Lagrangian Neural Networks (LNNs) learn mechanical systems from trajectory data by parameterizing a scalar Lagrangian and deriving the dynamics through the Euler-Lagrange equations, biasing the model toward motion that respects the variational structure of mechanics. The interactions studied so far have been pairwise-a...
Sena Kalabalik, Sukru Caglar, Abdullah Umut Hamzaogullari et al.· 0 citations
Vision-language models (VLMs) exhibit complementary capabilities, yet selecting the most suitable expert for a given image-question query remains challenging due to heterogeneous multimodal inputs and varying expert strengths. Existing routing approaches rely on text-based cues or static model profiles, failing to capt...
Wenjuan Zhu, Zheming Yang, Yunqing Hu et al.· 0 citations
It is shown that CopRoute's ordering attains, on the design data, the best guarantee any efficient fixed-ordering algorithm can give for the average number of calls to the first correct model, and that a separate calibration step certifies the all-miss risk of the deployed sets.
In this paper, we propose Data-Adaptive Mahalanobis Cross-Head Attention (DAMCHA), a simple and effective attention mechanism that generalizes Multi-Head Attention (MHA) through the lens of metric learning. Standard MHA implicitly learns a static, head-wise Euclidean similarity corresponding to the diagonal blocks of a...
Zhen-Ke Duan, Xin Li, Ji-Qun Pan et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Neural surrogates provide computationally efficient auto-regressive modeling of wave propagation, enabling e.g. fast inverse solutions. Despite recent progress, the current surrogates are not yet sufficient for the needs of ultrasonic sensing, characterized by high frequency and heterogeneous propagation media. We show...
Burla Nur Korkmaz, Petro Moilanen, Ari Salmi et al.· 0 citations
Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignment provides such correspondence at the chunk level, but leaves a distinct problem unresolved: credit alignment. A chunk-level signal specifies how much a span should chan...
Jingru Yang, Jinhang Wu, Minjing Shi et al.· 0 citations
On-Policy Distillation (OPD) has emerged as a powerful paradigm for transferring reasoning capabilities from frontier models to smaller models, while extending its success to multi-turn agentic environments remains challenging. We study agentic OPD through interaction states, distinguishing the objective task and execu...
Zhen-Tao Zhang, Yan-Zhao Zheng, Yan-Lin Liu et al.· 0 citations
Lagrangian Neural Networks (LNNs) learn dynamics from trajectory data by parameterizing a scalar Lagrangian and deriving accelerations through the Euler--Lagrange equation, providing a variational inductive bias that improves physical consistency over purely data-driven models. LNNs have recently been extended to gener...
Sukru Caglar, S. Kalabalik, Abdullah Umut Hamzaogullari et al.· 1 citation
Cancer diagnosis and treatment increasingly rely on multi-modal diagnostic technologies that generate high-dimensional datasets. Although these datasets are rich in pathological information, they pose considerable challenges in interpretation, dimensionality reduction, and clinical applicability. Conventional machine l...
Ali Anaissi, Yuan-Zhe Jia, Qi-Shun Peng et al.· 0 citations
Learning new tasks in multimodal continual instruction tuning can cause catastrophic forgetting of previously acquired knowledge. Although multi-expert LoRA distributes learning across experts, updates to a dense low-rank expert can still affect many output features. We introduce Monarch-MoE, which replaces the dense f...
Xi Zhang, Bo-Yu Diao, Ze-Sen Chen et al.· 0 citations
Across both models, different equal-budget masks win on different windows, and a retrospective oracle significantly improves over the best static mask on every dataset, however, dataset-specific masks transfer inconsistently, and Chronos representations do not support reliable unseen-domain routing.
A unified view is developed in which the log-probability ratio between a proxy expert and a proxy reference defines an implicit reward for KL-regularized policy optimization, which enables any-to-any transfer across models that differ in scale, training stage or generation.
Rong Wu, Dao-Cheng Fu, Yu Yang et al.· 0 citations
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.
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
