CHANNEL ARCHIVE // [1025] ARTICLES // PAGE 67 OF 69
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
CHANNEL // 01 [1025]
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
A bid to make AI circuits more stable has a proof gap
Source published
- mechanistic interpretability
- Certified Circuits
- circuit discovery
Can Gossip Help Networks Aggregate Rankings?
Source published
- ranking aggregation
- gossip algorithms
- decentralized computing
- NO VISUAL
A simple learning rule may help digit recognition withstand image corruption
Source published
- reservoir computing
- Hebbian learning
- image classification
Soft Set Theory and Its Many Extensions
Source published
- soft set theory
- mathematics
- uncertainty
- NO VISUAL
Can a few smart questions help an AI learn what you prefer?
Source published
- AI personalization
- Bayesian inference
- preference elicitation
Evolving Instructions Alongside AI Training Improves Benchmark Results
Source published
- Evolutionary System Prompt Learning
- E-SPL
- reinforcement learning
- NO VISUAL
Can AI find the right peer reviewers?
Source published
- peer review
- reviewer recommendation
- large language models
BrainVista tests whether AI can forecast changing brain states
Source published
- BrainVista
- fMRI
- brain-state forecasting
Teaching image models to notice the parts, not just the scene
Source published
- vision-language models
- image-text retrieval
- visual grounding
Tracing the Internal Signals Behind Language Model Reasoning
Source published
- large language models
- mechanistic interpretability
- Integrated Policy Gradient
FiLoRA explores whether instructions can shift an AI’s feature reliance
Source published
- multimodal AI
- LoRA
- feature reliance
MinPRO tests a prefix-aware approach to steadier language-model training
Source published
- large language models
- reinforcement learning
- off-policy optimization
A public image collection aims to give ERCP AI a clearer test
Source published
- ERCP
- medical imaging
- artificial intelligence
How Moral Concepts Are Organized Inside Language Models
Source published
- large language models
- Moral Foundations Theory
- AI interpretability
- NO VISUAL
Teaching aerial-image AI to spot change without drawing every change map
Source published
- remote sensing
- change detection
- weak supervision