89 citations · 711 across the 128 of their papers we have counts for
136 papers
Dr. No: Feature Steering for Abstention in Vision-Language Models
Farid Hasanov, Riccardo Renzulli, Bahram Zonooz +2
Large foundation models often answer even when the available visual or textual evidence is insufficient to support a reliable conclusion. This failure to abstain makes them hard to…
Correction-space Cross-variate Interaction for Test-time Adaptation in Time Series Forecasting
Yuanyuan Deng, Mykola Pechenizkiy, Songgaojun Deng
Test-time adaptation (TTA) is a promising paradigm for handling distribution shift in time-series forecasting (TSF), where models adapt at inference time, often leveraging delayed…
Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment
Mustafa Talha İlerisoy, Hung Manh Pham, Mathias Funk +2
Self-supervised respiratory encoders lack semantic grounding in clinical domain needed for zero-shot inference, limiting their utility without task-specific labeled data. We propos…
Fairness-Aware Network Embeddings: Methods, Applications, and Challenges
Ella Has, Harshith Kumar Yadav, Gaurav Dixit +2
Network embedding methods learn low-dimensional representations of graph-structured data to support downstream tasks such as node classification, link prediction, and influence max…
Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data
Emmanuel C. Chukwu, Rianne M. Schouten, Monique Tabak +1
Counterfactual explanations (CEs) for multivariate time-series classifiers are often difficult to interpret in domains where experts reason in terms of semantic feature groups rath…
Self-evolving LLM agents with in-distribution Optimization
Yudi Zhang, Meng Fang, Zhenfang Chen +1
Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decisi…
When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
Boqian Wu, Qiao Xiao, Patrik Okanovic +6
Scaling laws for dense LLMs under infinite data are well explored, but how sparsity interacts with limited data is not. In this work, we study sparse training in data-constrained r…
Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling
Qiao Xiao, Boqian Wu, Patrik Okanovic +6
Dynamic Sparse Training (DST) offers a promising paradigm for improving the training and inference efficiency of deep neural networks; however, we find that in large language model…
One Model for All: Multi-Objective Controllable Language Models
Qiang He, Yucheng Yang, Tianyi Zhou +3
Aligning large language models (LLMs) with human preferences is critical for enhancing LLMs' safety, helpfulness, humor, faithfulness, etc. Current reinforcement learning from huma…
PhysVid: Physics Aware Local Conditioning for Generative Video Models
Saurabh Pathak, Elahe Arani, Mykola Pechenizkiy +1
Generative video models achieve high visual fidelity but often violate basic physical principles, limiting reliability in real-world settings. Prior attempts to inject physics rely…
SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems
Rima Hazra, Bikram Ghuku, Ilona Marchenko +5
Large language models are rapidly being deployed as AI tutors, yet current evaluation paradigms assess problem-solving accuracy and generic safety in isolation, failing to capture…
Fingerprinting Concepts in Data Streams with Supervised and Unsupervised Meta-Information
Ben Halstead, Yun Sing Koh, Patricia Riddle +3
Streaming sources of data are becoming more common as the ability to collect data in real-time grows. A major concern in dealing with data streams is concept drift, a change in the…
The Unfairness of Multifactorial Bias in Recommendation
Masoud Mansoury, Jin Huang, Mykola Pechenizkiy +2
Popularity bias and positivity bias are two prominent sources of bias in recommender systems. Both arise from input data, propagate through recommendation models, and lead to unfai…
Counterfactual Explanations for Time Series Should be Human-Centered and Temporally Coherent in Interventions
Emmanuel C. Chukwu, Rianne M. Schouten, Monique Tabak +1
Counterfactual explanations are increasingly proposed as interpretable mechanisms to achieve algorithmic recourse. However, current counterfactual techniques for time series classi…
ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models
Somnath Banerjee, Sayan Layek, Sayantan Adak +3
Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can a…
Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving
Shunfeng Zheng, Yudi Zhang, Meng Fang +4
Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning-such as solving Olym…
PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
Olivier Schipper, Yudi Zhang, Yali Du +2
LLM-based agents have shown promise in various cooperative and strategic reasoning tasks, but their effectiveness in competitive multi-agent environments remains underexplored. To…
Conformalized Exceptional Model Mining: Telling Where Your Model Performs (Not) Well
Xin Du, Sikun Yang, Wouter Duivesteijn +1
Understanding the nuanced performance of machine learning models is essential for responsible deployment, especially in high-stakes domains like healthcare and finance. This paper…
MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages
Wenhan Han, Yifan Zhang, Zhixun Chen +7
Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation dat…
Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning
Yucheng Yang, Tianyi Zhou, Qiang He +3
Unsupervised reinforcement learning (URL) aims to learn general skills for unseen downstream tasks. Mutual Information Skill Learning (MISL) addresses URL by maximizing the mutual…
MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
Tristan Tomilin, Luka van den Boogaard, Samuel Garcin +7
Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning…
Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity
Qiao Xiao, Boqian Wu, Andrey Poddubnyy +4
Federated learning (FL) enables collaborative model training across decentralized clients while preserving data privacy, leveraging aggregated updates to build robust global models…
NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
Bram Grooten, Farid Hasanov, Chenxiang Zhang +9
Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial compu…
Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution
Qiao Xiao, Alan Ansell, Boqian Wu +4
Sparse large language models (LLMs) offer an attractive direction toward efficient deployment, but adapting them to downstream tasks remains challenging. The central difficulty is…