CHANNEL ARCHIVE // [166] ARTICLES // PAGE 2 OF 12
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
CHANNEL // 01 [166]
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
AR Glasses That Remember Encounters—and Keep the Images Behind Their Answers
Source published
- augmented reality
- AR glasses
- spatial memory
Virtual Sensors Seek the Source of Industrial Faults
Source published
- virtual sensors
- fault diagnosis
- ReDiVO
CogniLife proposes a way for AI experts to learn from their creators
Source published
- CogniLife
- AI agents
- expert marketplaces
An Optical AI Experiment That Revises Its Own Tools
Source published
- autonomous experimentation
- scientific agents
- optical see-through displays
A Geometric Approach to Making Transformer Attention Sparse
Source published
- structured sparsity
- Transformer attention
- Parametric Linear Conic Projection
AI Can Fix a Simulated System Without Finding What Broke It
Source published
- artificial intelligence
- scientific reasoning
- causal inference
Language Models Help Tune the Search for Better Satellite Imaging Schedules
Source published
- Earth observation
- satellite scheduling
- large language models
Proving GPU Kernel Correctness in Lean—Within Explicit Limits
Source published
- GPU kernel correctness
- formal verification
- Lean
Stricter AI checks did not consistently improve research results in two tests
Source published
- automated research
- large language models
- verifier strength
CaliSplat cuts the search cost of Gaussian image compression
Source published
- CaliSplat
- image compression
- 2D Gaussian representations
Preprint Finds Hidden Evaluation Errors Can Reshuffle AI Agent Rankings
Source published
- AI agents
- agent evaluation
- leaderboards
Correct Answers Can Hide an AI Model’s Dependence on Metadata
Source published
- language models
- metadata
- shortcut learning
H2RB preprint explores how human demonstrations can teach robots new tasks
Source published
- H2RB
- human-to-robot transfer
- vision-language-action models
When 4-Bit AI Models Run Faster—and When the Advantage Disappears
Source published
- large language models
- quantization
- LLM serving
When a Robot Experiment Becomes Scientific Evidence
Source published
- embodied AI
- AI for science
- self-driving laboratories