AI Explained
Plain explanations of trending AI concepts, with live visualizations.
Ring-Zero scales zero-RL reasoning to 1T parameters — Trillion-scale zero-RL — What does it mean?
Ring-Zero runs zero-RL — reward-only RL with no SFT warm-up — at 1T parameters and finds a two-phase discovery-then-sharpening learning pattern.
MemOps benchmarks agent memory as lifecycle operations — Memory lifecycle operations — What does it mean?
MemOps grades an agent's long-term memory as four operations — remember, forget, update, reflect — not one static store of facts.
Agent optimizer study shows regression control compounds gains — Regression control in continual optimization — What does it mean?
An agent optimizer keeps compounding gains only when regression control steers it past shortcuts that boost new tasks by erasing old wins.
TIGER routes visual tokens for multimodal speculative decoding — Text-conditioned visual routing — What does it mean?
Speculative decoding helps less on images. TIGER lets the draft model peek only at the image patches its current sentence is about.
ROBIN repairs biased behavior at transformer head level — Head-level bias subspace removal — What does it mean?
ROBIN localizes bias to specific attention heads with fairness probes, then notches a small bias subspace out of their output at inference — no retraining.
MCPEvol-Bench measures agents as MCP servers change — Tool-interface drift benchmarking — What does it mean?
MCPEvol-Bench mutates real MCP servers so tool interfaces drift underneath an agent — even the best of 12 models still loses about 14% once the tools evolve.
Transformer rank study reframes Pre-Norm as gradient preservation — Rank preservation vs magnitude control — What does it mean?
Skips and Pre-Norm are taught as magnitude control. A theory paper recasts them as what keeps a deep network's gradient rank alive.
Harness Handbook localizes agent behavior before edits — Behavior-centric harness map — What does it mean?
One behavior lives in the prompt, the state, the tool call, and the coordination code. File search returns files. A behavior map returns all 4.
D-Cut prunes speculative decoding verification across batches — Cross-request draft pruning — What does it mean?
Speculative decoding gives every request the same draft depth. D-Cut pools the drafts from all of them and verifies only the ones likely to be accepted.
Atrex-Bench tests LLM-written kernels on production traces — Trace-weighted kernel benchmarking — What does it mean?
A kernel benchmark that samples operators and shapes from real serving traces and weights each one by the GPU time it actually burns.
Plan evaluator study exposes omission incentives — Deletion non-monotonicity — What does it mean?
Deleting a step a plan needs can raise its score — the scorer drops both the step's cost and its chance of failing.
Long-Horizon-Terminal-Bench grades agent progress densely — Partial-reward threshold — What does it mean?
Pass/fail turns a 231-episode run into one bit. A partial-reward threshold grades how far the agent got, and moving the line moves the score.
