Diffusion models, image generation, text-to-image synthesis, and generative AI.
Ivan Lerner, Jean Feydy, Alexandre Kalimouttou et al.
Background: Timely, uncertainty-aware forecasting from irregular electronic health records (EHR) can support critical-care decisions, yet most approaches either impute to a grid or sacrifice interpret…
Haidong Zhao, Nikolaos Georgantas
Machine learning (ML) inference serving systems host deep neural network (DNN) models and schedule incoming inference requests across deployed GPUs. However, limited support for task prioritization an…
Bowen Sun, Chaozhuo Li, Yaodong Yang et al.
Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collecti…
Sudong Wang, Weiquan Huang, Xiaomin Yu et al.
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). H…
Jeanne Monnier, Thomas George, Frédéric Guyard et al.
Fairness in machine learning remains challenging due to its ethical complexity, the absence of a universal definition, and the need for context-specific bias metrics. Existing methods still struggle w…
Ce Chen, Yi Ren, Yuanming Li et al.
Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted video shots. We address this f…
Rogério Almeida Gouvêa, Gian-Marco Rignanese
While machine-learned interatomic potentials (MLIPs) accelerate phonon dispersion calculations, merely identifying dynamical instabilities in computationally predicted materials is insufficient; autom…
Zihao Li, Jiaru Zou, Feihao Fang et al.
Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world p…
Junan Hu, Jian Liu, Jingxiang Lai et al.
Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces visually. Yet supervised fine-tuning alone canno…
Shipeng Liu, Liang Zhao, Dengfeng Chen et al.
Tunnel inspection requires outputs that can support defect localization, measurement, severity grading, and engineering documentation. Existing training-free foundation-model pipelines usually stop at…
Tao Ge, Baolin Peng, Hao Cheng et al.
Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory structures and content…
Simon Dennis, Michael Diamond, Rivaan Patil et al.
Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking state and injecting routing instructions at eve…
Kenneth J. K. Ong
As Vision-Language Models (VLMs) become increasingly integrated into decision-making systems, it is essential to understand how visual inputs influence their behavior. This paper investigates the effe…
Lauren Cadwallader, Iain Hrynaszkiewicz, parth sarin et al.
Numerous metascience studies and other initiatives have begun to monitor the prevalence of open science practices when it is more important to understand the 'downstream' effects or impacts of open sc…
Guy Lutsker, Gal Sapir, Jordi Merino et al.
Understanding how human health changes over time, and why responses to interventions vary between individuals, remains a central challenge in medicine. Here we present HealthFormer, a decoder-only tra…
Emma Andrews, Sahan Sanjaya, Prabhat Mishra
Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cau…
Binghao Huang, Yunzhu Li
We present FlexiTac, a low-cost, open-source, and scalable piezoresistive tactile sensing solution designed for robotic end-effectors. FlexiTac is a practical "plug-in" module consisting of (i) thin, …
Silvio Martinico, Franco Maria Nardini, Cosimo Rulli et al.
Multivector retrieval models achieve state-of-the-art effectiveness through fine-grained token-level representations, but their deployment incurs substantial computational and memory costs. Current so…
Daniel Waxman, Fernando Llorente, Petar M. Djurić
The proliferation of capable and efficient machine learning (ML) models marks one of the strongest methodological shifts in signal processing (SP) in its nearly 100-year history. ML models support the…
Sascha Xu, Jilles Vreeken
We study the problem of understanding where two populations differ within a feature space, which we formalize in the concept of a differential subgroup: a subset of individuals from both populations w…
Matthias Hertel, Alexandra Nikoltchovska, Sebastian Pütz et al.
Time Series Foundation Models (TSFMs) have recently emerged as general-purpose forecasting models and show considerable potential for applications in energy systems. However, applications in critical …
Mehryar Mohri, Yutao Zhong
Preference learning has become the foundation of aligning Large Language Models (LLMs) with human intent. Popular methods, such as Direct Preference Optimization (DPO), minimize surrogate losses as pr…
Mehryar Mohri, Yutao Zhong
The choice of loss function in classification involves a fundamental trade-off: smooth losses (like Cross-Entropy) enable fast optimization rates but yield slow square-root consistency bounds, while p…
Eyon Jang, Damon Falck, Joschka Braun et al.
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration …
Yuval Domb
We develop a geometric and information-theoretic framework for encoder-decoder learning built on the Information Bottleneck (IB) principle. Recasting IB as a rate-distortion problem with Kullback-Leib…
Mehmet Iscan
Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved m…
Zhiqiang Kou, Junxiang Wu, Wenke Huang et al.
Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw …
Pourya Zamanvaziri, Amirhossein Sadr, Aida Pakniyat et al.
Multivariate time series forecasting plays a pivotal role in numerous real-world applications, including financial analysis, energy management, and traffic planning. While Transformer-based architectu…
Nhi Ngoc-Yen Nguyen, Anh-Duc Nguyen, Nghia Hieu Nguyen et al.
Scene-text image captioning requires fusing three information streams -- visual features, OCR-detected text, and linguistic knowledge -- to generate descriptions that faithfully integrate text visible…
Shijin Gong, Kai Ye, Jin Zhu et al.
Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three approaches have been widely adopted: (i) Proximal…
Sign up free and get daily digests tailored to your research interests.
Sign up free