Neural Representations as New Modes of Interactivity
cs.HC
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Evaluating the Promise and Pitfalls of LLMs in Hiring Decisions
- Qwen3-VL Technical Report
- GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
- Mechanistic Interpretability for AI Safety -- A Review
- Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
- Stochastic Parameter Decomposition
- Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Designing a Dashboard for Transparency and Control of Conversational AI
- Illusions of Intimacy: How Emotional Dynamics Shape Human-AI Relationships
- Scaling and evaluating sparse autoencoders
- Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
- Language Models Represent Space and Time
- Bridging the Gap in the Responsible AI Divides
- Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations
- Steering CLIP's vision transformer with sparse autoencoders
- Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift
- Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
- Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations
- Linear Representations of Political Perspective Emerge in Large Language Models
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems