Predicting student performance from educational interaction data requires models that are both accurate and sufficiently transparent to support meaningful intervention, while demographic information introduces an additional risk of unfair predictions. This study investigates a multi-objective framework that combines re...
Bente Hinkenhuis, S. S. M. Ziabari, A. M. Alsahag· 0 citations
Frequency-collapse attention [Zeris, 2026e] achieves large gains over standard dot-product attention by replacing the Q/K dot product with a bandpass-filtered inner product at a learned frequency. A natural follow-up question is: which filter shape works best, and why? We test five hypotheses about filter properties --...
Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visible chain-of-thought (CoT). This is a limit case for behavioral oversight, where surface tokens carry no information about the underlying reasoning. But hidden from the o...
Kaley Brauer, Claudio Mayrink Verdun, Samuel Marks· 0 citations
Self-conditioning is a core technique that enhances continuous flow-based language models, where the model learns to denoise generated text by conditioning on its own denoising estimate. While empirically successful, its performance improvements are poorly understood. Moreover, there is growing interest in the use of f...
Jaehoon Yoo, Wonjung Kim, Floor Eijkelboom et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Vision-language models that answer questions about chest radiographs are evaluated by their accuracy on labels derived from radiology reports. High benchmark accuracy is often interpreted as evidence that the model uses the image. A model that answers from the finding named in the question can score as well as a model...
Mahshad Lotfinia, Sebastian Ziegelmayer, Lisa Adams et al.· 0 citations
Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilingual settings, they lack adaptation to Chinese-specific regulatory policies, cultural context, and linguistic nuances, failing to support fi...
Wenbo Yu, Bohua Wang, Hao Fang et al.· 0 citations
Clinical early warning systems built on irregularly sampled medical time series (ISMTS) from electronic health records must deliver continuous risk scores for patient triage as well as interpretable rationales that clinicians can verify. Large language models (LLMs) are uniquely positioned for both, deriving risk from...
Hyeongwon Jang, Gyouk Chu, Changhun Kim et al.· 0 citations
Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific expressions grounded in shared interaction history; that is, with conceptual pacts. Prior work shows that multimodal LLMs fail to become more efficient across rounds, although they align on the l...
Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensi...
Qiming Shi, Zhaolu Kang, Yunfan Zhou et al.· 0 citations
Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often collapse stable user facts, episodic events, and behavioral rules into a shared space, allowing functionally distinct memories to be retrieved...
Hyeonjeong Ha, Jeonghwan Kim, Cheng Qian et al.· 0 citations
Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model families. We present the first large-scale evaluation of CoT monitorability across 1...
Eric Onyame, Runtao Zhou, Kowshik Thopalli et al.· 0 citations
Large language models (LLMs) can be said to have preferences: they reliably pick certain tasks and outputs over others, and preferences shaped by post-training and prompting appear to influence much of their behaviour. But models can also adopt different personas which have radically different preferences. How is this...
Oscar Gilg, Pierre Beckmann, Daniel Paleka et al.· 0 citations
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
