Identifying which tokens and activations truly influence model predictions is critical for both the efficiency and interpretability of large auto-regressive language models. Yet in practice, token importance is typically inferred from attention distributions that entangle contextual relevance with softmax-normalization...
Debabrata Mahapatra, Shubham Agarwal, Apoorv Saxena et al.· 0 citations
We propose co-creative learning as a novel paradigm where humans and AI, i.e., biological and artificial agents, mutually integrate their partial perceptual information and knowledge to construct shared external representations, a process we interpret as symbol emergence. Unlike traditional AI teaching based on unilate...
Ryota Okumura, Tadahiro Taniguchi, Akira Taniguchi et al.· 0 citations
[...] Since then, various APR approaches, especially those leveraging the power of large language models (LLMs), have been rapidly developed to fix general software bugs. Unfortunately, the effectiveness of these advanced techniques in the context of regression bugs remains largely unexplored. This gap motivates the ne...
Anh Ho, Thanh Le-Cong, Bach Le et al.· 0 citations
Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where removing data inadvertently impairs model utility. While prior work has focused on architectural innovations, the influence of data-level factors remains underexplored. We introduc...
Peizhi Niu, Evelyn Ma, Boya Hou et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language models (LLMs) have demonstrated the ability to generate formative feedback and instructional hints in English, making them increasingly relevant for AI-assisted education. However, their ability to provide effective instructional support across different languages, especially for mathematically grounded...
LLM benchmarks are often treated as coherent measurement units, yet they are heterogeneous collections of instances spanning diverse domains, skills, formats, and contexts. As a result, aggregate benchmark scores can conflate model capability with benchmark composition, obscuring what existing benchmarks actually cover...
Eunsu Kim, Haneul Yoo, Guijin Son et al.· 0 citations
It is found that, across multiple pre-trained decoder-only LLMs, the analyzed personas show large differences in representation space only within the final third of the decoder layers.
C. Cintas, M. Rateike, Erik Miehling et al.· AAAI/ACM Conference on AI, E...· 3 citations
Generative AI (GenAI) is rapidly advancing the field of Autonomous Driving (AD), extending beyond traditional applications in text, image, and video generation. We explore how generative models can enhance automotive tasks, such as static map creation, dynamic scenario generation, trajectory forecasting, and vehicle mo...
Katharina Winter, Abhishek Vivekanandan, Rupert Polley et al.· 0 citations
Deep neural networks (DNNs) play a crucial role in the field of artificial intelligence, and their security-related testing has been a prominent research focus. By inputting test cases, the behavior of models is examined for anomalies, and coverage metrics are utilized to determine the extent of neurons covered by thes...
Wenkai Li, Xiaoqi Li, Yingjie Mao et al.· 0 citations
Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its therapeutic potential for complex diseases. However, identifying effective reprogramming strategies through classical wet-lab experiments is hindered by lengthy time commitme...
The subcellular localization of RNAs, including long non-coding RNAs (lncRNAs), messenger RNAs (mRNAs), microRNAs (miRNAs) and other smaller RNAs, plays a critical role in determining their biological functions. For instance, lncRNAs are predominantly associated with chromatin and act as regulators of gene transcriptio...
Cece Zhang, Xuehuan Zhu, Nick Peterson et al.· 0 citations
Space missions are becoming increasingly ambitious, necessitating high-performance onboard spacecraft computing systems. In response, field-programmable gate arrays (FPGAs) have garnered significant interest due to their flexibility, cost-effectiveness, and radiation tolerance potential. Concurrently, neural networks (...
