Papers
Research papers from arXiv and related sources
Human-Aware Robot Behaviour in Self-Driving Labs
Self-driving laboratories (SDLs) are rapidly transforming research in chemistry and materials science to accelerate new discoveries. Mobile robot chemists (MRCs) play a pivotal role by autonomously...
Satheeshkumar Veeramani, Anna Kisil, Abigail Bentley, Hatem Fakhruldeen, Gabriella Pizzuto, Andre...
Aligning to Illusions: Choice Blindness in Human and AI Feedback
Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a hu...
Wenbin Wu
Sandpiper: Orchestrated AI-Annotation for Educational Discourse at Scale
Digital educational environments are expanding toward complex AI and human discourse, providing researchers with an abundance of data that offers deep insights into learning and instructional proce...
Daryl Hedley, Doug Pietrzak, Jorge Dias, Ian Burden, Bakhtawar Ahtisham, Zhuqian Zhou, Kirk Vanac...
Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity-akin to chameleons adapting their coloration to environmental cues-that can be exposed through toke...
Liyuan Mao, Le Yu, Jing Zhou, Chujie Zheng, Bowen Yu, Chang Gao, Shixuan Liu, An Yang, Weinan Zha...
NLE: Non-autoregressive LLM-based ASR by Transcript Editing
While autoregressive (AR) LLM-based ASR systems achieve strong accuracy, their sequential decoding limits parallelism and incurs high latency. We propose NLE, a non-autoregressive (NAR) approach th...
Avihu Dekel, Samuel Thomas, Takashi Fukada, George Saon
COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling
Systems that collect data on sleep, mood, and activities can provide valuable lifestyle counselling to populations affected by chronic disease and its consequences. Such systems are, however, chall...
Yee Man Ng, Bram van Dijk, Pieter Beynen, Otto Boekesteijn, Joris Jansen, Gerard van Oortmerssen,...
Adaptive Loops and Memory in Transformers: Think Harder or Know More?
Chain-of-thought (CoT) prompting enables reasoning in language models but requires explicit verbalization of intermediate steps. Looped transformers offer an alternative by iteratively refining rep...
Markus Frey, Behzad Shomali, Ali Hamza Bashir, David Berghaus, Mehdi Ali
A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation
We propose a Hierarchical Error-Corrective Graph FrameworkforAutonomousAgentswithLLM-BasedActionGeneration(HECG),whichincorporates three core innovations: (1) Multi-Dimensional Transferable Strateg...
Cong Cao, Jingyao Zhang, Kun Tong
AULLM++: Structural Reasoning with Large Language Models for Micro-Expression Recognition
Micro-expression Action Unit (AU) detection identifies localized AUs from subtle facial muscle activations, providing a foundation for decoding affective cues. Previous methods face three key limit...
Zhishu Liu, Kaishen Yuan, Bo Zhao, Hui Ma, Zitong Yu
Rectified flow-based prediction of post-treatment brain MRI from pre-radiotherapy priors for patients with glioma
Purpose/Objective: Brain tumors result in 20 years of lost life on average. Standard therapies induce complex structural changes in the brain that are monitored through MRI. Recent developments in ...
Selena Huisman, Nordin Belkacemi, Vera Keil, Joost Verhoeff, Szabolcs David
Leaderboard Incentives: Model Rankings under Strategic Post-Training
Influential benchmarks incentivize competing model developers to strategically allocate post-training resources toward improvements on the leaderboard, a phenomenon dubbed benchmaxxing or training ...
Yatong Chen, Guanhua Zhang, Moritz Hardt
M$^3$-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineering
Multimodal large language models have recently shown promising progress in visual mathematical reasoning. However, their performance is often limited by a critical yet underexplored bottleneck: ina...
Peijin Xie, Zhen Xu, Bingquan Liu, Baoxun Wang
Local-Global Prompt Learning via Sparse Optimal Transport
Few-shot adaptation of vision-language models (VLMs) like CLIP typically relies on learning textual prompts matched to global image embeddings. Recent works extend this paradigm by incorporating lo...
Deniz Kizaroğlu, Ülku Tuncer Küçüktas, Emre Çakmakyurdu, Alptekin Temizel
SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
Answering complex, real-world queries often requires synthesizing facts scattered across vast document corpora. In these settings, standard retrieval-augmented generation (RAG) pipelines suffer fro...
Yagiz Can Akay, Muhammed Yusuf Kartal, Esra Alparslan, Faruk Ortakoyluoglu, Arda Akpinar
Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology
Multiple instance learning (MIL) has enabled substantial progress in computational histopathology, where a large amount of patches from gigapixel whole slide images are aggregated into slide-level ...
Mina Jamshidi Idaji, Julius Hense, Tom Neuhäuser, Augustin Krause, Yanqing Luo, Oliver Eberle, Th...
Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design
We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with symbolic computation tools, and human strategic ...
Hai Xia, Carla P. Gomes, Bart Selman, Stefan Szeider
CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support
Large language models (LLMs) show significant potential for clinical decision support (CDS), yet their black-box nature -- characterized by untraceable reasoning and probabilistic hallucinations --...
Liuyi Xu, Yun Guo, Ming Chen, Zihan Dun, Yining Qian, An-Yang Lu, Shuang Li, Lijun Liu
Human-AI Divergence in Ego-centric Action Recognition under Spatial and Spatiotemporal Manipulations
Humans consistently outperform state-of-the-art AI models in action recognition, particularly in challenging real-world conditions involving low resolution, occlusion, and visual clutter. Understan...
Sadegh Rahmaniboldaji, Filip Rybansky, Quoc C. Vuong, Anya C. Hurlbert, Frank Guerin, Andrew Gilbert
Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regula...
Yehonatan Elisha, Oren Barkan, Noam Koenigstein
Novel Semantic Prompting for Zero-Shot Action Recognition
Zero-shot action recognition relies on transferring knowledge from vision-language models to unseen actions using semantic descriptions. While recent methods focus on temporal modeling or architect...
Salman Iqbal, Waheed Rehman