Speech-based Alzheimer's disease (AD) assessments increasingly rely on pretrained self-supervised learning (SSL) models that learn acoustic representations directly from raw audio, exposing the model to recording factors. We ask whether such factors are merely encoded in SSL representations or can systematically alter...
Serli Kopar, Alkis Koudounas, R. Rane et al.· 0 citations
Large Language Models (LLMs) are increasingly applied to process streaming data, with practitioners relying on benchmarks to select the best model even though these signals only approximate real performance. While oracle annotations can provide reliable feedback, they are often costly and difficult to obtain at scale....
Alessandro Turrin, Patrik Okanovic, Torsten Hoefler et al.· 0 citations
Model intelligence and fast response jointly shape the quality of interaction with speech language models, yet remain difficult to achieve together. Explicit chain-of-thought (CoT) improves reasoning and audio understanding, but generating intermediate reasoning tokens delays responses. Describing fine-grained acoustic...
Yu-Xiang Wang, Kun-Yu Feng, Yuan-Cheng Wang et al.· 2 citations
Collaboration depends on shared context, and technical documentation is one way that context persists across people and AI teammates. Specificity, the amount and exactness of detail expressed in language, shapes what information documentation captures and how precisely that information is communicated. This work audits...
Rocker D'Antonio, Thomas Benton Townsend, D. Manias· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
RPTune is proposed, an end-to-end framework that couples learned catalog curation with LLM post-training using automatically generated, catalog-grounded supervision, and consistently improves search accuracy across both proprietary and open-weight LLMs.
Chu-Xuan Hu, He-Jie Cui, Norman Huang et al.· 0 citations
This work presents VERITYGATE, a four-gate checker for declared evidence IDs, entities, numbers, and claim types, which checks a fixed schema; it does not verify every fact in the prose.
Language models learn content and style jointly, making stylistic variation in their outputs difficult to identify and control. We study whether recurring styles in model responses can be discovered without supervision and explicitly controlled. We design an algorithm that learns to separate representations of content...
Ioana Marinescu, E. Oermann, Kyunghyun Cho· 0 citations
Explainable suicide-risk assessment requires models not only to estimate risk severity, but also to identify supporting language and the risk and protective factors expressed in a post. We present our system for the IEEE BigData 2026 Cup on Explainable Suicide Risk Assessment on Social Media, which addresses three task...
Xuan-Zhong Feng, Geoffrey Martin, He-Xin Dong et al.· 0 citations
Speculative decoding accelerates large language model inference by drafting future tokens cheaply and verifying them with the target model in parallel. Block drafters score a whole block of future tokens in one forward pass, yet standard decoding verifies only the top-scoring chain and discards the other candidates. Be...
Fine-tuning adapts aligned large language models (LLMs) to downstream tasks, but a few dozen harmful examples can remove their refusal of harmful requests. Prior work localizes safety-related behavior to specific layers, directions, and tokens, suggesting targets for protection. We test whether successful localization...
Jungseob Lee, D. Lee, Sugyeong Eo et al.· 1 citation
Audits of AI visibility summarise the brand recommendations of deployed language models into per-system profiles. We test whether such a profile describes the system on one corpus of 6,475 stored responses (6,324 analysable) collected between December 2025 and February 2026 from five deployed endpoints across gift-reco...
Several recent pipelines build RLVR training data by masking a span of real corpus text and asking a language model to invent plausible wrong answers around it. The correct option is therefore genuine human prose; every distractor is synthetic. Correctness and provenance become entangled, and a policy could in principl...
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.
