Skip to content
View stochi0's full-sized avatar

Block or report stochi0

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
stochi0/README.md

ayush / stochi — a moon gate overlooking a mountain courtyard

I like World Models, RL & AI for Science. Previously an RL Resident at Prime Intellect.

Website · Papers · Writings · Projects · Email · X · ORCID

Papers

  • Intervention Search & Response Prediction — An agent found an intervention that worked. Could it predict what would happen with one it hadn’t tried? AgenticLS · NeurIPS 2026 workshop · Accepted spotlight.
  • Budgeted Predictive Knowledge — When the world changes and an agent can only recheck a few predictions, which should it check first? NEmo · NeurIPS 2026 workshop · Accepted poster.

Writings

Projects

  • Yuntun — I trained a Qwen3-style model on FineWeb using tensor parallelism.
  • Weigou — I experimented with training LLaMA-style models across GPUs.
  • GPT-2 Speedrun — Multi-GPU GPT-2 training with streamed FineWeb-Edu and resumable checkpoints.
  • BeaconGrad — I wrote autograd in NumPy and checked its gradients against finite differences and PyTorch.
  • Expandable Subspace Ensemble — I tested how a model learns new CIFAR-10 classes by expanding its feature space.
  • Discrete Walk-Jump Sampling — Antibody generation with Langevin exploration and one-step denoising.
  • Concrete Score Matching — I used score matching to learn from discrete data and Metropolis–Hastings to draw samples.

Pinned Loading

  1. latentpaths/intervention-search-response-prediction latentpaths/intervention-search-response-prediction Public

    Measuring intervention search and response prediction separately under an assay budget.

    Python

  2. latentpaths/budgeted-predictive-knowledge latentpaths/budgeted-predictive-knowledge Public

    Selecting which stored predictions receive fresh evidence under a limited update budget.

    Python

  3. latentpaths/statecraft latentpaths/statecraft Public

    Hidden, stateful environments for comparing native and programmatic tool calling.

    Python

  4. latentpaths/sparse-signal-loop latentpaths/sparse-signal-loop Public

    Experiments on feedback, working memory, and reusable skills for LLM agents.

    Python

  5. yuntun yuntun Public

    Qwen3-style language modeling with FineWeb streaming and tensor parallelism.

    Python

  6. beacongrad beacongrad Public

    NumPy autograd and neural networks, with gradient and PyTorch parity checks.

    Python