127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “papers”

18,005 results

Safety

https://x.com/CAIS/status/2060031683420999844?s=20

DGX agent

https://x.com/CAIS/status/2060031683420999844?s=20 AI systems may soon help run economies, infrastructure, and military operations. But these systems are not reliably loyal or secure. An adversary can

safetydan-hendrycks--x

6 Jun 2026

Agents

Search: “papers”

https://x.com/CAIS/status/2060031683420999844?s=20

Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents

Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming

ITP-STDP: An Intrinsic-Timing Power-of-Two Learning Engine for On-Chip SNN Training

LatentWave: JEPA Pretraining for Wireless Foundation Models

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation

New research from Renmin University. Treat skill selection as a harness in its own right. If you design skill routing for personal or edge a…

Ontology-constrained multi-LLM scoring of hypothesis support in the predictive processing literature

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

Reformulating Neural Operators in d+1 Dimensions for Embedding Evolution

Risk Assessment of Autonomous Driving: Integrating Technical Failures, Ethical Dilemmas, and Policy Frameworks

Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking

Separation Power of Equivariant Neural Networks

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

The End of Software Engineering: How AI Agents Are Fundamentally Restructuring the Software Paradigm

Uncertainty Aware Functional Behavior Prediction and Material Fatigue Assessment for Circular Factory

Where's the Structure? A Systematic Literature Review of Empirical Research on Human-AI Collaboration and Hybrid Intelligence for Learning

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

X-Band UAV-enabled Integrated Sensing and Communications for Vehicular Networks

A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation

Agents' Last Exam

// Agents' Last Exam // Agents' Last Exam is a living benchmark of over 1,000 economically valuable tasks, built with 250+ industry experts …

Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

Benchmarking Open-Source Layout Detection Models for Data Snapshot Extraction from Institutional Documents

Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models

Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems

CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction

Channel-Wise Mixed-Precision Quantization for Large Language Models

CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing

CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement

Critical context on the new Anthropic blog: 1, AGI is *harder* than RSI (as used below). AGI: machine can do anything human can do, autonomo…

Deep Learning-based 3D Oral Cavity Reconstruction Using 2D Intraoral Images

Domain-Aware Mispronunciation Detection and Diagnosis Using Language-Specific Statistical Graphs

Drishti AI-Event Guardian: An Intelligent Real-Time Crowd Monitoring and Emergency Response System for Mass Gathering Events

Efficient Computation of Distance Functions for Navigation Vector Fields in Lie Groups

Efficient Mean Curvature Computation on High-Dimensional Data Manifolds

Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems

EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation

Entropy-Based Evaluation of AI Agents: A Lightweight Framework for Measuring Behavioral Patterns

Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails

Geodesic Flow Matching on a Riemannian Degradation Manifold for Blind Image Restoration

Global-Local Monte Carlo Tree Search in Vision-Language Models for Text-to-3D Indoor Scene Generation

HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD Maps

Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?

I always appreciate the opportunity to discuss @LawZero_ and our approach to honest, reliable AI. Working on the Scientist AI with my brilli…

IDEAL: Leveraging Infinite and Dynamic Characterizations of Large Language Models for Query-focused Summarization

Critical context on the new Anthropic blog: 1, AGI is harder than RSI (as used below). AGI: machine can do anything human can do, autonomo…