Skip to content
View zatchbell1311-wq's full-sized avatar
1 follower · 7 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report zatchbell1311-wq

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
zatchbell1311-wq/README.md

Dhruv Dubey

Independent AI Researcher · LLM Memory Architectures · Open Source Contributor

Research

Building novel memory architectures for LLMs — independently, without lab resources.

DSPM (Dynamic Semantic Patch Memory)

  • 82.4% token reduction
  • 94.2% compression-retention ratio across 7 technical dialogue domains
  • Statistically validated (Wilcoxon signed-rank, p = 0.0431)
  • Zenodo preprint: https://zenodo.org/records/19438636
  • Accepted into the Sarvam AI Startup Program

SSPM (Streaming Sparse Prompt Modeling)

Vyom OS (ALISA — AI-Integrated OS Architecture)

  • Systems-level architecture spanning:
    • Bootloader
    • Paging
    • Priority Scheduling
  • Presented, under review, IEEE-affiliated ICSEAI 2026

Open Source

Yale pie (pie-project/pie)

  • 4 merged PRs:
    • #382 — stderr forward-port
    • #383 — sharded GGUF loading
    • #391 — E2E test coverage for raw-completion
    • #407 — async system test coverage
  • Open PRs: #460 (CUDA graph key-collision fix), #462 (Vulkan/Windows Context::fork() corruption fix)
  • Issue #418
    • Isolated a Vulkan-backend memory-corruption defect via clean baseline comparison
    • Documented workaround

UW VibeServe (uw-syfi/vibesys)

  • 3 merged PRs, supervised by Vic Shihang Li (UW SyFI):
    • #54 — default queue reference, accuracy checker, and benchmark harness
    • #241 — deep-agent graph caching (eliminated full graph rebuild per invocation)
    • #312 — CI gates for format, lint, and coverage in development guide
  • Invited into core UI team (August 2026)

Point Cloud Library (PCL)

  • Merged PR #6398
  • Fixed non-deterministic azimuth orientation in ShapeContext3DEstimation

Pyserini / Anserini (Castorini Research Group, University of Waterloo)

  • Merged PR #2483
  • Merged PR #3227
  • Reviewed and merged by Prof. Jimmy Lin
  • Reproduced and validated baseline metrics:
    • BM25
    • uniCOIL
    • SPLADE
    • Contriever
  • Environment:
    • Ubuntu 24.04
    • Java 21

Stack

  • Python
  • C/C++
  • TypeScript
  • PyTorch
  • OS Kernels & Memory Management
  • LLM Inference Pipelines
  • REST APIs
  • PostgreSQL
  • Supabase
  • Groq API
  • Gemini API

Achievements

  • Solved 300+ LeetCode problems
    • Arrays, Linked Lists, STL, Dynamic Programming, Graphs, Trees
  • 331 combined Zenodo views
  • 186 downloads across two published preprints
  • NVIDIA GTC 2025 attendee
  • Solo participant, Meta PyTorch Hackathon × Scaler

Links

Pinned Loading

  1. dynamic-semantic-patch-memory dynamic-semantic-patch-memory Public

    DSPM achieves a mean Token Reduction Rate (TRR) of 82.4% ± 4.21% across seven heterogeneous technical dialogue scenarios, surpassing the 55% and 60% design targets, while retaining a mean consiste…

    Python 1

  2. pcl pcl Public

    Forked from PointCloudLibrary/pcl

    Point Cloud Library (PCL)

    C++ 1

  3. Sparse-Semantic-Patch-Memory-SSPM-Proof-of-Concept- Sparse-Semantic-Patch-Memory-SSPM-Proof-of-Concept- Public

    The repository accompanies the SSPM research preprint and includes a Google Colab–ready notebook for experimental validation and visualization.

    Jupyter Notebook 1

  4. anserini anserini Public

    Forked from castorini/anserini

    Anserini is a Lucene toolkit for reproducible information retrieval research

    Java

  5. pyserini pyserini Public

    Forked from castorini/pyserini

    Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

    Python

  6. semantic-patch-triage-env semantic-patch-triage-env Public

    META Hackathon

    Python