CHANNEL ARCHIVE // [225] ARTICLES // PAGE 15 OF 15
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
CHANNEL // 01 [225]
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
LOLPlay tests whether visual AI agents can keep up with League of Legends
Source published
- LOLPlay
- League of Legends
- visual AI agents
A Wrong Chemistry Answer May Hide a More Structured Internal Representation
Source published
- language models
- functional groups
- chemical representations
Teaching AI latent spaces a preferred direction of change
Source published
- latent space
- Randers geometry
- Finsler geometry
ReVi plans the story before generating a novel’s video recap
Source published
- ReVi
- novel-to-recap video generation
- multi-agent systems
Heart failure prediction models need stronger validation, review finds
Source published
- heart failure
- mortality prediction
- systematic review
Using an offline language model to build Bitcoin flash-crash simulations
Source published
- Bitcoin
- perpetual futures
- flash crashes
When sending an AI query to a smaller model first cannot save money
Source published
- large language models
- tiered inference
- confidence-gated routing
Medical AI teams improve when evidence targets gaps exposed during reasoning
Source published
- medical artificial intelligence
- multi-agent reasoning
- retrieval-augmented generation
Reserving resources for AI agents when their workloads are unknown
Source published
- agentic AI
- resource orchestration
- conformal prediction
Verified tool-health snapshots improve AI agents’ first choices in controlled tests
Source published
- AI agents
- Agent Harness Awareness
- tool health
When should an AI reviewer be allowed to overrule another agent?
Source published
- large language models
- multi-agent systems
- AI oversight
CARD separates mathematical proof from the transform a robot executes
Source published
- CARD
- certifiable geometric estimation
- robotic navigation
When AI Compliance Changes With Oversight, the Value Being Tested Matters
Source published
- alignment faking
- language models
- AI evaluation
MCPGuard Finds Protocol Checks Missing from Two Official MCP SDKs
Source published
- Model Context Protocol
- MCPGuard
- SDK conformance
Context-aware steering gives language models a more flexible control dial
Source published
- activation steering
- CLAS
- large language models