay Günlük
Andrea Lodi
Leveraging Dantzig–Wolfe Decomposition in the Original Variable Space for Mixed-Integer Programming Dantzig–Wolfe decomposition has been… (voir plus) extensively applied to solve large-scale mixed-integer programs with decomposable structures, leading to exact solution approaches, such as branch and price. However, these approaches would require solving the problem in an extended variable space and are not readily present in off-the-shelf solvers. In “Recovering Dantzig–Wolfe Bounds by Cutting Planes,” Chen, Günlük, and Lodi propose a computational effective approach for generating cutting planes from Dantzig–Wolfe decomposition to enhance branch and cut in the space of original variables. The proposed approach requires a relatively small number of cutting planes to recover the strength of the Dantzig–Wolfe dual bound and should be easy to implement in general-purpose mixed-integer programming solvers. The authors show that these cutting planes typically lead to a formulation with lower dual degeneracy and hence, a better computational performance than naïve approaches, such as the objective function cut.
2024-12-31
Oper. Res. (publié)
doi.org
arxiv.org
Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
Zhongyu Li
Xue Bin Peng
Pieter Abbeel
Sergey Levine
Glen Berseth
Koushil Sreenath
This paper presents a comprehensive study on using deep reinforcement learning (RL) to create dynamic locomotion controllers for bipedal rob… (voir plus)ots. Going beyond focusing on a single locomotion skill, we develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. Our RL-based controller incorporates a novel dual-history architecture, utilizing both a long-term and short-term input/output (I/O) history of the robot. This control architecture, when trained through the proposed end-to-end RL approach, consistently outperforms other methods across a diverse range of skills in both simulation and the real world. The study also delves into the adaptivity and robustness introduced by the proposed RL system in developing locomotion controllers. We demonstrate that the proposed architecture can adapt to both time-invariant dynamics shifts and time-variant changes, such as contact events, by effectively using the robot's I/O history. Additionally, we identify task randomization as another key source of robustness, fostering better task generalization and compliance to disturbances. The resulting control policies can be successfully deployed on Cassie, a torque-controlled human-sized bipedal robot. This work pushes the limits of agility for bipedal robots through extensive real-world experiments. We demonstrate a diverse range of locomotion skills, including: robust standing, versatile walking, fast running with a demonstration of a 400-meter dash, and a diverse set of jumping skills, such as standing long jumps and high jumps.
2024-12-31
Int. J. Robotics Res. (publié)
doi.org
arxiv.org
Reliability Assessment of Distribution Systems With Microgrids Using Discrete-Time Markov Chains
Jean-William Lauzon
Ilhan Kocar
Antoine Lesage-Landry
Microgrids can improve the reliability and resiliency of modern distribution systems. The stochasticity of local non-dispatchable distribute… (voir plus)d energy resources (NDDERs), combined with the time-dependency of battery energy storage systems (BESSs) and load shedding strategies (LSSs), complicates the reliability assessment of distribution networks embedded with microgrids. In this work, we propose a minimal cut-set method using a discrete-time Markov chain to perform the time-series adequacy assessment. Our method offers an alternative to sequential Monte Carlo simulations (SMCSs) to account for the stochasticity of NDDERs and the time-dependency of BESSs and LSSs. Case studies on modified IEEE-RTBS Bus2 and IEEE 123-Test Feeder systems assess the accuracy of the method when compared with SMCSs.
2024-12-31
IEEE Transactions on Power Delivery (publié)
doi.org
Representing Positional Information in Generative World Models for Object Manipulation
Stefano Ferraro
Pietro Mazzaglia
Tim Verbelen
Bart Dhoedt
Sai Rajeswar
Object manipulation capabilities are essential skills that set apart embodied agents engaging with the world, especially in the realm of rob… (voir plus)otics. The ability to predict outcomes of interactions with objects is paramount in this setting. While model-based control methods have started to be employed for tackling manipulation tasks, they have faced challenges in accurately manipulating objects. As we analyze the causes of this limitation, we identify the cause of underperformance in the way current world models represent crucial positional information, especially about the target's goal specification for object positioning tasks. We introduce a general approach that empowers world model-based agents to effectively solve object-positioning tasks. We propose two declinations of this approach for generative world models: position-conditioned (PCP) and latent-conditioned (LCP) policy learning. In particular, LCP employs object-centric latent representations that explicitly capture object positional information for goal specification. This naturally leads to the emergence of multimodal capabilities, enabling the specification of goals through spatial coordinates or a visual goal. Our methods are rigorously evaluated across several manipulation environments, showing favorable performance compared to current model-based control approaches.
2024-12-31
ECAI (publié)
doi.org
arxiv.org