Latent Space Alignment

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 25

Oct 7, 2026cs.LG

Shared Gaussianization: What Gaussian Regularizers Certify About Contrastive Learning, and What They Miss

What can a distribution-matching regularizer such as SIGReg in LeJEPA certify about contrastive learning? We study shared Gaussianization (SG), a characteristic-function Gaussianity test on the average of two normalized views, scaled by an independent

χ_d

radius. Because disagreeing views shorten the average, one test detects both misalignment and non-uniformity. SG vanishes exactly at the aligned, uniform minimizers of population InfoNCE, and under equal marginals it bounds the InfoNCE excess by

4\cdot 3^{3/4}β

times the square root of the SG loss, plus a term linear in the loss. The square-root rate and this dimension-free constant are sharp, and no squared mean-embedding distance on view pairs achieves a faster rate. With an explicit alignment term, a rotation-invariant uniformity test gives a linear bound if and only if its spectrum dominates that of InfoNCE's kernel

e^{βu^\top v}

; SG's own test does, Gaussian kernels

e^{-γ\|u-v\|^2}

qualify exactly when

γ\ge β/2

, and moment matching never does. Away from the optimum, the objectives differ. Along an isotropic nuisance channel, pure SG lowers its loss by adding per-view nuisance whenever the shared code is non-uniform. An alignment weight above the channel's gain makes the nuisance-free solution a strict local minimizer; for LeJEPA, the same rule gives a critical SIGReg weight that decreases with the batch size. At finite batch size, an off-diagonal U-statistic removes a plug-in bias toward misalignment. In controlled latent-variable models, pure SG retains per-view style, an alignment weight above the measured gain removes it, and for LeJEPA at three batch sizes the measured gain separates the encoders that retain style from those that do not. InfoNCE training also reaches a lower SG

_{0.2}

loss than SG

_{0.2}

training from scratch, which points to an optimization gap.

Ruoyu Zhao, Yuting Chen, Jinheng Zhang +2

City University of Hong Kong · Georgia Institute of Technology · University of Pennsylvania +2

Contrastive Learning Self-Supervised Visual Representation Learning Latent Space Alignment

Oct 7, 2026eess.AS

A Strength-Monotonic Law for Domain Alignment in Frozen-Embedding Bioacoustic Classification

When does distribution alignment help a frozen foundation-model embedding generalize across acoustic domains? For cross-domain mosquito-species classification we report a strength-monotonic law: the stronger an encoder is on the target task, the more its unseen-domain generalization relies on a distribution-alignment (MMD) term, and the more it is harmed by domain-rebalanced sampling. Across four encoder families and a within-encoder HuBERT layer sweep (n=8), the rebalancing leg orders exactly with encoder strength (Spearman -1.000), while the MMD-benefit leg is monotonic within each stream and -0.857 pooled; fixing architecture and varying only representation strength flips the rebalancing effect from benefit to collapse. The law is actionable: a single MMD term is the sole lever on a strong encoder, so we reduce the field's default recipe to a frozen Perch 2.0 embedding, a lightweight probe, cross-entropy, one MMD, and input augmentation. The reduced recipe stays within seed noise of the full composite (BA_unseen 0.299+/-0.006 vs. 0.307+/-0.014). As boundary conditions of the same law, three community defaults (backbone fine-tuning, multi-modal fusion, and domain rebalancing) each hurt unseen-domain accuracy under a leave-domain protocol, shown with single-variable, multi-seed evidence. We present a mechanism and the recipe it explains, not a leaderboard entry.

Yucheng Gong, Rui Zhou, Binbin Zeng +2

Department of Software Engineering, School of Software, Chongqing Finance and Economics College Chongqing Key Laboratory of Data Mining and Integrated Application for Ecological Environment

Cross-Domain Generalization Audio Classification Audio Representation Learning Latent Space Alignment

Oct 6, 2026cs.LG

Learning Cross-Model Activation Alignments with Explicit Many-to-Many Layer Maps

LLMs are released at a rapid pace, raising a natural question: how do two independently trained models relate, both in which layers correspond and in how features transform between them? We study this by learning an activation alignment, a map from a source model's layerwise activations to a target's. Our method, MATCHA, factors this map into a layer map, whose output is an explicit target-by-source matrix that can be extracted and inspected, and a layer-shared feature map between hidden spaces. Most of prior work fixes the layer correspondence in advance, pairing layers at roughly the same relative depth; in contrast, we learn both factors jointly from prompts. Across 42 pairs of seven models spanning three different families, MATCHA reconstructs the target's activations more faithfully and improves retrieval-based metrics substantially, w.r.t. previous approaches. The recovered maps are broadly monotone in depth but, in contrast with most previous approaches, are consistently many-to-many: each target layer draws on a band of source layers. Our alignments also enable transfer of activation-space interventions, allowing steering vectors and probes developed for one model to transfer to another.

Alina Sudakov, Guy Bar-Shalom, Fabrizio Frasca +1

Technion · Technion, NVIDIA Research

Latent Space Alignment Transfer Learning

Oct 5, 2026cs.CV

On Color Alignment in VAE Latent Spaces and Its Applications

Variational autoencoders (VAEs) are a key part of modern text-to-image models, which generate images within their latent space. VAEs are known to disentangle the main factors of variation in the data, and color is known to be one of the most structured of these in natural images: decorrelating it yields one luminance axis and two opponent-color axes. Color should therefore be expected to emerge as a distinct factor in the VAE latent space. Yet how these latent spaces represent color remains largely unexplored. In this work, we show that the VAEs of text-to-image models share a color subspace aligned with brightness and opponent-colors. Through a linear approximation of the encoder and targeted latent steering, we find this subspace consistently across a broad range of VAEs, from SD1.5 to FLUX.2 and Z-Image. Building on this characterization, we propose three applications: ColorTuning, which achieves state-of-the-art in precise numerical color generation on the fine-grained CSS3/X11 system of GenColorBench, saturation control, to adjust the global chromatic intensity, and color transfer, to change the palette to match a reference. The code and models are publicly available at https://julian075.github.io/Color_Subspace/

Julian D. Santamaria, Kai Wang, Jesús Malo +2

Computer Vision Center · Universitat Aut`onoma de Barcelona · City University of Hong Kong (Dongguan) +1

Variational Autoencoders Image Generation Representation Disentanglement Controllable Image Generation Latent Space Alignment

Oct 4, 2026cs.LG

Do Neural Networks Learn Structure-Preserving Maps? A Case Study in Latent-to-Hilbert Embeddings

We ask whether a neural network can learn a structure-preserving map from a compressed latent space to a Hilbert-space representation. Using an 8-dimensional autoencoder bottleneck on MNIST and

n

-qubit product-state targets from PCA-based angle encoding, we report four findings. Although the target angles are generated by a nonlinear sigmoid transformation of the latent projections, the resulting mapping is well approximated by a linear function over the observed latent distribution: linear regression from

z

to the true target angles achieves

R^{2} = 0.98

, while regression to the MLP's recovered angles achieves

R^{2} = 0.91

. The learned map's primary direction is strongly aligned with the target-induced direction, with cosine similarity

0.989

, while remaining nearly orthogonal to the input's principal direction, with cosine similarity

0.002

. The map is genuinely rank-4: removing any singular direction degrades inner-product preservation by

2.5

--

5.9\times

despite a singular-value spectrum with two dominant and two small values. The learned subspace does not coincide with the PCA basis used to construct the target, and different random seeds recover the same primary direction but diverge in higher ranks. Finally, kernel ridge regression with an RBF kernel outperforms a tuned MLP (IP error

0.0144

vs.\

0.0197

), suggesting that for approximately linear structure-preserving mappings, classical kernel methods may be a simpler and more effective alternative.

Muhammad Adnan Shahzad

Department of Computer Science and Software Engineering (CSSE) Montreal, QC, Canada

Representation Learning Latent Space Alignment

Sep 29, 2026cs.CL

NinaXander: Feasibility and Limits of Composing Frozen Language Models Across Architecture Families via a Shared Latent Space

In this paper we propose NinaXander, a series of composed language models obtained by connecting layers of frozen language models from different architecture families with a single trained shared-latent adapter. A composed model runs the first layers of one model, converts the resulting intermediate representation once with the adapter, and then runs the remaining layers of the other model. Once the adapter is trained, several composed models that connect at different layers are obtained without retraining. Using the recurrent RWKV-4-Raven-7B and the Transformer-based Tulu-Pythia-6.9b, abbreviated as RWKV and Pythia, this study examines whether frozen models from different families can be recombined post hoc. The composed models answered multiple-choice questions, and those whose generations we examined produced syntactically well-formed text. The configuration that combines the first 5 layers of Pythia with the remaining 27 layers of RWKV reduced the Transformer key-value (KV) cache by 84.4% with accuracy not significantly different from that of RWKV alone. In multiple-choice accuracy, however, no composed model matched the parent model Pythia, and language-modeling performance decreased sharply on WikiText, a corpus of Wikipedia articles outside the training domain. The correspondence between intermediate representations was also obtained in one favorable case, with a shared tokenizer, the same depth, and the same hidden width, and does not show that the models share a general semantic space.

Takanori Kotama, Shun-ichiro Hayashi, Daichi Mukunoki +2

Graduate School of Informatics Nagoya University · Information Technology Center Nagoya University

Latent Space Alignment

Sep 24, 2026cs.CG

It's the Geometry, Not the Model: Effective Rank and Subspace Alignment in Functional Connectivity Classification

Resting-state functional connectivity (FC) is widely used to classify brain phenotypes and disorders. Most pipelines use the full connectome and seek gains through model design. We instead examine how FC geometry constrains classification and cross-site transfer. Across-subject FC variation concentrates in a small effective subspace, suggesting substantial redundancy in nominal dimensions. Across cohorts, these subspaces may differ in orientation even when their effective ranks are comparable, potentially limiting transfer. Across 2,330 subjects from HCP, ABIDE, and ADHD-200, effective-rank analysis reveals strong spectral concentration. Projection onto leading components at the effective-rank scale recovers most of the full-FC classification performance. In ABIDE, site-specific effective subspaces are weakly aligned, and their principal-angle overlap predicts pairwise transfer after covariate adjustment despite comparable per-site effective ranks. Controlled rotations that alter subspace orientation while preserving the mean and covariance spectrum drive transfer toward chance, whereas displacement-matched label-orthogonal rotations do not. These results identify subspace orientation as a key factor in transfer degradation under controlled perturbations. This study offers a geometric diagnostic of FC generalization and suggests evaluating cross-site harmonization by its ability to align effective subspaces alongside classification accuracy.

Xiao Fan, Jingyuan Li, Yubo Han +6

Intrinsic Dimensionality Functional Connectivity Cross-Domain Transfer Learning Representation Alignment Latent Space Alignment

Sep 23, 2026cs.LG

Stable Neural Decoding Across Sessions via Task-Conditioned Latent Alignment for Brain-Machine Interfaces

Achieving stable long-term neural decoding in invasive brain-machine interfaces (BMIs) remains challenging due to variations in recorded neural populations across sessions. Current latent alignment approaches may overlook task-dependent structure during cross-session adaptation. We propose Task-Conditioned Latent Alignment (TCLA), a framework that stabilizes neural decoding by learning a shared latent space. TCLA learns a low-dimensional source representation using neural reconstruction and continuous behavioral supervision. During target-session adaptation, the shared representation is fixed, while target neural activity is mapped into the source latent space by aligning source and target distributions separately for each task condition. We evaluated TCLA on seven nonhuman primate datasets spanning multiple tasks. In long-term cross-session evaluation, TCLA achieved a mean

R^2

of

0.476\pm0.014

with a negative

R^2

failure rate of only 6.8%. Across 1,356 within-subject session pairs, TCLA achieved a mean

R^2

of

0.371\pm0.009

with a failure rate of 6.8%. Across 2,134 cross-subject session pairs, TCLA achieved a mean

R^2

of

0.218\pm0.004

with a failure rate of 12.9%, substantially better than those of the comparison methods. These results demonstrate that by preserving behaviorally relevant and task-dependent latent structure, TCLA improves the robustness of neural decoding across recording sessions and subjects. The source code is publicly available at https://github.com/FAMD-CASIA/TCLA.

Canyang Zhao, Bolin Peng, J. Patrick Mayo +2

Institute of Automation, Chinese Academy of Sciences, Beijing, China · Departments of Ophthalmology and Bioengineering, University of Pittsburgh, Pittsburgh, USA · School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China

Brain-Computer Interfaces Neural Decoding Invariant Representation Learning Latent Space Alignment

Sep 14, 2026cs.CV

Multimodal Floorplan Encoding: Learning Dense Modality-Invariant Representations

Floorplans arise in many forms, from vector CAD drawings to raster renderings and sensor-derived density maps. This heterogeneity makes it difficult to build learning systems that transfer across modalities and support geometry-centric tasks such as alignment and retrieval. We introduce the Multimodal Floorplan Encoder (MMFE), which maps diverse 2D indoor representations into a shared dense latent grid. MMFE combines a frozen DINOv3 backbone with a trainable Dense Prediction Transformer (DPT) head, and is trained with a per-cell Information Noise-Contrastive Estimation (InfoNCE) objective that aligns spatially corresponding regions across modalities while using all other cells as negatives. To improve robustness to geometric distortions, we incorporate controlled similarity transformations and enforce geometric consistency through feature-grid warping. On Structured3D, a held-out out-of-domain dataset, MMFE improves cross-modal dense matching, enables robust similarity alignment with RANSAC, and yields strong retrieval when paired with learned aggregation.

Xavier Anadón, Rémi Pautrat, Rui Wang

University of Zaragoza, Spain · Microsoft, Switzerland

Representation Learning Cross-Modal Representation Learning Cross-Modal Alignment Cross-Modal Feature Matching Multimodal Contrastive Learning Latent Space Alignment

Aug 31, 2026cs.RO

Temporal Forcing: 4D Representation Alignment for Vision-Language-Action Models

Long-horizon robotic manipulation requires vision-language-action (VLA) models to track scene states and their evolution beyond the current observation. However, simply conditioning policies on observation history does not guarantee that the history is effectively utilized: action supervision constrains what the policy should do, but only indirectly constrains what its history representations should retain. To resolve this, we present Temporal Forcing, a 4D representation alignment framework that explicitly supervises latent temporal states and their transitions. Specifically, we first introduce a history pathway that compresses past observations into compact latent tokens. We then align these tokens and current-frame features with geometric targets from a pretrained 4D foundation model, providing direct supervision at both the state and transition levels. The 4D foundation model and alignment heads are used only for training-time supervision. Temporal Forcing improves average success from 96.6% to 98.8% on LIBERO, with the largest gain on LIBERO-Long (93.8% to 97.2%), and from 53.5% to 62.8% across twelve RoboTwin 2.0 tasks. Furthermore, Temporal Forcing increases full-task success from 20.0% to 43.3% on a physical multi-stage hidden-placement task. Controlled experiments show that 4D representation alignment is crucial for making observation history beneficial to the model. Code will be publicly available.

Xingyu Ding, Yuzhong Zhao, Chunhai Zhao +3

Nanjing University, Nanjing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China

Representation Learning Robotic Manipulation Vision-Language-Action Models Latent Space Alignment

Aug 6, 2026cs.LG

How Far Do Simple Transformations Translate Across Text Embedding Models?

We investigate whether simple transformations can translate representations across heterogeneous text embedding models. Understanding how independently trained models organize semantic information is an enabler for AI-to-AI latent communication without decoding into human-readable text. Focusing on lightweight translators such as linear mappings, we test the literature hypothesis of latent universality in a realistic text setting beyond simplified benchmarks. Across nine embedding models differing in architecture, pooling strategy, and training objective, we evaluate compatibility using CKA, downstream transfer, fidelity, and retrieval. Simple translators recover meaningful shared structure and support transfer for some compatible pairs, but fail sharply for others. Compatibility depends jointly on architecture, training objective, pooling, and data distribution. Overall, the results show that heterogeneous embedding spaces are not universally related by simple mappings as often suggested in some literature.

Sid Ali Hamideche, Louis-Adrien Dufrène, Quentin Lampin +1

Orange Research · Orange

Representation Learning Text Embedding Evaluation Text Embedding Models Latent Space Alignment

Jun 30, 2026cs.CV

Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers

Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: Teacher and Student must inhabit the same latent space. This Shared-Space constraint prevents knowledge transfer from modern high-capacity Teachers (e.g., SD 3.5 and Flux) into compact, deployment-friendly Students such as SD 1.5, whose latent resolution and VAE parameterization differ from the Teacher. We formalize this overlooked regime as Cross-Space Distillation, where Teacher and Student differ in both latent resolution and VAE space. To enable distillation under this mismatch, we introduce the Bridge, a lightweight latent interface that maps Student latents into the Teacher space without modifying the Student backbone. Bridge combines a frozen Student VAE decoder as a spatial prior with a compact learnable projector, and is trained with latent reconstruction and attention fidelity objectives for stable Teacher-space alignment. Across diverse modern Teachers, Bridge enables substantial gains for compact one-step Students; for example, it improves SD 1.5 from 5.4 to 9.4 HPSv3 while preserving one-step inference, low latency, and broad ecosystem compatibility. These results show that heterogeneous large Teachers can be distilled into efficient, deployable backbones through a lightweight latent-space interface.

Anh Nguyen, Ngan Nguyen, Duc Vu +11

Qualcomm AI Research† · University of Wisconsin–Madison · Johns Hopkins University +1

Diffusion Model Distillation Cross-Architecture Knowledge Distillation Diffusion Model Inference Acceleration Latent Space Alignment

Jun 23, 2026cs.SD

Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement

Generative models, particularly diffusion and score-based approaches, have recently achieved strong performance in speech enhancement, but their iterative sampling process limits real-time deployment. Flow Matching offers an efficient alternative by transporting noisy speech toward clean speech through an ordinary differential equation with few function evaluations. In this work, we propose a skip-free encoder-decoder backbone for flow-matching speech enhancement, guided by Latent Representation Alignment (LRA). Instead of relying on U-Net skip connections, which may transfer noise-correlated low-level features to the decoder, the proposed model aligns its bottleneck and decoder representations with clean latent features extracted from a frozen Descript Audio Codec encoder-decoder without quantization. This codec-aligned supervision promotes compact clean-speech representations while preserving efficient few-step inference. Experiments on WSJ0-CHiME3 and VoiceBank-DEMAND show improved PESQ and perceptual quality, especially on VoiceBank-DEMAND, using only five function evaluations.

Wangyi Pu, Michele Scarpiniti

Department of Information Engineering, Electronics and Telecommunications, Sapienza University of Rome, Italy

Flow Matching Speech Enhancement Flow-Based Generative Modeling Latent Space Alignment

Jun 21, 2026cs.LG

Subspace-Constrained Federated Learning with Low-Rank Adaptation

Federated low-rank adaptation methods are attractive for fine-tuning large models under communication and privacy constraints, but heterogeneous client data can induce geometric misalignment between local low-rank updates. We study whether this subspace misalignment leads to destructive aggregation and slower convergence in LoRA-based federated learning. We propose a subspace-regularized federated LoRA objective that encourages local client updates to remain close to a shared global reference subspace. We present a complete empirical evaluation on two pretrained models, RoBERTa-large and SmolLM-360M, over HellaSwag in a non-IID 10-client federated setting, across 3 random seeds (42, 43, 44), yielding 24 total experimental runs (4 methods x 3 seeds x 2 models). On RoBERTa-large, Subspace-Reg achieves the strongest mean best accuracy (0.454 +/- 0.023), mean final accuracy (0.429 +/- 0.011), and lowest final loss (1.363) across all three seeds, outperforming FedAvg, SVD redistribution, and FedSVD baselines by a large margin. On SmolLM-360M, FedAvg leads on accuracy, revealing that accuracy gains are model-dependent. Crucially, Subspace-Reg achieves near-perfect basis overlap, approximately 0.9999, on both models and across all seeds, versus 0.958 to 0.991 for all baselines, providing robust support for the geometric alignment hypothesis. The code is publicly available at https://github.com/sadia-sigma-lab/Subspace-Constrained-Federated-learning-with-Lora.

Neranjan Senarath, Rohit Muralitharan, Sadia Asif

Department of ECSE Rensselaer Polytechnic Institute Troy, NY 12180, USA · Department of Computer Science Rensselaer Polytechnic Institute Troy, NY 12180, USA

Federated Learning Aggregation Non-IID Federated Learning Low-Rank Adaptation Federated Fine-Tuning Representation Alignment Latent Space Alignment+1

Jun 17, 2026cs.LG

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most existing model merging approaches follow the Task Arithmetic paradigm, which decomposes fine-tuned weights into pre-trained parameters and task vectors, and performs merging exclusively in the task-vector space. The effectiveness of this paradigm implicitly relies on the assumption that task-specific knowledge is encoded solely within task vectors. We argue that this assumption generally does not hold due to the intrinsic task preferences of pre-trained models. Specifically, we identify \textbf{Load-Bearing Wall (LBW) dimensions}, namely some task-critical knowledge that remains embedded in the pre-trained weights rather than being fully transferred into task vectors. We characterize LBW dimensions from both scalar-weight and subspace perspectives, thereby covering the major paradigms of existing model merging methods. Our analysis reveals that, by ignoring LBW dimensions, task-vector-based approaches fail to fully resolve task conflicts and may inadvertently damage task-specific knowledge encoded in the pre-trained model, leading to degradation. To address this issue, we propose PACT, which preserves the anchored task-specific cores (i.e., LBW dimensions) within task vectors by aligning their orthogonal complements with the subspace of the pre-trained weights. These aligned subspace components are then removed from the task vectors before applying existing model merging algorithms. Furthermore, we develop an efficient variant based on randomized SVD to improve scalability. PACT can be seamlessly integrated with existing methods. Extensive experiments across multiple benchmarks demonstrate that PACT consistently enhances mainstream model merging approaches and establishes new state-of-the-art performance.

Ningyuan Shi, Zhipeng Zhou, Hao Wang +2

Shanghai Jiao Tong University · Nanyang Technological University · The Hong Kong University of Science and Technology (Guangzhou)

Multi-Task Learning Task Vector Merging Model Merging Latent Space Alignment

Jun 15, 2026cs.LG

Learning aligned EEG representations with subject-specific encoders

Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts. We study whether task supervision and architecture alone can learn subject-aligned representations. We replace a shared EEG encoder with subject-specific encoders followed by a common classifier, and compare this hybrid model with standard EEGNet, AttentionBaseNet, and CTNet baselines with Euclidean Alignment (EA) on three motor-imagery datasets and one motor-execution dataset. EA improves shared encoders by recentering subject covariances, whereas the hybrid encoder reduces reliance on EA: removing EA has little effect on validation-loss dynamics or latent-space organization, and both hybrid variants consistently outperform non-aligned shared baselines. Subject-specific heads increase class distinctiveness and place each subject close to its own latent manifold while improving within-subject class separation. However, on cross-subject classification, subject-specific heads hinder direct parameter transfer to unseen subjects, motivating quantitative head selection and a brief calibration session. Although decoding gains depend on the dataset and backbone, our main findings concern that the sole use of architecture pressure promotes representation learning and alignment in a direction complementary to domain adaptation methods such as Euclidean Alignment. A per-subject low-rank adapter of only 2Cr parameters recover the full encoder's accuracy across five backbones and ranks

r=1

to 16, so the per-subject module can be compressed by two to three orders of magnitude.

Bruna J. Lopes, Gabriel Schwartz, Sylvain Chevallier +2

University of São Paulo, São Paulo, Brazil · Université Paris-Saclay, Inria TAU team, LISN-CNRS, France · Institut de neuromodulation, GHU Paris, psychiatrie et neurosciences, centre hospitalier Sainte-Anne, pôle hospitalo-universitaire 15, Université Paris Cité, Paris, France +3

Cross-Subject EEG Decoding MI Classification EEG Decoding Representation Alignment Latent Space Alignment

Jun 14, 2026q-bio.NC

Task-guided cross-subject latent alignment: a multi-encoder-decoder VAE

Aligning neural activity across subjects offers the promise of discovering shared computational principles and generalizable decoders. However, traditional alignment methods require shared stimuli across subjects, a constraint that limits applicability to naturalistic paradigms with limited or non-overlapping data. We introduce a Multi-Encoder-Decoder Variational Autoencoder (MED-VAE) that achieves cross-subject alignment without shared stimuli by anchoring representations to a common scaffold provided by a pretrained ANN. Using the Natural Scenes Dataset, we show that MED-VAE creates common latent spaces with superior semantic organisation, achieving higher cross-subject alignment than common methods while maintaining robust generalisation to held-out stimuli where traditional methods degrade. Reconstructing from these common spaces back to each subject's original neural space, MED-VAE preserves equal stimulus-driven signal in its cross-subject latent space. Finally, we show that this superior alignment directly enables cross-subject neural prediction, as demonstrated via cross-subject image decoding. In summary, we introduce a framework to identify generalisable common subspaces for cross-subject predictions and downstream tasks, demonstrated here for visual cortex responses to static images.

Angeliki Papathanasiou, Jascha Achterberg, Thomas E. Nichols +1

Centre for Neural Circuits and Behaviour, Department of Physiology Anatomy and Genetics, University of Oxford · Big Data Institute, Nuﬃeld Department of Medicine, University of Oxford

Variational Autoencoders Neural Decoding Latent Space Alignment

Jun 4, 2026cs.CV

Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

Latent visual reasoning (LVR) inserts supervised latent tokens between perception and answer generation in vision-language models (VLMs). The field uses alignment between these latents and their visual targets, i.e., cosine similarity or mean squared error (MSE), as both the training loss and the quality metric, assuming that better alignment yields a better answer. We test this with a designed matrix of five LVR variants and find the assumption inverted: cosine alignment is negatively correlated with accuracy across all five (r=-0.94). To explain this, we introduce PRISM, a pair of inference-time diagnostics: a linear probe that asks where the answer is decodable, and a corruption test that asks whether the latent is load-bearing. The supervised latents are largely bypassed. Corrupting them shifts accuracy by at most four points. The answer is decodable downstream of the latent but not at it, and the size of this decodability gap predicts how much each variant relies on its latent under perturbation. Consistent with an Information Bottleneck reading of the loss, the auxiliary objective reshapes the language model via shared parameters rather than via the latent variable it nominally optimizes.

XiuYu Zhang, Junfeng Fang, Zhenkai Liang

National University of Singapore

VLM Evaluation Latent Visual Reasoning VLM Reasoning Representation Probing Latent Space Alignment

May 26, 2026stat.ML

Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks

Neural networks are known to develop latent representations that are

aligned

, namely structurally similar across networks trained with different architectures, training protocols, or training datasets. We study this phenomenon in a controlled setting, where we train an ensemble of networks on regression and classification tasks using training sets perturbed by independent realizations of a noise process. We show that the signal-to-noise ratio (SNR) and the training sample size influence the alignment in qualitatively similar ways in networks trained on real-world datasets and in an extremely simple

linear

network with a single hidden layer, for which the alignment can be estimated analytically. Across linear and nonlinear networks, regression and classification tasks, and both synthetic and real-world data, we consistently observe that alignment varies monotonically with SNR but non-monotonically with training sample size. In particular, the alignment is minimized near the interpolation threshold, and a stronger alignment does not necessarily correspond to better generalization error. These findings reveal a non-trivial dependence of alignment on data quality and quantity, decoupled from generalization performance.

Ali Hussaini Umar, Alessandro Laio

SISSA · SISSA & ICTP

Neural Representation Geometry Latent Space Alignment

May 23, 2026cs.LG

Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m

Independently trained transformers compute the same function in residual-stream bases that differ by a uniform random rotation on

\mathrm{SO}(d_{\mathrm{model}})

. We call this phenomenon polymorphism: same function, mutually unintelligible interior coordinates. One matrix multiplication per model pair removes it: an orthogonal Procrustes fit on a single batch of activations transfers sparse-autoencoder feature dictionaries and steering vectors between independently trained models, with no retraining. The phenomenon is invisible to the standard SAE universality metric. Decoder-column cosine similarity matches across seeds at 98%, the SAE-universality headline number, while an SAE trained on one seed reconstructs another seed's activations at negative explained variance, worse than predicting the constant mean. The decoder columns align; the encoder reads from a rotated frame. A single Procrustes rotation

R

restores reconstruction to within 0.025 EV of the within-seed ceiling at every internal site.

R

is Haar-distributed:

\|R - I\|_F

matches the random-orthogonal prediction

\sqrt{2 d_{\mathrm{model}}}

to 0.1% at

d_{\mathrm{model}} = 512

, and a Kolmogorov-Smirnov test of

R

's eigenvalue spectrum against Haar

\mathrm{SO}(d_{\mathrm{model}})

returns

p \approx 1.000

pooled and per-pair. Diff-of-means steering vectors transfer in three regimes by alignment with

R

's invariant subspace: clean when pinned by shared output weights, partial when overlapping the rotated subspace, inverted otherwise. With no shared I/O (Pythia), all three collapse to universally inverted. The same rotation account holds across training checkpoints within a single run. Validated on a 104k-parameter Dyck-3 transformer and nine independently-trained Pythia-70m seeds on The Pile, via a pre-registered four-bar operational framework. Frontier-scale (10B+) replication remains open.

Jordan F. McCann

Independent Researcher

Transformer Interpretability Transformer Sparse Autoencoders Mechanistic Interpretability Representation Alignment Latent Space Alignment

May 18, 2026cs.CV

LatentUMM: Dual Latent Alignment for Unified Multimodal Models

Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue does not stem from a lack of shared representations, but from the absence of explicit alignment between the transformations that map into and out of the latent space. As a result, generation and re-encoding can follow inconsistent trajectories, leading to semantic drift under modality transitions. In this work, we propose LatentUMM, a framework that constructs an enhanced shared latent space to explicitly align these transformations and improve cross-modal consistency. LatentUMM consists of two stages. First, dual latent alignment enforces consistency at both the modality and capacity levels: cross-modal alignment uses a stronger embedding model to impose structured cross-modal semantics, while dual capacity alignment enforces bidirectional consistency under generation and re-encoding. Second, latent dynamics stabilization improves robustness via stochastic latent rollouts and preference optimization, favoring trajectories that better preserve semantic consistency. Experiments show that LatentUMM consistently improves multimodal consistency across diverse architectures. Code is available at: https://github.com/AIFrontierLab/TorchUMM/tree/main/src/umm/post_training/LatentUMM.

Yinyi Luo, Wenwen Wang, Hayes Bai +2

Carnegie Mellon University · William & Mary

Cross-Modal Learning Unified Multimodal Models Cross-Modal Alignment Multimodal Foundation Models Latent Space Alignment Multimodal Understanding

May 10, 2026cs.LG

SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations

Latent representations learned by neural networks often exhibit semantic structure, where concept similarity is reflected by geometric proximity in embedding space. However, comparing such spaces across models remains difficult: changes in architecture, pretraining data, objective, or random seed can yield embeddings with similar content but incompatible geometry. This latent space alignment problem is central to interpretability, transfer and multimodal learning, federated systems, and semantic communication; however, progress remains limited by the lack of large-scale, model-diverse, and metadata-rich benchmarks. To address this gap, we introduce SEMASIA, a large-scale collection of latent representations extracted from approximately 1,700 pretrained vision models across eight standard image-classification benchmarks. SEMASIA pairs embeddings with structured metadata describing architectures, training regimes, pretraining sources, and model scale. We demonstrate three applications of the resource. First, we analyze the conceptual organization of individual latent spaces, showing consistent prototype-like clustering and hierarchical semantic neighborhoods across models and datasets. Second, we benchmark supervised alignment mappings between latent spaces using reconstruction error and downstream task performance. Third, we perform a large-scale regression analysis of how pretraining-data complexity, specialization, transfer learning, augmentation, and model scale relate to geometric and probing properties of embeddings. By coupling representational scale with standardized metadata, SEMASIA provides a reproducible foundation for studying latent geometry, evaluating alignment methods, and developing next-generation heterogeneous and interoperable AI systems.

Mario Edoardo Pandolfo, Enrico Grimaldi, Lorenzo Marinucci +4

Dept. Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy. · National Inter-University Consortium for Telecommunications (CNIT), Parma, Italy. · Dept. of Statistical Sciences, Sapienza University of Rome, Rome, Italy. +1

Neural Representation Geometry Visual Representation Learning Latent Space Alignment

Apr 15, 2026q-bio.NC

Seeing the imagined: latent functional alignment in visual imagery decoding from fMRI data

Recent progress in visual brain decoding from fMRI has been enabled by large-scale datasets such as the Natural Scenes Dataset (NSD) and powerful diffusion-based generative models. While current pipelines are primarily optimized for perception, their performance under mental-imagery remains less well understood. In this work, we study how a state-of-the-art (SOTA) perception decoder (DynaDiff) can be adapted to reconstruct imagined content from the NSD-Imagery benchmark. We propose a latent functional alignment (LFA) approach that maps imagery-evoked activity to the pretrained model's semantic content-enriched conditioning space, by adding a simple alignment module, while keeping the original remaining components frozen. To mitigate the limited amount of matched imagery-perception supervision, we further introduce a neural retrieval-based augmentation strategy that selects semantically related NSD perception trials from the same participants. Across four subjects, LFA consistently improves high-level semantic reconstruction metrics relative to the frozen pretrained baseline and a voxel-space ridge alignment baseline, and enables above-chance decoding from multiple cortical regions. These results suggest that semantic structure learned from perception can be leveraged to stabilize and improve visual imagery decoding under out-of-distribution conditions.

Fabrizio Spera, Tommaso Boccato, Michal Olak +2

Department of Biomedicine and Prevention, University of Rome Tor Vergata, Rome, Italy · Tether Evo · A.A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, USA

Neural Decoding Visual Neuroscience Neuroimaging Latent Space Alignment

Feb 26, 2026cs.LG

SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport

The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the world. Recent work exploits this convergence by aligning frozen pretrained vision and language models with lightweight alignment layers, but typically relies on contrastive losses and millions of paired samples. In this work, we ask whether meaningful alignment can be achieved with substantially less supervision. We introduce a semi-supervised setting in which pretrained unimodal encoders are aligned using a small number of image-text pairs together with large amounts of unpaired data. To address this challenge, we propose SOTAlign, a two-stage framework that first recovers a coarse shared geometry from limited paired data using a linear teacher, and then refines the alignment on unpaired samples via an optimal-transport-based divergence that transfers relational structure without overconstraining the target space. SOTAlign effectively leverages unpaired images and text, learning robust joint embeddings across datasets and encoder pairs, and significantly outperforming supervised and semi-supervised baselines. Code is available at https://github.com/ExplainableML/SOTAlign.

Simon Roschmann, Paul Krzakala, Sonia Mazelet +2

Helmholtz Munich · Technical University of Munich · Munich Center for Machine Learning +3

Cross-Modal Learning Multimodal Embedding Vision-Language Alignment Semi-Supervised Learning Latent Space Alignment Multimodal Understanding

Feb 5, 2026cs.LG

Multi-Way Representation Alignment

The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces. However, current strategies for mapping these representations are inherently pairwise, scaling quadratically with the number of models and failing to yield a consistent global reference. In this paper, we study the alignment of

M \ge 3

models. We first adapt Generalized Procrustes Analysis (GPA) to construct a shared orthogonal universe that preserves the internal geometry essential for tasks like model stitching. We then show that strict isometric alignment is suboptimal for retrieval, where agreement-maximizing methods like Canonical Correlation Analysis (CCA) typically prevail. To bridge this gap, we finally propose Geometry-Corrected Procrustes Alignment (GCPA), which establishes a robust GPA-based universe followed by a post-hoc correction for directional mismatch. Extensive experiments demonstrate that GCPA consistently improves any-to-any retrieval while retaining a practical shared reference space.

Akshit Achara, Tatiana Gaintseva, Mateo Mahaut +5

King’s College London, London, United Kingdom · Queen Mary University of London, London, United Kingdom · Universitat Pompeu Fabra, Barcelona, Spain +5

Neural Representation Geometry Latent Space Alignment