Latent Space

Follow this topic Ask about this topic

Recent momentum

-35%

11 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

6 new papers

A weekly snapshot of new work published in Latent Space.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Latent Space.

201 papers

Latest in Latent Space

Browse all topics →

ClinicalEncoder26AM: A Multlilingual Diagnosable ColBERT Model; Evidences from the MultiClinNER Shared Task
May 27, 2026François RemyMedical Ontology Multimodal Clinical Data
Latent Diffusion for Missing Data
May 27, 2026Alberte Heering Estad, Ignacio Peis, Jes FrellsenLatent Diffusion Model Latent Space
ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
May 27, 2026Yu Zhang, Yidi Shao, Wenqi Ouyang +5Deformable Objects Latent Space
From Latent Space to Training Data: Explainable Specialization in Minimal MLPs
May 25, 2026Enrique Alba, Ezequiel Lopez-RubioMultilayer Perceptrons Latent Space
HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control
May 25, 2026Simon Schaefer, Joshua Näf, Stefan LeuteneggerHuman Motion Generation Motion Estimation
Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces
May 25, 2026Konstantinos Emmanouilidis, Tianjiao Ding, Nghia Nguyen +2Adversarial Transferability Gaussian Mixture Models
UWM-JEPA: Predictive World Models That Imagine in Belief Space
May 25, 2026Santosh Kumar Radha, Oktay GoktasLatent World Models Joint-Embedding Predictive Architectures
Learning from Semantic Dictionaries: Discriminative Codebook Contrastive Learning for Unified Visual Representation and Generation
May 24, 2026Imanol G. Estepa, Jesús M Rodríguez-de-Vera, Bhalaji Nagarajan +1Contrastive Loss Contrastive Learning
Learning High-Frequency Continuous Action Chunks in Latent Space
May 24, 2026Kunyun Wang, Yuhang Zheng, Yupeng Zheng +2Action Chunks Generalizable Robotic Manipulations
Lngram: N-gram Conditional Memory in Latent Space
May 24, 2026Yunao Zheng, Guoyang Xia, Xiaojie Wang +1N$-Grams Features Graph Language Models
COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing
May 22, 2026Florian Barthel, Shalini De Mello, Koki Nagano +33D Editing Animatable 3D Human Avatars
Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
May 22, 2026Bingtian Qiao, Yue Shi, Yingjie Zhou +3Generative Super-Resolution Image Restoration
Posterior Collapse as Automatic Spectral Pruning
May 21, 2026Johannes HirnEntropy Collapse Collapse
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
May 21, 2026Yifan Dai, Zhenhua Wu, Bohan Zeng +18Audio-Visual Reasoning Omni-Modal
Divide et Calibra: Multiclass Local Calibration via Vector Quantization
May 20, 2026Cesare Barbera, Lorenzo Perini, Giovanni De Toni +2Multiclass Classification Multicalibration and Calibration
Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry
May 19, 2026Pablo Marcos-Manchón, Rishi Jha, Lluís FuentemillaImplicit Neural Representations Brain Magnetic Resonance Imaging
Latent Space Guided Scenario Sampling for Multimodal Segmentation Under Missing Modalities
May 19, 2026Irem Ulku, Ö. Özgür Tanrıöver, Erdem AkagündüzMissing Modalities Latent Space
Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
May 18, 2026Manal Benhamza, Marianne Clausel, Myriam TamiCausal Representation Learning Identifiability
PERL: Parameter Efficient Reasoning in CLIP Latent Space
May 18, 2026Simone Carnemolla, Salvatore Calcagno, Daniela Giordano +2Vision-Language Model Adaptation Frozen Contrastive Language-Image Pre-Training Visual Encoder
Bayesian Latent Space Models for Graphs Are Misspecified: Toward Robust Inference via Generalized Posteriors
May 18, 2026Aldric LabartheBayesian Exponential Random Graph Models
One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception
May 18, 2026Yang Li, Weize Li, Quan Yuan +7Collaborative Perception Perceptual Understanding
LatentUMM: Dual Latent Alignment for Unified Multimodal Models
May 18, 2026Yinyi Luo, Wenwen Wang, Hayes Bai +2Unified Multimodal Models Cross-Modal Learning
GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
May 15, 2026Roman Bresson, Konstantinos Divriotis, Johannes F. Lutzeyer +2Variational Autoencoder Latent Space
From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint
May 15, 2026Jacques Raynal, Pierre Slangen, Elsa Raynal +1Single-Subject Gait Dataset Parkinson
Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction
May 14, 2026Santosh Kumar PaidiFuture Video Prediction Joint-Embedding Predictive Architectures
SpectraFlow: Unifying Structural Pretraining and Frequency Adaptation for Medical Image Segmentation
May 14, 2026Zhiquan Chen, Haitao Wang, Guowei Zou +1Medical Image Segmentation Model Pretraining
Rethinking the Good Enough Embedding for Easy Few-Shot Learning
May 13, 2026Michael Karnes, Alper YilmazFew-Shot Learning Visual Embeddings
Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling
May 13, 2026Gaurav Rudravaram, Lianrui Zuo, Karthik Ramadass +17Brain Connectome Modality Latent Space
On the Limits of Latent Reuse in Diffusion Models
May 13, 2026Yifeng Yu, Lu YuLatent Space Target Domain
Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering
May 13, 2026Konstantinos Soiledis, Maximos Kaliakatsos Papakostas, Dimos Makris +1Identity-Conditioned Latent Diffusion Models Waveforms
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
May 13, 2026Marte Eggen, Eirik Reiestad, Kristian Gjøsteen +1Backdoor Attacks Neural Network
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
May 12, 2026Shixing Yu, Promit Ghosal, Kyra GanToken-Level Uncertainty Large Language Model Output
Martingale-Consistent Self-Supervised Learning
May 12, 2026Moritz Gögl, Hanwen Xing, Christopher YauSelf-Supervised Conformal Test Martingales
diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories
May 11, 2026Florent Guépin, Cheick Tidiani Cisse, Denis Renaud +2Trajectory Prediction Discrete Diffusion Model
Latent Geometry Beyond Search: Amortizing Planning in World Models
May 9, 2026Hoang Nguyen, Xiaohao Xu, Xiaonan HuangLatent World Models Classical Planning
Uncertainty Quantification for Cardiac Shape Reconstruction with Deep Signed Distance Functions via MCMC methods
May 8, 2026Jan Verhülsdonk, Thomas Grandits, Francisco Sahli Costabal +3Cardiac Motion Continuous Distance Field
How to Train Your Latent Diffusion Language Model Jointly With the Latent Space
May 8, 2026Viacheslav Meshchaninov, Alexander Shabalin, Egor Chimbulatov +4Diffusion Language Models Latent Diffusion Model
ModelLens: Finding the Best for Your Task from Myriads of Models
May 8, 2026Rui Cai, Weijie Jacky Mo, Xiaofei Wen +5Benchmark Datasets Machine Learning
Invariant Features in Language Models: Geometric Characterization and Model Attribution
May 7, 2026Agnibh Dasgupta, Abdullah Tanvir, Xin ZhongSemantic Representations Invariance
Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
May 7, 2026Nilaksh, Saurav Jha, Artem Zholus +1Latent World Models Robot Policies
AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling
May 7, 2026Francisco Giral, Abhijeet Vishwasrao, Andrea Arroyo Ramo +8Aerodynamics Latent Bridge Matching
From Diffusion to Rectified Flow: Rethinking Text-Based Segmentation
May 6, 2026Zishen Qu, Xuesong Li, Haijian Gu +5Few-Shot Segmentation Text-To-Image Diffusion Models
Multimodal synthesis of MRI and tabular data with diffusion in a joint latent space via cross-attention
May 5, 2026Daniel Mensing, Jan Kapar, Jochen G. Hirsch +3Medical Image Generation Magnetic Resonance Imaging
Fine-Grained Graph Generation through Latent Mixture Scheduling
May 4, 2026Nidhi Vakil, Hadi AmiriData Generation Variational Autoencoder
FLoRA: Fusion-Latent for Optical Reconstruction and Flood Area Segmentation via Cross-Modal Multi-Task Distillation Network
May 4, 2026Jagrati Talreja, Tewodros Syum Gebre, Leila Hashemi-BeniFlood Detection Sen1Floods11
PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning
May 3, 2026Xinxing Yu, Ajian Liu, Sunyuan Qiang +53D Semantic Segmentation Self-Supervised
Sparse Representation Learning for Vessels
May 2, 2026Chinmay Prabhakar, Bastian Wittmann, Paul Büschl +3Retinal Vessel Segmentation Voxel
CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling
Apr 30, 2026Yingrui Wu, Youkang Kong, Mingyang Zhao +3Indoor Scene Generation Floor Plan Generation
A Gated Hybrid Contrastive Collaborative Filtering Recommendation
Apr 29, 2026Eduardo Ferreira da Silva, Mayki dos Santos Oliveira, Joel Machado Pires +6Collaborative Filtering Recommendation
Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrieval
Apr 27, 2026Esteban Rodríguez-Betancourt, Edgar Casasola-MurilloComposed Image Retrieval Self-Supervised Representations
SPLIT: Separating Physical-Contact via Latent Arithmetic in Image-Based Tactile Sensors
Apr 27, 2026Wadhah Zai El Amri, Nicolás Navarro-GuerreroTactile Sensors Deformable Objects
Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model
Apr 26, 2026Sinjini Mitra, Constantine Kyriakakis, Shenyuan Liang +2Generative Adversarial Network Domain Adaptation
GenAssets: Generating in-the-wild 3D Assets in Latent Space
Apr 24, 2026Ze Yang, Jingkang Wang, Haowei Zhang +33D Assets 3D Latent Diffusion Model
From Tokens to Concepts: Leveraging SAE for SPLADE
Apr 23, 2026Yuxuan Zong, Mathias Vast, Basile Van Cooten +2Semantic Representations Latent Space
StyleVAR: Controllable Image Style Transfer via Visual Autoregressive Modeling
Apr 22, 2026Liqi Jing, Dingming Zhang, Peinian Li +3Photorealistic Style Transfer Visual Autoregressive Models
JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning
Apr 22, 2026Ali Aghababaei-Harandi, Aude Sportisse, Massih-Reza AminiSemi-Supervised Learning Pseudo-Labeling
Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference
Apr 21, 2026François RemyClinical Notes Bert-Based Models
Geometric Decoupling: Diagnosing the Structural Instability of Latent
Apr 20, 2026Yuanbang Liang, Zhengwen Chen, Yu-Kun LaiLatent Space Instability
Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models
Apr 20, 2026Venkatesh Thirugnana Sambandham, Torsten SchönText-To-Image Image Generation
LASER: Low-Rank Activation SVD for Efficient Recursion
Apr 19, 2026Ege Çakar, Ketan Ali Raghu, Lia ZhengSparse Expert Activation Low-Rank Factorization

May 27, 2026 · cs.CLJ/K move · Enter open · S save

ClinicalEncoder26AM: A Multlilingual Diagnosable ColBERT Model; Evidences from the MultiClinNER Shared Task

François Remy

Parallia AI

ClinicalEncoder26AM is a multilingual Diagnosable ColBERT for clinical and biomedical texts, which aligns at multiple levels its token-level semantic with ClinicalMap25, a clinical latent space inspired by BioLORD-2023 and enriched with synthetic and annotated supervision. The post-training recipe builds upon BGE-M3, and combines synthetic clinical notes, patient--doctor conversations, and annotated resources such as MedMentions, while considering both named-entity-level and sentence-level representations in a multi-adapter distillation, along with a ColBERT-style retrieval objective. In this system demonstration paper, we evaluate the model in the MultiClinNER shared task by finetuning it as a BIO tagger for patient symptoms, disorders, and procedure spans, using a lightweight two-layer CNN head to improve local boundary detection. The resulting system remains simple, processes most documents in a single 8192-token window, and achieves state-of-the-art multilingual entity recall, while achieving Top 5 overall across all entity types and languages in Character-weighted F1 scores. Training curves further show that ClinicalEncoder26AM is markedly more data-efficient than the base M3 model, supporting the usefulness of its clinical post-training for downstream information extraction. The model can be downloaded on https://huggingface.co/Parallia/ClinicalEncoder26AM-Diagnosable-Colbert-L2-for-multilingual-medical-texts

Medical Ontology Multimodal Clinical Data Bert-Based Models Multilingual Language Models Multimodal Embeddings Latent Space

Open paper Ask about it PDF