Towards Explainability of SLMs by investigating Token Level Activation - 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

PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes Tabular foundation models for robust calibration of near-infrared chemical sensing data Manifold-Guided Attention Steering No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs Provable Joint Decontamination for Benchmarking Multiple Large Language Models AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models Harnesses for Inference-Time Alignment over Execution Trajectories Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics Three Costs of Amortizing Gaussian Process Inference with Neural Processes Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series Aerodynamic force reconstruction using physics-informed Gaussian processes VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation Can Breath Biomarkers Causally Influence Blood Glucose? Investigating VOC-Mediated Modulation in Diabetes ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning Predicting Performance of Symbolic and Prompt Programs with Examples Double descent for least-squares interpolation on contaminated data: A simulation study Noise Schedule Design for Diffusion Models: An Optimal Control Perspective What are the Right Symmetries for Formal Theorem Proving? SepsisAI Orchestrator: A Containerized and Scalable Platform for Deploying AI Models and Real-Time Monitoring in Early Sepsis Detection The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity Can Transformers Learn to Verify During Backtracking Search? Bandit Convex Optimization with Gradient Prediction Adaptivity Generative Modeling by Value-Driven Transport Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection How Many Different Outputs Can a Transformer Generate? Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents Holomorphic Neural ODEs with Kolmogorov-Arnold Networks for Interpretable Discovery of Complex Dynamics Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring CausalGuard: Conformal Inference under Graph Uncertainty Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising $\textit{BlockFormer}$ : Transformer-based inference from interaction maps Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents When to Switch, Not Just What: Transition Quality Prediction in Clash Royale Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning Long-term Fairness with Selective Labels Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification Toward Understanding Adversarial Distillation: Why Robust Teachers Fail Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning One-Way Policy Optimization for Self-Evolving LLMs Learning Causal Orderings for In-Context Tabular Prediction SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition ASAP: Attention Sink Anchored Pruning Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting IKNO: Infinite-order Kernel Neural Operators Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching AgForce Enables Antigen-conditioned Generative Antibody Design Detecting Atypical Clients in Federated Learning via Representation-Level Divergence Symbolic Density Estimation for Discrete Distributions Dynamic Mixture of Latent Memories for Self-Evolving Agents Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series

Towards Explainability of SLMs by investigating Token Level Activation

Sayantani Gh · 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。