Templated type-safe hashmap implementation in C using open addressing and linear probing for collision resolution.
An open addressing linear probing hash table, tuned for delete heavy workloads
Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN accuracy.
Blazingly fast hash table implementation in C using open addressing with linear probing and Robin Hood hashing for collision resolution.
Official PyTorch Implementation of Guarding Barlow Twins Against Overfitting with Mixed Samples
PyTorch Implementation of Attention Prompt Tuning: Parameter-Efficient Adaptation of Pre-Trained Models for Action Recognition
(Incomplete, In Continuation) Implementation of Data Structures like Stacks, Queues, etc. using C programming language
[arXiv] "Uncovering the Hidden Cost of Model Compression" by Diganta Misra, Agam Goyal, Bharat Runwal, and Pin-Yu Chen
Exploring and interpreting pretrained deep neural networks.
Train a JEPA world model on a set of pre-collected trajectories from an environment involving an agent in two rooms.
Official codebase for "Siamese Prototypical Contrastive Learning"
A repository to test the Platonic Representation Hypothesis (Isola et al. 2024) on the Tic-Tac-Toe mini-world
A framework to compute threshold sensitivity of deep networks to visual stimuli.
Resolves hash table collisions using linear probing, quadratic probing, and linear hashing. All data structures implemented from scratch. Optimized for efficient time and space complexity. Written in C++.
Your one-stop GitHub repo for competitive coding and data structures! 🤖 Curated notes, practice problems, and real-world applications. Sharpen your skills and ace those interviews! 💻🔥
Exploration and Comparison of Transformers for Image Classification.
Integer-keyed hash map that preserves insertion order: compact dictionary design, Fibonacci hashing, 64-bit keys and values on every build, and lookups several times faster than PureBasic's built-in Map.
LinearMap is a minimalistic, high-performance hash map built around open addressing with linear probing. Instead of relying on buckets, used by std::unordered_map, it uses a fully contiguous memory layout to squeeze out every bit of performance modern CPUs can offer.
Mechanistic interpretability of code models through probing, perturbations, and causal interventions
To associate your repository with the linear-probing topic, visit your repo's landing page and select "manage topics."