127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “context”

14,981 results

Research

Multi-Gate Residuals

DGX agent

arXiv:2605.23259v1 Announce Type: cross Abstract: While Attention Residuals has shown some effectiveness in addressing the widespread issue of unbounded activation growth across deep residual layers,

researcharxiv-cs-ai

25 May 2026

Safety

Naturalistic measure of social norms alignment

DGX agent

arXiv:2605.23420v1 Announce Type: new Abstract: Social norms reflect shared expectations on acceptable behavior. Measuring social norms alignment remains challenging, with existing approaches typicall

Search: “context”

Multi-Gate Residuals

Naturalistic measure of social norms alignment

On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning

Operator Learning for Reconstructing Flow Fields from Sparse Measurements: a Language Model Approach

PaP-NF: Probabilistic Long-Term Time Series Forecasting via Prefix-as-Prompt Reprogramming and Normalizing Flows

PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction

Pooling and Semantic Shift: The Fundamental Challenges in Long Text Embedding and Retrieval

RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations

Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control

SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction

Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations

The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models

U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025

Vision Transformers Need Better Token Interaction

What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference

When Is Next-Token Prediction Useful? Marginalization, Ergodicity, Mixture Identifiability, Local Sufficiency, RAG, Tools, and Programming

X-TRACK: Physics-Aware xLSTM for Realistic Vehicle Trajectory Prediction

A Mechanistic Explanatory Strategy for XAI

Abstraction for Offline Goal-Conditioned Reinforcement Learning

AgForce Enables Antigen-conditioned Generative Antibody Design

ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage

Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models

Can Transformers Learn to Verify During Backtracking Search?

ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification

CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimization

Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost

Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification

EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes

End-to-End Semantic ID Generation for Generative Advertisement Recommendation

Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs

HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction

How Many Different Outputs Can a Transformer Generate?

Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks

MoralityGym: A Benchmark for Evaluating Hierarchical Moral Alignment in Sequential Decision-Making Agents

MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems

Neuro-Symbolic AI for Analytical Solutions of Differential Equations

Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier

RADAR: Defending RAG Dynamically against Retrieval Corruption

Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets

When to Switch, Not Just What: Transition Quality Prediction in Clash Royale

Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning

Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?

An Entity Linking Agent for Question Answering

An Evidence Hierarchy for Bayesian Object Classification via OSINT-Aided Heterogeneous Sensor Fusion

Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation