CHANNEL ARCHIVE // [685] ARTICLES // PAGE 41 OF 46
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
CHANNEL // 01 [685]
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
When Answer Order Changes an AI Decision
Source published
- System One decision models
- demographic bias
- AI auditing
Estimating AI Reliability With Fewer Repeated Trials
Source published
- AI evaluation
- Beta mixtures
- repeated sampling
Compressing Small Language Models: When Combining Techniques Helps—and When It Fails
Source published
- small language models
- model compression
- quantization
Exo lets AI agents rewrite their harness while working
Source published
- Exo
- AI agents
- agent harnesses
Medical AI scores fall sharply when answer choices disappear
Source published
- medical AI
- large language models
- medical question answering
Can Matching Score Distributions Bring AI Judges Closer to Human Ratings?
Source published
- LLM-as-a-judge
- streaming quantile matching
- score calibration
A framework for human–AI teamwork that accounts for how advice changes decisions
Source published
- human–AI collaboration
- collaborative omnimechanism design
- outcome indistinguishability
A Transformer’s Arithmetic Circuit Works Despite Local Geometric Distortion
Source published
- mechanistic interpretability
- modular addition
- transformer circuits
Can an AI Monitor Tell Score Manipulation From a Mistake?
Source published
- AI monitoring
- reward hacking
- large language models
A map of robot behavior helps people investigate failures
Source published
- robotics
- behavior graphs
- deployment data
CalVLA makes robot confidence more informative—but not control more successful
Source published
- CalVLA
- vision-language-action policies
- OpenVLA
When AI Safeguards Miss the Same Mistakes
Source published
- AI agents
- LLM safeguards
- correlated errors
A Neural Network Learns to Group Related Logic Functions
Source published
- NPN classification
- Boolean functions
- graph neural networks
Can One Token per Creator Improve Recommendations?
Source published
- generative recommendation
- Atomic Creator Tokens
- Semantic IDs
When Coding Agents Work Alone, Their Changes Can Clash
Source published
- AI coding agents
- multi-agent coordination
- ParallACT