arxivJul 30bullish

From Cellular Responses to Pharmacological Domains: Multimodal Zero-Shot Drug Representation Learning

arXiv:2607.25322v1 Announce Type: new Abstract: Multimodal drug discovery enables drug representation learning beyond chemical structure by incorporating cellular responses such as gene expression and cell morphology. However, direct fusion and instance-level contrastive alignment may mix mechanism-

#multimodal #drug-discovery #representation-learning Read on arxiv →

arxivJul 10

From Performance to Viability: A Bootstrap Framework for Latent-Space Representation Learning in Adaptive Biological Systems

arXiv:2606.01374v2 Announce Type: replace Abstract: Observable performance is commonly used to characterize biological systems. In adaptive systems, however, similar performances may arise from distinct organizations, and configurations that appear comparable at a given time may follow different lon

#machine-learning #representation-learning #biological-systems Read on arxiv →

arxivJul 2bullish

Identifying Latent Concepts and Structures for Generalized Category Discovery

arXiv:2607.00620v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings. However, current approaches primarily focus on designing clustering objectives, often overlooking a critical bottle

CO1 model #computer-vision #representation-learning #open-world-recognition Read on arxiv →

arxivJun 10bullish

Tractogram foundation model

arXiv:2606.09893v1 Announce Type: cross Abstract: Diffusion MRI (dMRI) tractography is the only noninvasive approach for mapping white-matter pathways in the living human brain. It represents each brain as a tractogram: a large, unordered set of three-dimensional streamlines that includes informatio

TR1 model #medical-imaging #representation-learning #diffusion-mri Read on arxiv →

arxivJun 5bullish

Toward Scalable and Valid Conditional Independence Testing with Spectral Representations

arXiv:2512.19510v2 Announce Type: replace Abstract: Conditional independence (CI) is central to causal inference, feature selection, and graphical modeling, yet it is untestable in many settings without additional assumptions. Existing CI tests often rely on restrictive structural conditions, limiti

#machine-learning #representation-learning #causal-inference Read on arxiv →

arxivMay 13bullish

MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning

arXiv:2602.07940v3 Announce Type: replace Abstract: To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collectively known as general continual learning (GCL), encapsulates practi

ME1 model #continual-learning #pretrained-models #meta-learning Read on arxiv →

arxivMay 11bullish

Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment

arXiv:2605.06885v1 Announce Type: cross Abstract: Diffusion language models (DLMs) have recently demonstrated capabilities that complement standard autoregressive (AR) models, particularly in non-sequential generation and bidirectional editing. Although recent work has shown that pretrained autoregr

DIAU2 models #diffusion #language-models #representation-learning Read on arxiv →

arxivMay 1

Robust Learning on Heterogeneous Graphs with Heterophily: A Graph Structure Learning Approach

arXiv:2604.27387v1 Announce Type: new Abstract: Heterogeneous graphs with heterophily have emerged as a powerful abstraction for modeling complex real-world systems, where nodes of different types and labels interact in diverse and often non-homophilous ways. Despite recent advances, robust represen

#heterogeneous-graphs #representation-learning #graph-structure Read on arxiv →

arxivApr 11

Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yor\`ub\'a

arXiv:2604.07467v1 Announce Type: new Abstract: Discrete speech units (DSUs) are derived by quantising representations from models trained using self-supervised learning (SSL). They are a popular representation for a wide variety of spoken language tasks, including those where prosody matters. DSUs

#speech-recognition #representation-learning #quantisation Read on arxiv →