{"total":93,"rows":[{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2510.06477","title":"Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin","created":"2025-10-07","cited_by_count":52,"area":null},{"id":"2405.15273","title":"Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders","created":"2024-05-24","cited_by_count":38,"area":null},{"id":"2401.04136","title":"The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline","created":"2024-01-07","cited_by_count":33,"area":"diffusion"},{"id":"2410.02338","title":"How Much Can RAG Help the Reasoning of LLM?","created":"2024-10-03","cited_by_count":31,"area":"lr"},{"id":"2312.14499","title":"Hutchinson Trace Estimation for High-Dimensional and High-Order Physics-Informed Neural Networks","created":"2023-12-22","cited_by_count":23,"area":null},{"id":"2311.12803","title":"On Copyright Risks of Text-to-Image Diffusion Models","created":"2023-09-15","cited_by_count":20,"area":"diffusion"},{"id":"2311.15283","title":"Bias-Variance Trade-off in Physics-Informed Neural Networks with Randomized Smoothing for High-Dimensional PDEs","created":"2023-11-26","cited_by_count":19,"area":null},{"id":"2401.01623","title":"Can AI Be as Creative as Humans?","created":"2024-01-03","cited_by_count":17,"area":null},{"id":"2406.01549","title":"An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation","created":"2024-06-03","cited_by_count":16,"area":"rag"},{"id":"2402.03254","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2501.02191","title":"On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing","created":"2025-01-04","cited_by_count":11,"area":null},{"id":"2401.09067","title":"Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding","created":"2024-01-17","cited_by_count":10,"area":null},{"id":"2502.02853","title":"Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation","created":"2025-02-05","cited_by_count":10,"area":"offlinerl"},{"id":"2505.15239","title":"Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers","created":"2025-05-21","cited_by_count":10,"area":null},{"id":"2404.17951","title":"Cauchy-Schwarz Divergence Information Bottleneck for Regression","created":"2024-04-27","cited_by_count":9,"area":null},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2512.21720","title":"An Information Theoretic Perspective on Agentic System Design","created":"2025-12-25","cited_by_count":8,"area":"agents"},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2505.17322","title":"From Compression to Expression: A Layerwise Analysis of In-Context Learning","created":"2025-05-22","cited_by_count":6,"area":"offlinerl"},{"id":"2601.22709","title":"Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs","created":"2026-01-30","cited_by_count":6,"area":"mllm"},{"id":"2312.00057","title":"VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2403.07601","title":"Unified Source-Free Domain Adaptation","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2405.16731","title":"Pretraining with Random Noise for Fast and Robust Learning without Weight Transport","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2505.13946","title":"Visual Instruction Bottleneck Tuning","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2507.23554","title":"DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer","created":"2025-07-31","cited_by_count":5,"area":"agents"},{"id":"2404.13904","title":"Deep Regression Representation Learning with Topology","created":"2024-04-22","cited_by_count":4,"area":null},{"id":"2406.06227","title":"PAC-Bayes Analysis for Recalibration in Classification","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2410.22887","title":"Generalization Bounds via Conditional $f$-Information","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2509.20829","title":"Explaining Grokking and Information Bottleneck through Neural Collapse Emergence","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2509.26327","title":"A Generalized Information Bottleneck Theory of Deep Learning","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2602.04920","title":"CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2312.00462","title":"Learning Unorthogonalized Matrices for Rotation Estimation","created":"2023-12-01","cited_by_count":3,"area":null},{"id":"2410.13577","title":"Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2501.03074","title":"AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation","created":"2025-01-06","cited_by_count":3,"area":null},{"id":"2505.16950","title":"Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2505.17423","title":"VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2509.18043","title":"Prepare Before You Act: Learning From Humans to Rearrange Initial States","created":"2025-09-22","cited_by_count":3,"area":"offlinerl"},{"id":"2510.22099","title":"Generalization or Memorization: Dynamic Decoding for Mode Steering","created":"2025-10-25","cited_by_count":3,"area":"mechinterp"},{"id":"2311.04561","title":"Information-Theoretic Generalization Bounds for Transductive Learning and its Applications","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2401.02904","title":"Class-wise Generalization Error: an Information-Theoretic Analysis","created":"2024-01-05","cited_by_count":2,"area":null},{"id":"2406.05510","title":"Representation Learning with Conditional Information Flow Maximization","created":"2024-06-08","cited_by_count":2,"area":null},{"id":"2409.10075","title":"Steinmetz Neural Networks for Complex-Valued Data","created":"2024-09-16","cited_by_count":2,"area":null},{"id":"2409.18630","title":"Entropy, concentration, and learning: a statistical mechanics primer","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2502.09122","title":"Improving Deep Regression with Tightness","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2502.15540","title":"Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2504.18538","title":"Generalization Capability for Imitation Learning","created":"2025-04-25","cited_by_count":2,"area":"offlinerl"},{"id":"2511.17843","title":"JigsawComm: Joint Semantic Feature Encoding and Transmission for Communication-Efficient Cooperative Perception","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2512.22102","title":"Explainable Multimodal Regression via Information Decomposition","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2601.01896","title":"Tackling the Inherent Difficulty of Noise Filtering in RAG","created":"2026-01-05","cited_by_count":2,"area":"rag"},{"id":"2602.00454","title":"Cross-Modal Memory Compression for Efficient Multi-Agent Debate","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2602.14626","title":"Concepts' Information Bottleneck Models","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2402.01238","title":"Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2407.01017","title":"Coding for Intelligence from the Perspective of Category","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2407.14320","title":"How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2503.04667","title":"An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2503.06325","title":"Understanding the role of autoencoders for stiff dynamical systems using information theory","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2507.10215","title":"A Graph Sufficiency Perspective for Neural Networks","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.02126","title":"Understanding Learning Dynamics Through Structured Representations","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2509.02084","title":"Towards Comprehensive Information-theoretic Multi-view Learning","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2509.20997","title":"Binary Autoencoder for Mechanistic Interpretability of Large Language Models","created":"2025-09-25","cited_by_count":1,"area":"mechinterp"},{"id":"2510.02390","title":"F-scheduler: illuminating the free-lunch design space for fast sampling of diffusion models","created":"2025-09-30","cited_by_count":1,"area":"diffusion"},{"id":"2510.24194","title":"Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames","created":"2025-10-28","cited_by_count":1,"area":"offlinerl"},{"id":"2510.25096","title":"Learning Fair Graph Representations with Multi-view Information Bottleneck","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2510.25262","title":"IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2511.08152","title":"Boomda: Balanced Multi-objective Optimization for Multimodal Domain Adaptation","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2512.05515","title":"DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2602.06549","title":"Refining the Information Bottleneck via Adversarial Information Separation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.04688","title":"Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2605.13032","title":"What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2406.06700","title":"Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2410.15475","title":"Multimodal Fusion via Self-Consistent Task-Gradient Fields","created":"2024-10-20","cited_by_count":0,"area":null},{"id":"2411.03068","title":"Alpha and Prejudice: Improving $\\alpha$-sized Worst-case Fairness via Intrinsic Reweighting","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2505.08961","title":"Learning Informative Attention Weights for Person Re-Identification","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2505.19470","title":"Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2509.22365","title":"HierLight-YOLO: A Hierarchical and Lightweight Object Detection Network for UAV Photography","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2509.25225","title":"MSCoD: An Enhanced Bayesian Updating Framework with Multi-Scale Information Bottleneck and Cooperative Attention for Structure-Based Drug Design","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.15422","title":"Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2601.11334","title":"Information Theoretic Perspective on Representation Learning","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2601.15751","title":"Tabular Incremental Inference","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.14002","title":"The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2605.09316","title":"Neural Information Causality","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2609.05174","title":"SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.05913","title":"Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language Models","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.19122","title":"Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.31722","title":"Where Does the Watermark Hide? Push-Pull Disentanglement for Invisible Watermark Removal","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.33640","title":"SafeMol: Dual-Modality Safety Alignment for Molecular Multimodal Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.36118","title":"The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interface","created":"2026-09-28","cited_by_count":0,"area":"vla"},{"id":"2609.38768","title":"Learning Under Forgetting: Statistical Support-Selective Retention in Stochastic Training Dynamics","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39525","title":"Mitigating Representation Gaps in Amortized Bayesian Inference with Auxiliary Supervision","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01175","title":"Rethinking the Information Bottleneck: Structured Decomposition under Label-Induced Partitions","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.16049","title":"Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}