Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks - 惯性聚合

推荐订阅源

博客园 - Franky

Proofpoint News Feed

Palo Alto Networks Blog

Hackread – Cybersecurity News, Data Breaches, AI and More

The Register - Security

Security @ Cisco Blogs

Simon Willison's Weblog

Recorded Future

大猫的无限游戏

Microsoft Research Blog - Microsoft Research

Tailwind CSS Blog

cs.CV updates on arXiv.org

Cyber Security Advisories - MS-ISAC

Application and Cybersecurity Blog

True Tiger Recordings

有赞技术团队

Cisco Talos Blog

Hacker News - Newest: "LLM"

The GitHub Blog

cs.AI updates on arXiv.org

博客园 - 叶小钗

Hugging Face - Blog

Hacker News: Ask HN

Security Archives - TechRepublic

Future of Privacy Forum

PCI Perspectives

Help Net Security

让小产品的独立变现更简单 - ezindie.com

The Blog of Author Tim Ferriss

Netflix TechBlog - Medium

罗磊的独立博客

Apple Machine Learning Research

Security Latest

美团技术团队

博客园 - 三生石上(FineUI控件)

Schneier on Security

CERT Recently Published Vulnerability Notes

cs.LG updates on arXiv.org

Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems Evaluation of Pipelines for Data Integration into Knowledge Graphs Predicting Performance of Symbolic and Prompt Programs with Examples Bandit Convex Optimization with Gradient Prediction Adaptivity When to Switch, Not Just What: Transition Quality Prediction in Clash Royale How Many Different Outputs Can a Transformer Generate? Can Breath Biomarkers Causally Influence Blood Glucose? Investigating VOC-Mediated Modulation in Diabetes On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective Double descent for least-squares interpolation on contaminated data: A simulation study From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability Holomorphic Neural ODEs with Kolmogorov-Arnold Networks for Interpretable Discovery of Complex Dynamics Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics IKNO: Infinite-order Kernel Neural Operators Symbolic Density Estimation for Discrete Distributions Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study Tabular foundation models for robust calibration of near-infrared chemical sensing data $\textit{BlockFormer}$ : Transformer-based inference from interaction maps Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning Harnesses for Inference-Time Alignment over Execution Trajectories Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification Manifold-Guided Attention Steering Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising Support-aware offline policy selection for advertising marketplaces stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems Thermodynamic Irreversibility of Training Algorithms Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model Aerodynamic force reconstruction using physics-informed Gaussian processes Detecting Atypical Clients in Federated Learning via Representation-Level Divergence AgForce Enables Antigen-conditioned Generative Antibody Design Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning What are the Right Symmetries for Formal Theorem Proving? Noise Schedule Design for Diffusion Models: An Optimal Control Perspective OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning Dynamic Mixture of Latent Memories for Self-Evolving Agents Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines Can Transformers Learn to Verify During Backtracking Search? ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction Engineering Hybrid Physics-Informed Neural Networks for Next-Generation Electricity Systems: A State-of-the-Art Review Provable Joint Decontamination for Benchmarking Multiple Large Language Models Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation Three Costs of Amortizing Gaussian Process Inference with Neural Processes SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy Toward Understanding Adversarial Distillation: Why Robust Teachers Fail LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs TBP-mHC: full expressivity for manifold-constrained hyper connections through transportation polytopes PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans One-Way Policy Optimization for Self-Evolving LLMs Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning CausalGuard: Conformal Inference under Graph Uncertainty

Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks

Vamshi Sunku · 2026-05-23 · via cs.LG updates on arXiv.org

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。