This work calls on specialist developers to provide consistent representation interfaces and, especially, on LLM developers to train models to receive, combine and reason with these inputs, which could expand scientific agents' information while preserving conventional tools'flexibility.
Study of 2PL, GPCM, and NRM decoders paired with LSTM, Transformer, and DKVMN encoders shows why item parameters, especially discrimination and option slopes, must be evaluated separately from response prediction.
Wen-Rui Yuan, S. M. van den Berg, J. Steinrücke· 0 citations
A spectral framework based on the singular value structure of the prior-preconditioned forward operator is proposed, which provides an exact, interpretable decomposition of the posterior covariance into data-informed and indeterminacy epistemic components, enabling precise accounting of uncertainty reduction through Ba...
Ismail Huseynov, S. Haufe· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work proposes MoEZip, a routing-aware KV cache compression for sparse MoE language models, and proposes a novel metric based on the Fisher information matrix of routing distributions that combines attention weights for routing-aware scoring of contexts.
We consider the problem of model order reduction (MOR) in reproducing kernel Hilbert spaces (RKHSs). We prove generalizations of well-known necessary interpolatory conditions for norm-optimal reduced-order models, originally stated for rational functions in $H_2$ Hardy-Hilbert spaces. We construct an alternative to the...
Tamás Dózsa, Andrea Angino, Rolf Krause et al.· 0 citations
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acquired ones, resulting in catastrophic forgetting. As a trajectory unfolds, different stages may require different capabilities, yet conventional joint t...
Rui Shi, Xunjian Yin, Jiacheng Sang et al.· 0 citations
This work proposes WSR-Tune, a Weight Space Reparameterization-based fine-tuning framework that preserves safety during downstream adaptation and achieves a more favorable trade-off between downstream performance and safety retention, demonstrating its effectiveness for reliable LLM fine-tuning.
Minsu Kim, Jongbok Won, Jeesup Park et al.· 0 citations
Location encoders learn compact representations of latitude--longitude coordinates for downstream geospatial prediction tasks. Existing approaches are pretrained using continuous or naturally occurring supervision, such as imagery, climate variables, or species distributions, and therefore do not explicitly capture adm...
Deep learning for EEG-based seizure detection faces critical challenges: severe annotation scarcity and extreme class imbalance, where ictal events comprise less than 10\% of clinical recordings. We present DiffEEG, a 9.6M-parameter self-supervised foundation model that addresses both limitations through denoising diff...
Abdulkader Helwan, Lina Abou-Abbas, Hussein El Amouri et al.· 0 citations
Multi-Meta-RAG improves retrieval for multi-hop question answering by filtering a vector store on metadata, specifically the news source and the publication date, which it extracts from each query using GPT-3.5. This extractor requires a proprietary API call for every query, and its output is not restricted to the allo...
In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with every generated token. Under high concurrency, aggregate memory usage therefore increases endogenously over time: the service process itself creates future ca...
Ruicheng Ao, Jing Dong, Gan Luo et al.· 0 citations
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 27, 2026
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
