AirFM-DDA is proposed, an Air-interface Foundation Model in the Delay-Doppler-Angle (DDA) domain, which reparameterizes CSI into the DDA domain to resolve multipath components along physically meaningful axes and employs window-based attention with frame-structure-aware positional encoding.
Kejia Bian, Meixia Tao, Jianhua Mo et al.· arXiv.org· 6 citations· ⚡1
The platform supports an end-to-end workflow encompassing EIS preprocessing with selectable impedance representations, agent setup and training, ECM generation for new measurements, and visualization-based evaluation and analysis of agent decision-making.
A. Jaberi, Yonatan Kurniawan, Robert Black et al.· 0 citations
This work pairs the brain emulator with large language models that generate news headlines from linguistic parameters such as valence, arousal, and dominance and shows that these parameters can be recovered from predicted brain maps, demonstrating that the emulator's synthetic neural encodings preserve information about the controlled stimulus dimensions.
Niels Bracher, Xavier Intes, Stefan T. Radev· arXiv.org· 0 citations
Experiments on synthetic and real-world benchmarks show that FG$^2$-GDN and its variant improve associative recall and long-context understanding over GDN and KDA, with comparable computational efficiency.
Ping-Wei Sun, Yuxuan Hu, Jian-Chao Tan et al.· arXiv.org· 1 citation· ⚡1
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work describes coordinated perturbation as a budgeted subset-selection problem over pairwise observations and introduces an Adaptive Subset Selection Attack (ASSA) as a scalable search heuristic for probing high-impact perturbation sets.
REALM is proposed, which jointly learns the model parameters and a scalar expertise value for each annotator, entirely unsupervised and requiring nothing beyond annotator identity, and extends to multiple tasks via a learned expertise matrix.
Sajjad Ghiasvand, M. Beliaev, Mahnoosh Alizadeh et al.· arXiv.org· 0 citations
This work proposes MOONSHOT, a general and flexible framework that extends any single-objective pruning method into a multi-objective formulation by jointly optimizing both the layer-wise reconstruction error and second-order Taylor approximation of the training loss.
Gabriel Afriat, Xiangui Meng, Shibal Ibrahim et al.· Trans. Mach. Learn. Res.· 0 citations
This work augments a large, fully annotated experimental dataset for batch distillation with a corresponding simulation dataset, creating a novel hybrid dataset that provides a unique basis for simulation-to-experiment style transfer, the generation of pseudo-experimental data, and future research on deep AD methods in chemical process monitoring.
Jennifer Werner, J. Arweiler, Indra Jungjohann et al.· Computers & Chemical Eng...· 0 citations
EvoLen is a tokenizer that combines evolutionary stratification with length-aware decoding to better preserve motif-scale functional sequence units and demonstrates that tokenization introduces a critical inductive bias and that incorporating evolutionary information yields more biologically meaningful and interpretable sequence representations.
Nan Huang, Xiaoxiao Zhou, Junxia Cui et al.· arXiv.org· 0 citations
This work introduces LIBERO-Para, a controlled benchmark that independently varies action expressions and object references for fine-grained analysis of linguistic generalization in VLA models, and proposes PRIDE, a metric that quantifies paraphrase difficulty using semantic and syntactic factors.
Chanyoung Kim, Minwoo Kim, Minseok Kang et al.· arXiv.org· 7 citations· ⚡2
Identification of causal directionality in bivariate numerical data is a fundamental research problem with important practical implications. This paper presents two alternative methods to identify direction of causation by considering conditional distributions: (1) Anticipated Asymmetric Geometries (AAG) and (2) Monotonicity Index (MI). The AAG method compares the actual conditional distributions to anticipated ones along two variables. Different comparison metrics, such as Pearson correlation, cosine distance, Jaccard index, K-L divergence, K-S distance, MAE, MSE, and mutual information have been evaluated. Anticipated distributions have been projected as normal based on dual response statistics: mean and standard deviation. The MI method compares the calculated monotonicity indexes of the gradients of conditional distributions along two axes and exhibits counts of gradient sign changes. Both methods assume stochastic properties of the bivariate data and exploit anticipated unimodality of conditional distributions of the effect. The proposed methods are straightforward and include only a limited number of hyperparameters that affect the accuracy of the identification. For a given set of hyperparameters, both the AAG and MI methods provide a unique, deterministic solution. To address sensitivity to hyperparameters, tuning has been done by utilizing a full factorial Design of Experiment. It turns out that the AAG method outperforms MI, achieving top weighted accuracies of 81.4% with simple tuning and 84.3% with size-adaptive tuning, compared with 81.6% for GRCI or 82.0% for CAREFL-H on the 99 pairs of the Tubingen real-world cause-effect examples. A decision tree has been fitted to distinguish misclassified cases using the input data's symmetrical bivariate statistics to address the question of: How decisive is the identification method of causal directionality?
These results suggest that in diversity-aware multi-armed bandits, e.g., for generative model selection, exploration can arise intrinsically from the objective's geometry, particularly for widely used metrics such as FID and Vendi where tight confidence bounds are difficult to construct.
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
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.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
