AI research and projects
The research, projects, and explanations behind the people. Read the source, inspect verified code and models, and find a collaborator.
A source check confirms that a source supports the summary. It is not an independent replication or endorsement. Our methodology ↗
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
Dr. Been Kim · Google DeepMindInvented TCAV (Testing with Concept Activation Vectors), an interpretability framework that uses directional derivatives in activation space to quantify how much a human-understandable concept (e.g., stripes on a zebra) contributes to a model's prediction.
Requires user-provided exemplars for concept definitions; high-level abstract concepts without clear visual or lexical exemplars can be difficult to vectorize cleanly.
Context: InceptionV3, ResNet internal activation layers, linear classifiers in latent embedding manifolds.
View missionLeakage and the Reproducibility Crisis in Machine-Learning-Based Science
Dr. Sayash Kapoor · Princeton UniversityPublished a comprehensive meta-analysis of machine learning scientific literature discovering data leakage across 329 papers spanning 17 fields, establishing formal taxonomy and verification criteria to prevent train-test contamination.
Meta-analyses depend on publicly available replication code; studies with proprietary or non-shared datasets could not be independently tested.
Context: Reproducibility audit across computer vision, clinical healthcare predictions, and natural language processing.
View missionMixtral of Experts: Sparse Mixture-of-Experts Open Weight Model
Arthur Mensch · Mistral AIPublished the architectural blueprint for Mixtral 8x7B, a sparse mixture-of-experts model where a router chooses 2 out of 8 feedforward experts per token, activating only 13B parameters out of 47B during forward pass and outperforming Llama 2 70B with 6x faster throughput.
High RAM/VRAM memory footprint for hosting all 47B parameters despite activating only 13B during computation; requires specialized multi-GPU tensor or pipeline parallelism.
Context: 46.7B total parameters, 12.9B active parameters per token, 32k token context window, Top-2 softmax gating router.
View missionModel Cards for Model Reporting: Standardizing ML Evaluation Disclosures
Dr. Margaret Mitchell · Hugging FaceAuthored the seminal ACM FAccT paper introducing 'Model Cards for Model Reporting', an operational documentation standard that details model architecture, intended tasks, training parameters, out-of-scope uses, and disaggregated demographic evaluations.
Static documentation can diverge from deployed weights if model inputs undergo runtime changes or unlogged adapter swaps.
Context: Disaggregated evaluation metrics across intersecting demographic slices and environmental contexts.
View missionOn the Dangers of Stochastic Parrots: Can Language Models Be Too Big?
Dr. Timnit Gebru · Distributed AI Research Institute (DAIR)Published the landmark ACM FAccT paper critically examining the environmental costs, training data biases, lack of semantic grounding, and illusion of intent when scaling large autoregressive language models without curated provenance.
Focusing on systemic risks does not quantify operational benefits in domain-specific tasks where automated verification pipelines exist.
Context: Analysis of Web-scraped pre-training corpora (Common Crawl, C4) and environmental compute costs.
View missionRelative Representations Enable Non-Degenerate Latent Space Alignment
Dr. Been Kim · Google DeepMindCo-authored breakthrough research demonstrating that representations can be compared across disparate neural networks by computing pairwise angles and similarities to anchor points, proving latent geometries are invariant across architectures.
Choice and distribution of anchor points can introduce variance in representation reconstruction accuracy across domain shifts.
Context: Cross-model embedding alignment across Vision Transformers, CNNs, and language models without weight access.
View missionSocial Chemistry 101: Learning to Reason about Social and Moral Norms
Dr. Yejin Choi · University of Washington / Allen Institute for AIIntroduced Social Chemistry 101, a computational framework and dataset containing 292,000 rules-of-thumb covering social conventions, moral rules, and situational ethical trade-offs, enabling LLMs to reason explicitly about multi-cultural norms.
Moral norms vary across geographic cultures, religious traditions, and temporal epochs; models require adaptive normative context parameters.
Context: Structured social rule-of-thumb generation with attribute classifications (morality, social judgment, agreement level).
View missionThe Pile: An 800GB Dataset of Diverse Text for Language Modeling
Stella Biderman · EleutherAI / Booz Allen HamiltonCo-authored the curation and statistical characterization of The Pile, an 825GB open-source pre-training dataset combining 22 diverse text subsets (arXiv, PubMed, GitHub, StackExchange), establishing the foundation for modern open foundation models.
Includes academic text requiring high domain literacy; copyright and licensing complexities in mixed web-scraped sub-components.
Context: FastText deduplication, exact substring filtering, perplexity benchmark analysis.
View missionWinoGrande: An Adversarial Winograd Schema Challenge at Scale
Dr. Yejin Choi · University of Washington / Allen Institute for AIAuthored WinoGrande, an adversarial benchmark of 44,000 pronoun resolution problems designed using AFLITE algorithmic bias-reduction to prevent models from exploiting superficial dataset artifacts, becoming a gold-standard benchmark for evaluating machine commonsense.
Frontier models now achieve high performance on static text pairs; evaluating dynamic situational commonsense requires multi-turn environmental grounding.
Context: AFLITE adversarial filtering over RoBERTa embeddings; standard inclusion in Open LLM Leaderboard and HELM.
View missionULMFiT: Universal Language Model Fine-tuning for Text Classification
Jeremy Howard · Answer.ai / fast.aiSeminal research paper introducing inductive transfer learning to natural language processing via 3-step pre-training, discriminative fine-tuning, and slanted triangular learning rates, outperforming prior custom architectures by orders of magnitude.
Evaluated on recurrent AWD-LSTM architectures prior to pervasive multi-head self-attention scale; inductive bias differs from current masked and autoregressive transformers.
Context: AWD-LSTM 3-layer language model pre-trained on WikiText-103; foundation for modern BERT/transformer transfer learning pipelines.
View mission8-Bit Optimizers via Block-wise Dynamic Quantization with Low-Precision States
Tim Dettmers · Allen Institute for AI (Ai2)A breakthrough algorithmic paper by Tim Dettmers introducing 8-bit Adam and low-precision optimizer states, reducing memory consumption of deep learning training states by 75% without compromising model convergence.
Custom CUDA block-level quantization; optimizer speedups are maximized on modern Tensor Core architectures.
Context: Benchmarked on language modeling, machine translation, and ImageNet classification with PyTorch.
View missionAbu Dhabi Investment Authority (ADIA): Empirical Domain-Specific AI Evaluation Benchmark & Methodology
Dr. Marcos Lopez de Prado · Abu Dhabi Investment Authority (ADIA)An empirical evaluation methodology developed by Dr. Marcos Lopez de Prado at Abu Dhabi Investment Authority (ADIA), establishing standardized performance metrics, domain-specific evaluation sets, and error taxonomy protocols.
Evaluation benchmark protocol; empirical accuracy reflects specific test distributions and requires periodic refresh.
Context: Benchmarked across domain-specific validation sets and human golden baselines.
View missionNatural Adversarial Examples and Out-of-Distribution Detection in Neural Networks
Dr. Dan Hendrycks · Center for AI SafetyA foundational safety study by Dr. Dan Hendrycks introducing the ImageNet-A and ImageNet-O benchmarks, exposing fundamental vulnerabilities where vision models fail catastrophically on naturally occurring adversarial examples.
Vision classification benchmark; physical world adversarial perturbations present additional environmental dynamics.
Context: Evaluated ResNet, DenseNet, and early vision-transformer architectures under natural distribution shifts.
View missionOutsider Oversight: Designing Independent External Audits for Deployed AI
Inioluwa Deborah Raji · Mozilla Foundation / UC BerkeleyAn influential empirical paper by Deborah Raji examining the methodology and systemic impact of third-party external audits on proprietary machine learning systems deployed in criminal justice and hiring.
External audit methodology; access to internal training datasets is often obstructed by commercial trade secrecy.
Context: Evaluates algorithmic accountability across automated facial recognition and predictive risk scoring algorithms.
View missionDEF CON 31 Generative Red Team Challenge: Community Vulnerability Discovery
Dr. Rumman Chowdhury · Humane IntelligenceThe largest public AI red-teaming exercise in history, organized by Dr. Rumman Chowdhury and Humane Intelligence, evaluating frontier LLMs across thousands of independent hackers for demographic bias, hallucination, and prompt injection.
Cross-sectional snapshot of model behaviors under community stress; commercial safety alignment shifts rapidly with model updates.
Context: Evaluated models from OpenAI, Google, Anthropic, Meta, Hugging Face, Cohere, and Stability AI.
View missionJohns Hopkins University / Bayesian Health: Domain-Specific AI Evaluation Benchmark & Methodology
Dr. Suchi Saria · Johns Hopkins University / Bayesian HealthAn empirical evaluation methodology developed by Dr. Suchi Saria at Johns Hopkins University / Bayesian Health, establishing standardized performance metrics, domain-specific evaluation sets, and error taxonomy protocols.
Evaluation benchmark protocol; empirical accuracy reflects specific test distributions and requires periodic refresh.
Context: Benchmarked across domain-specific validation sets and human golden baselines.
View mission