Collaborative analysis of decentralized confidential datasets is important, but direct sharing of original datasets is often restricted by privacy and institutional constraints. Data collaboration (DC) analysis transforms each dataset into privacy-preserving intermediate representations via party-specific obfuscation functions and integrates them into common collaboration representations using an anchor dataset. However, many existing DC analysis methods rely on linear transformations for data obfuscation and integration, which may increase reconstruction risk. Although nonlinear dimensionality reduction can mitigate this risk, conventional linear integration methods cannot accurately align intermediate representations produced by nonlinear transformations. Moreover, existing integration methods mainly minimize discrepancies among parties and do not explicitly incorporate geometric or target-variable information useful for downstream analysis. To overcome these limitations, we first formulate linear target-normalized integration (LTI) as a linear integration method and then kernelize it to obtain kernel-based target-normalized integration (KTI). KTI admits a globally optimal solution via kernel ridge regression and an eigenvalue problem. We also introduce graph regularization and a centering constraint so that the target representation can capture geometric and target-variable information useful for downstream analysis. Experiments on image classification tasks demonstrate that KTI improves classification accuracy over existing linear integration methods under nonlinear dimensionality reduction, with further gains from target-variable-aware graph regularization and centering. The results also show that dimensionality reduction choices substantially affect both classification accuracy and reconstruction risk.
Yamato Suetake, Yuta Kawakami, Shunnosuke Ikeda et al.· 0 citations
It is concluded that progress in two-phase AI now depends as much on findable, decodable, benchmarkable, benchmarkable, and physically interpretable data infrastructure as on model architecture.
Christy Dunlap, Ridwan Olabiyi, Firas Al-Hindawi فراس الهنداوي et al.· Transport Phenomena· 0 citations
This work presents ImplicitTerrainV2, which advances terrain INRs toward a compact, efficient neural terrain data format by combining a spectral control mechanism with wavelet-guided spatial adaptivity, derivative-aware supervision, and post-training model compression.
Haoan Feng, Xin Xu, Leila De Floriani· arXiv.org· 0 citations
Activation steering has emerged as a lightweight approach for modifying language model behavior without parameter updates, yet existing methods remain brittle: unstable across layers and prone to disturbing behavior unrelated to the target concept. We trace these failures to a hidden assumption shared by widely-used methods such as CAA, ActAdd, and ITI: that the intermediate activation space is Euclidean. We show this assumption is fundamentally flawed. The metric that actually governs how a hidden-state perturbation changes the output is the Fisher information metric of the softmax layer, pulled back to the intermediate layer through the Jacobian of the intervening layers. From it we derive a closed-form steering direction, applied to a hidden state at an intermediate layer, that reaches a target concept change with the least non-target distortion. The framework is sharpest in the early and middle intermediate layers, where the metric is strongly non-Euclidean and geometric correction matters most. We evaluate it on three verb-morphology concepts: third-person-singular, progressive, and past-tense inflection, following standard counterfactual-concept evaluation. On GPT-2 Small, this non-Euclidean geometry is borne out empirically, and our method lowers off-target KL divergence by median factors of 1.4--6.5x against individual steering baselines. On Llama-3-8B and Qwen3-8B, it lowers off-target KL by median factors of 1.8--3.6x against individual baselines at the early and middle layers. These results show that geometric correction retains its advantage on larger models with more complex internal structure.
Sihan Wang, Jiayi Zhao, Qingyan Cao et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
These results suggest a tractable operator-level description of learning near dynamical transitions, together with scalable diagnostics for amplified low-dimensional learning geometry.
A posterior-sampling algorithm is proposed and shown that both are competitive with full-prior latent bandits when same-state instances share reward parameters, and preferable to them when reward scales differ between instances with the same latent state.
Emil Carlsson, Newton Mwai, Fredrik D. Johansson· arXiv.org· 0 citations
Finite-iteration behavior of the exact asynchronous recursions used by categorical distributional temporal-difference methods is studied and analogous finite-iteration guarantees for horizon-stacked categorical methods under episodic sampling are established.
Ege C. Kaya, Abolfazl Hashemi· arXiv.org· 2 citations
It is shown that the maximum hypergraph density of any multiclass hypothesis class is upper-bounded by its DS dimension, which proves a longstanding conjecture of Daniely and Shalev-Shwartz (2014) and determines the optimal dependence of the sample complexity on the DS dimension for multiclass as well as list learning.
A feasibility study based on a 2.5D U-Net architecture to detect GME in space-time connected data, resulting in improved detection of moving GMEs against the background with respect to classical spot detection algorithms and 2D U-Net, yet retaining real-time execution speed with respect to more complex deep-learning architectures is proposed.
Andrea Angino, Ken Trotti, D. U. Pizzagalli et al.· 0 citations
A performance recovery framework based on Self-Distillation Fine-Tuning (SDFT) that effectively restores model capabilities and offers new insights into the internal mechanisms of self-distillation is introduced.
This work formalises LH in a core probabilistic programming language (PPL) and gives sufficient syntactic conditions for its prevention, proving that a safe language fragment satisfying these conditions cannot produce likelihood-hacking programs.
Jacek Karwowski, Y. Kaddar, Zihuiwen Ye et al.· arXiv.org· 2 citations
This work proposes a flexible, effective sampling method for masked language models (MLMs), and reports results from an extensive in vitro head-to-head evaluation for the antibody engineering setting, revealing that the choice of sampling method can have a substantial impact, motivating future research into this under-explored area.
Calvin McCarter, Nicholas Bhattacharya, Sebastian W. Ober et al.· arXiv.org· 1 citation
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
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
