The stability of safety refusal decisions across random seeds and temperature settings is investigated by investigating the stability of safety refusal decisions across random seeds and temperature settings to demonstrate that single-shot safety evaluations are insufficient for reliable safety assessment and that evaluation protocols must account for stochastic variation in model behavior.
An end-to-end approach that fuses MMFMs with translation LLMs, enabling joint end-to-end training and achieving a 1-second latency reduction in SimulST compared to cascaded pipelines and also improves the overall translation quality is proposed.
Sai Koneru, Matthias Huck, Jan Niehues· arXiv.org· 0 citations
This work proposes Think-at-Hard (TaH), a looped transformer optimized for selective iteration that employs a lightweight neural decider to trigger latent iteration, only at tokens likely to be incorrect after the standard forward pass.
Tianyu Fu, Yichen You, Ze-Kai Chen et al.· 0 citations
A conceptual bias sensitive news interface is proposed that visualizes emotional cues across news sources and helps readers notice affective framing patterns in daily news.
Mohd Ruhul Ameen, Akif Islam, Abu Saleh Musa Miah et al.· 2026 International Conferenc...· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
PRISM, an agentic retrieval framework that leverages large language models in a structured loop to retrieve relevant evidence with high precision and recall, achieves higher retrieval accuracy while filtering out distracting content, enabling downstream QA models to surpass full-context answer accuracy while relying on significantly less irrelevant information.
Md Mahadi Hasan Nahid, Davood Rafiei· arXiv.org· 8 citations
OceanGym is introduced, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments, and reveals substantial gaps between state-of-the-art MLLM-driven agents and human experts.
Yida Xue, Mingjun Mao, Xiangyuan Ru et al.· 0 citations
Safety-aware Contrastive Decoding (SafeCoDe) is introduced, a lightweight and model-agnostic decoding framework that dynamically adjusts token generation based on multimodal context that consistently improves context-sensitive refusal behaviors while preserving model helpfulness.
This work introduces a 98% automated pipeline to produce high-quality Quranic datasets and presents a novel ASR-based approach for pronunciation error detection utilizing the authors' custom Quran Phonetic Script (QPS) to encode Tajweed rules (unlike the IPA standard for Modern Standard Arabic).
Abdullah Abdelfattah, Mahmoud I. Khalil, Hazem M. Abbas· arXiv.org· 1 citation
This work introduces a controlled setting to study the causes and training dynamics of cross-lingual knowledge transfer by training small Transformer models from scratch on synthetic multilingual datasets and suggests methods to encourage representational unification as part of training that would improve LLMs'cross-lingual transfer.
C. Blum, Katja Filipova, Ann Yuan et al.· arXiv.org· 5 citations
Cognitive Chain-of-Thought (CoCoT) is introduced, a reasoning framework that structures vision-language-model reasoning through three cognitively inspired stages: Perception, Situation, and Norm, showing that structuring model reasoning through cognitively grounded stages enhances interpretability and social alignment, laying the groundwork for more reliable multimodal systems.
Eunkyu Park, Wesley Hanwen Deng, Gunhee Kim et al.· 3 citations
Empirically, PRISM reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines, and achieves this efficiency while simultaneously enhancing performance, surpassing models fine-tuned on the full dataset across eight multimodal and three language understanding benchmarks.
Jinhe Bi, Yifan Wang, Danqi Yan et al.· arXiv.org· 73 citations· ⚡4
This work proposes Short-Films 20K (SF20K), the largest publicly available movie dataset, and accompanies this dataset with SF20K-Test, a manual, open-ended question answering benchmark, showing that instruction tuning on the large-scale dataset substantially improves model performance.
Ridouane Ghermi, Xi Wang, Vicky Kalogeiton et al.· International Journal of Com...· 11 citations· ⚡1
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.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
