ShadeAlsha / IConLinks
ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"
☆96Updated this week
Alternatives and similar repositories for ICon
Users that are interested in ICon are comparing it to the libraries listed below
Sorting:
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆40Updated 8 months ago
- [ICLR 2025] Large (Vision) Language Models are Unsupervised In-Context Learners☆13Updated 2 weeks ago
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.☆78Updated last month
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆140Updated last month
- An implementation of PSGD Kron second-order optimizer for PyTorch☆91Updated 2 months ago
- Implementation of Mind Evolution, Evolving Deeper LLM Thinking, from Deepmind☆53Updated 3 weeks ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 6 months ago
- ☆31Updated last year
- Conference schedule, top papers, and analysis of the data for NeurIPS 2023!☆119Updated last year
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [to appear at ICLR 2025]☆19Updated last month
- Esoteric Language Models☆77Updated last week
- A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.☆93Updated 6 months ago
- Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.☆103Updated 2 months ago
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆127Updated 3 weeks ago
- Code for ExploreTom☆84Updated 6 months ago
- Getting crystal-like representations with harmonic loss☆190Updated 2 months ago
- ☆55Updated 7 months ago
- ☆79Updated 10 months ago
- Python Library to evaluate VLM models' robustness across diverse benchmarks☆208Updated last week
- ☆74Updated 8 months ago
- ☆70Updated 9 months ago
- PyTorch library for Active Fine-Tuning☆80Updated 4 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆241Updated 2 months ago
- ☆81Updated last year
- open source alpha evolve☆64Updated last month
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated 10 months ago
- Implementations of attention with the softpick function, naive and FlashAttention-2☆79Updated last month
- An AI benchmark for creative, human-like problem solving using Sudoku variants☆70Updated last month
- Official Code for Paper: Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation☆80Updated 2 weeks ago
- Generative Modeling with Bayesian Sample Inference☆22Updated last month