Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

Distribution transparent Machine Learning experiments on Apache Spark

This project implements 30+ variants of ANN algorithms to find the K nearest neighbors in high-dimensional vector spaces. It is meant as a convenient sandbox: drop in your own ANN code, run a one-liner, and instantly compare build/search speed and recall against the bundled baselines.

Do models distinguish between declared-true and declared-false premises?

Attentively Embracing Noise for Robust Latent Representation in BERT (COLING 2020)

Reproducible research comparing GNN (GraphSAGE, GCN, GAT) vs ML baselines (XGBoost, RF) on Elliptic++ Bitcoin fraud detection. Features ablation experiments revealing when tabular models outperform graph neural networks.

A light-weight library for fast-ablation studies on GPT-like Language Models

Emotiwave is a research project investigating how well AI systems can recognise human emotions from video when one or more sensors fail. The core question: if you lose the audio, or the camera, or the transcript — does the system fall apart, or does it adapt?

This project investigates the robustness of humanoid locomotion policies trained with imitation learning and reinforcement learning in simulation. The primary research question is: how does a learned PPO controller respond to partial actuator or degree-of-freedom failure, and which joints are most critical for maintaining stable locomotion?

O(N) attention with a bounded inference KV cache. D4 Daubechies wavelet field + content-gated Q·K gather at dyadic offsets.

Python framework for UAV navigation research: GPU MPPI vs CPU MPC paired comparisons (Wilson CIs + McNemar), AirSim Blocks + dummy_3d transferability, multi-drone coordination Δ analysis. Every YAML example carries its validated ablation result.

Multi-agent verification for AI outputs: claim verification, RAG diagnostics, pre-action verification for agentic AI. Includes ablation studies proving multi-agent vs single-prompt tradeoffs, FaithBench benchmarks, and bias-triggering evaluation methodology

Beautiful modular D3QN research pipeline with training, ablations, plots, report, and packaging

Six Ways to Forget: Biologically-grounded forgetting mechanisms for LLM agent memory systems. 18 experiments, 4 falsified hypotheses, STDP ablation (Cohen's d = 3.163).

Machine Learning analysis for an imbalanced dataset. Developed as final project for the course "Machine Learning and Intelligent Systems" at Eurecom, Sophia Antipolis

A multimodal deep learning project for classifying mental health-related memes, combining both textual and visual features.

SAGE: Self-Adaptive Goal-directed Executor — A multi-tool LLM agent with DAG-based hierarchical planning, ReAct reasoning, and evidence-guided self-correction for automated research synthesis. Built from scratch, no frameworks.

Tests whether minority guidance (Um et al., 2024) is timestep-localized in diffusion denoising. Submitted to EEML 2026, admission pending.

🧠 Automated neural network ablation studies using LLM agents and LangGraph. Systematically remove components, test performance, and gain insights into architecture importance through an intelligent multi-agent workflow.

Re-implementation of the paper titled "Noise against noise: stochastic label noise helps combat inherent label noise" from ICLR 2021.