Representation Space

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% 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 field, kept on the site without email delivery.

Period ending 2026-09-14

4 new papers

A weekly snapshot of new work published in Representation Space.

Period ending 2026-09-07

8 new papers

A weekly snapshot of new work published in Representation Space.

Inside this field

Focused directions

Focused topic

Representation Space

Within Representation Space

77 papersExplore

Focused topic

Representational Capacity

Within Representation Space

63 papersExplore

Focused topic

Representational Drift

Within Representation Space

47 papersExplore

Focused topic

Representation Quality

Within Representation Space

47 papersExplore

229 papers

Latest in Representation Space

Open your feed →

Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
May 29, 2026Riju Marwah, Ritvik Garimella, Vishal Pallagani +3Autoregressive Language Models Large Language Models Fail
Reward Learning from Best-of- $N$ Preference Data: Targets, Tradeoffs, and Design PrinciplesReward Learning from Best-of-N Preference Data: Targets, Tradeoffs, and Design Principles
May 28, 2026Rattana Pukdee, Maria-Florina Balcan, Pradeep RavikumarBest-Of-N Preference Learning
Improving Relative Representations with Learned Anchors and Whitened Inner Products
May 28, 2026Oscar Thorsted Svendsen, Nikolaj Holst Jakobsen, Fabian Mager +1Independent Anchor Network Representation Learning
SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations
May 28, 2026Qinpei Luo, Ruichun Ma, Xinyu Zhang +1Printed Circuit Board Computer-Aided Design
VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing
May 28, 2026Haoyuan Shi, Xiancong Ren, Yingji Zhang +9Diffusion-Based Vision-Language-Actions Vision-Language-Action
Striding Across Reynolds Numbers: Representation Geometry in Neural PDE Generalisation
May 28, 2026Jianing ShiShallow Water Equations Neural Partial Differential Equation Solvers
AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
May 27, 2026Zhen-Hao Xie, Yu-Cheng Shi, Da-Wei ZhouClip-Based Class-Incremental Learning In-Context Learning
The Attentional White Bear Effect in Transformer Language Models
May 27, 2026Rebecca Ramnauth, Brian ScassellatiProtein Language Model Representational Drift
Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models
May 27, 2026Prasanth K KSparse Autoencoders Model Activations
REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysis
May 27, 2026Ruohan Lei, Jianxin Gao, Wanli Peng +1Image Steganalysis Representation Quality
On the Structural (Dis)Agreement of Landscape Representations in Black-Box Optimization
May 27, 2026Sara Gjorgjieva, Eva Tuba, Barbara Koroušić Seljak +2Black-Box Optimization Optimization Landscape
Towards Controllable Image Generation through Representation-Conditioned Diffusion Models
May 26, 2026Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel EilertsenPocket-Conditioned Diffusion Unconditional Image Generation
Real Images, Worse Judgments: Evaluating Vision-Language Models on Concreteness and Imagery
May 26, 2026Yifan Jiang, Ruoxi Ning, Sheng Yao +1Representational Drift Relevance
Similarity-based representation factorization for revealing interpretable dimensions in representational data
May 26, 2026Florian P. Mahner, Ka Chun Lam, Francisco Pereira +1Representational Capacity Semantic Similarity Metrics
MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting
May 26, 2026Joonhyung BaeArt Korean
Implicit Null-space Manifold Generation for Redundant Robotic Systems
May 25, 2026Taiki Ishigaki, Teresa Vidal-Calleja, Ko Ayusawa +1Statistical Manifold Robots
RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation
May 25, 2026Wenhui ChuRobot Perception Recent Vision Foundation Models
Interpretation, Learning, and Empathy as One Constraint: A Residual-Adequacy Architecture with Accountable Abstention
May 24, 2026Chainarong AmornbunchornvejAbstention Abductive Reasoning
Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
May 24, 2026Yang Xiao, Siyi Wang, Eun-Jung Holden +1Acoustic Representation Continual Learning
Omissive Bias in Religious Representation: Benchmarking LLM Answers to Everyday Ethical Decision-making
May 23, 2026David Wingate, Sheryl Carty, Joshua Coates +13Large Language Model Bias Ethics
Characterizing the Representational Capacity of Neural Processes
May 22, 2026Robin YoungRepresentational Capacity Capacity
LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability
May 22, 2026Sadjad Alikhani, Akshay Malhotra, Shahab Hamidi-Rad +1Transfer Learning Wireless Networks
Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning
May 22, 2026Muhammad Usama, Dong Eui ChangRepresentational Drift Optimization Convergence Analysis
Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
May 22, 2026Guoming Li, Shangyu Zhang, Junwei Pan +7Recommender Systems Recommendation
Feature Lottery? A Bifurcation Theory of Concept Emergence
May 22, 2026Fuming YangFeature Learning Bifurcation
SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation
May 21, 2026Javad Parsa, Enis Simsar, Amir Joudaki +2Text-To-Image Diffusion Models Low-Rank Adaptation Experts
RiT: Vanilla Diffusion Transformers Suffice in Representation Space
May 21, 2026Le Zhang, Ning Mang, Aishwarya AgrawalFlow-Matching Loss Diffusion Transformers
Learning Emergent Modular Representations in Multi-modality Medical Vision Foundation Models
May 21, 2026Yuting He, Chenyu You, Shuo LiSelf-Supervised Learning Experts
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
May 20, 2026Lucheng Fu, Ye Yu, Yiyang Wang +4Overfitting Representational Drift
A New Framework to Analyse the Distributional Robustness of Deep Neural Networks
May 20, 2026Divij Khaitan, Subhashis BanerjeeDeep Neural Network Distribution Shifts
Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
May 20, 2026Gene Tangtartharakul, Katherine R. StorrsExperts Expert Judgment
Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity
May 20, 2026Weiqi Wang, Zhiyi Tian, Chenhan Zhang +2Machine Unlearning Representation Quality
Axiomatizing Neural Networks via Pursuit of Subspaces
May 19, 2026Mehmet Yamac, Mert Duman, Ugur Akpinar +4Artificial Neural Networks Representation Space
Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation ModelsCapability \neq Interpretability: Human Interpretability of Vision Foundation Models
May 19, 2026Julien Colin, Lore Goetschalckx, Nuria Oliver +1Model Interpretability Methods Vision Foundation Models
Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
May 19, 2026Valentina Njaradi, Clémentine Dominé, Rachel Swanson +2Model Pretraining Unlabeled Data
Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions
May 19, 2026Ha Dang, Sebastian Schmidt, Juergen HesserNeural Operators Partial Differential Equations
Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
May 19, 2026Subba Reddy Oota, Anant Khandelwal, Khushbu Pahwa +4Human Visual Cortex Representational Drift
What Makes a Representation Good for Single-Cell Perturbation Prediction?
May 19, 2026Wenkang Jiang, Yuhang Liu, Yichao Cai +5Single-Cell Perturbation Prediction Representation Quality
OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization
May 19, 2026Wei-Bin Kou, Guangxu Zhu, Ming Tang +4Semi-Supervised Learning Regularization Methods
Euclidean Embedding of Data Using Local Distances
May 19, 2026Dimitris ArabadjisHyperspherical Embedding Geometry Euclidean
Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detection
May 18, 2026Yixing Yong, Jian Wang, Ming Lei +2Infrared Small Target Detection Infrared
The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation
May 17, 2026Ninad Joshi, Ashutosh Ranjan, Vivek Srivastava +1Text-To-Image Diffusion Models Formalizing Artistic Processes
Large language models reorganize representational geometry during in-context learning
May 16, 2026Hua-Dong Xiong, Li Ji-An, Robert C. Wilson +2In-Context Learning Representational Capacity
Scale Determines Whether Language Models Organize Representation Geometry for Prediction
May 16, 2026Weilun XuRepresentation Space Feature Alignment
Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents
May 16, 2026Weicheng XueAI Risk Assessment Representation Quality
Learning Relative Representations for Fine-Grained Multimodal Alignment with Limited Data
May 16, 2026Shiwon Kim, Yu Rang ParkMultimodal Alignment Multimodal Pretraining
Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers
May 14, 2026Jakub Grzywaczewski, Dawid Płudowski, Przemysław BiecekPre-Trained Vision-Language Models Vision-Language Reasoning
MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
May 14, 2026Jiaqi Sun, Boyang Sun, Rasmy M. H. +2Efficient Continual Learning Continual Learning
Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces
May 14, 2026Sanjoy Chowdhury, Dinesh ManochaReasoning Traces Reasoning Benchmark
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
May 13, 2026William Lehn-Schiøler, Magnus Ruud Kjær, Rahul Thapa +10Electroencephalography Foundation Models Improving Sparse Autoencoders
Towards Visually Grounded Multimodal Summarization via Cross-Modal Transformer and Gated Attention
May 12, 2026Abid Ali, Diego Molla-Aliod, Usman NaseemSummarization Representational Drift
Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
May 12, 2026Zeguan Xiao, Xuanzhe Xu, Yun Chen +4Large Language Model Unlearning Machine Unlearning
A Mechanistic Investigation of Supervised Fine Tuning
May 12, 2026Ruhaan ChopraSupervised Fine-Tuning Model Activations
Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
May 11, 2026Ege C. Kaya, Aliasghar Pourghani, Vijay Gupta +1Distributional Reinforcement Learning Representation Space
Don't Look at the Numbers: Visual Anchoring Bias and Layer-wise Representation in VLMs
May 11, 2026M. ShalankinRecent Vision-Language Models Representation Quality
On periodic distributed representations using Fourier embeddings
May 11, 2026Jakeb ChouinardHyperspherical Embedding Geometry Representation Space
Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions
May 11, 2026Sayan Kumar ChakiKnowledge Graph Embeddings Knowledge Graphs
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
May 10, 2026Katarzyna Filus, Kamil Faber, Roberto Corizzo +1Forgetting Continual Learning
XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity
May 10, 2026Alvin Kimbowa, Moein Heidari, David Liu +1U-Net Convolutional Neural Network Compression
SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations
May 10, 2026Mario Edoardo Pandolfo, Enrico Grimaldi, Lorenzo Marinucci +4Latent Representation Alignment Latent Representation

May 29, 2026 · cs.CLJ/K move · Enter open · S save

Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement

Riju Marwah, Ritvik Garimella, Vishal Pallagani, Atishay Jain+2

Autoregressive language models frequently degrade during long-horizon generation, producing repetitive text, losing instruction adherence, and exhibiting unstable entropy. Despite the prevalence of these failures, practitioners lack online diagnostics to detect them in real-time as they occur. We formalize this degradation as cognitive fatigue, a measurable generation-time state characterized by decay in attention to the original prompt, representational drift, and entropy miscalibration. We introduce the Fatigue Index (FI), a lightweight, model-agnostic diagnostic that aggregates these three signals under explicit axioms (monotonicity, boundedness, interpretability) enabling reliable runtime monitoring. Across nine models (1B-13B parameters), FI trajectories exhibit structured temporal dynamics, predict task degradation (AUROC = 0.95) and repetition (Spearman rho = 0.94), and reveal non-monotonic scaling behavior: instruction-tuned models below 3B exhibit faster collapse than base models, with this trend reversing at 7B. Stress analyses further show that FI onset accelerates under longer contexts, middle-positioned evidence, and reduced numerical precision. These results establish cognitive fatigue as a coherent and measurable phenomenon, and position FI as a principled tool for runtime reliability monitoring in production LLM systems.

Autoregressive Language Models Large Language Models Fail Autoregressive Transformers Representational Drift Measures Formalization

Open paper Ask about it PDF