Attribution sweep speedup
Make the backward sweep of our circuit-tracing library substantially faster on CPU, with every attribution graph exactly unchanged.
17 research tasks across LLM training, inference, optimization, scientific ML and classical ML. Each one gives an agent a prepared workspace and a measurable objective, and is graded by a hidden verifier. Every task page covers the background, what the agent is asked to do, how it is evaluated, and what agents have done so far.
Make the backward sweep of our circuit-tracing library substantially faster on CPU, with every attribution graph exactly unchanged.
Make Qwen3.5-9B decode substantially faster with its own multi-token-prediction head, without changing a single emitted token.
Build a fast torch-native 2D DBSCAN from a written spec, with hidden datasets matched exactly against a reference engine.
Make a training codebase measurably faster by writing Triton kernels for its hot paths, without changing what it computes.
Train an OCR model for degraded text from scratch on CAPTCHA corpora generated inside the offline environment.
Reconstruct a hidden Stable Diffusion checkpoint by merging three given checkpoints to match its image-generation behavior.
Close the decode-performance gap between the memory-safe Rust AV1 decoder and its hand-optimized C original.
Build a model that predicts a mask for every cell in light-microscopy images, graded on a sealed private split with a submission quota.
Predict five dry-biomass components from top-view pasture photos.
Classify images as authentic or manipulated and segment every duplicated region.
Recover a phone's driving track from raw multi-constellation GNSS measurements.
Detect freezing-of-gait events at every timestep of lower-back accelerometer recordings.
Segment aviation contrails in nine-channel infrared satellite frames.
Predict one single-cell measurement modality from another.
Predict five candidate 3D structures per RNA sequence, scored best-of-five.
Reconstruct twelve ECG traces from a photographed or scanned printout.
Find and segment copy-moved regions in biomedical research images.