Papers Representation Learning
“Representation Learning” 태그가 달린 논문 12,899편 · 필터 해제
Learning Discriminative Geometry for Drifting Models
Recently proposed Drifting Models shift iterative distribution refinement from inference to training, enabling effective one-step generation. However, their performance on complex image datasets depends strongly on the r…
Representation LearningDensity EstimationDo Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale
A trainable input embedding table assigns each vocabulary item an independently adjustable vector. We investigate whether this token-specific parameterization is required for substantial language-modeling capability, or …
Representation LearningHigher-Order Molecular Grammars for Generative and Foundation Models in Chemistry
Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph formalisms struggle to explicitly encode higher-order topology, such as ring systems and recurring moti…
Representation LearningSurface-volume self-supervised representation learning of brain MRI for genetic discovery
Existing genome-wide association studies (GWAS) of brain imaging provide predefined or deep-learning-derived imaging phenotypes, yet these phenotypes come from either volumetric scans or cortical surface meshes, so each …
Self-Supervised LearningRepresentation LearningLatent-Foresight: End-to-End Learning Predictable Representations for Latent World Models
Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of Vision Foundation Models (VFMs) yields semantically rich representat…
Dimensionality ReductionRepresentation LearningScene UnderstandingPragmatic DML with AI-Learned Representations
Text, images, and other rich covariates are increasingly compressed into AI-learned representations and then used as controls in causal analysis. We study when this approach is valid and develop a practical framework for…
Representation LearningCausal InferenceA Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
Retrieval-Augmented Generation (RAG) systems for multi-hop Question Answering (QA) must balance retrieval quality with computational cost. This cost is incurred during indexing time, through the use of expensive Knowledg…
Multi-hop Question AnsweringRepresentation LearningKnowledge GraphsMeasuring the Stability Assumption Behind Action Chunking
Action chunking improves the performance of policies learned by behavioural cloning, and several mechanisms have been proposed to explain why, including temporal consistency, horizon reduction, representation learning, a…
Representation LearningNeither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)
Existing work on Semantic IDs (SIDs) for generative recommendation treats SID construction as a representation learning problem: encode items into a quantised latent space and read off codes. We argue this view is incide…
Representation LearningLangevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback
Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimensional structure, evolving on slow timescales. However, target traje…
Representation LearningTransfer LearningPDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs
Physical trajectories contain more than snapshots of a system: they also reveal how its states evolve under governing conditions. However, representation learning for parametric partial differential equations (PDEs) has …
Representation LearningYuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
Symbolic models make melody, harmony, rhythm, and form explicit but typically stop before a finished recording; audio models produce complete songs while leaving composition implicit. We introduce YuE2, which unifies sym…
Representation LearningMusic GenerationTactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors
Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trained image encoders are standard in robot learning pipelines, tactile…
Self-Supervised LearningRepresentation LearningJEPA-Anything: Learning Predictive Models across Different Worlds
World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling across…
Representation LearningActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Action tokenizers play a central role in autoregressive vision-language-action (VLA) models, determining both the targets for policy training and the executable commands recovered from predicted tokens. Their fidelity is…
Representation LearningFreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection
Unauthorized hardware replacement can preserve a wireless device's logical identity while altering its physical implementation, posing a challenge to hardware integrity verification. Spatio-frequency polarization fingerp…
Representation LearningAnomaly DetectionType-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning
Software clones are fragments of code that are similar or functionally equivalent to each other. They pose significant challenges for maintenance, refactoring, and bug detection. Detecting Type-IV clones, which are seman…
Representation LearningContrastive LearningMyoFlow: Anchor-Tied Rectified Flow for HD-sEMG Gesture Recognition Across Sessions and Subjects
High-density surface electromyography (HD-sEMG) gesture recognition supports prosthetic control, assistive robotics, and rehabilitation, but electrode re-donning and physiological variability cause distribution shifts th…
Representation LearningGesture RecognitionHub-Spectral Activation of Latent Multimodal Knowledge
Multimodal representation learning seeks shared representations for cross-modal retrieval and knowledge transfer. Hub-based binding reduces pairwise supervision costs, but separate hub connections cannot guarantee reliab…
Representation LearningCross-Modal RetrievalHyCoSeq: Contextual Hyperbolic Representation Learning for Genomic Sequences
Hyperbolic geometry provides a natural inductive bias for genomic representation learning, but existing hyperbolic genomic models primarily use Lorentz convolutions to learn local sequence representations, while their re…
Representation Learning