BenChaliah / Superposition-Transformer
a novel architecture that leverages Autoencoders to superimpose the hidden representations of a base model and a fine-tuned model within a shared parameter space. Using B-spline-based blending coefficients and autoencoders that adaptively reconstruct the original hidden states based on the input data distribution.
☆42Updated 2 months ago
Alternatives and similar repositories for Superposition-Transformer:
Users that are interested in Superposition-Transformer are comparing it to the libraries listed below
- The official code for MedAgent_Pro☆13Updated this week
- [ICLR 2025] Weighted-Reward Preference Optimization for Implicit Model Fusion☆12Updated 2 weeks ago
- Control LLM☆13Updated this week
- Official implementation of ECCV24 paper: POA☆24Updated 7 months ago
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆10Updated this week
- LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models☆17Updated this week
- Do Vision and Language Models Share Concepts? A Vector Space Alignment Study☆14Updated 4 months ago
- ☆16Updated 3 months ago
- This repo contains code for the paper "Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM"☆13Updated this week
- Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆14Updated 3 weeks ago
- Knowledge Unlearning for Large Language Models☆22Updated 3 weeks ago
- Official repository of DialSim☆16Updated this week
- [WACV 2025] Official implementation of "Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation" by Xiwen Wei, Guihong L…☆35Updated 4 months ago
- [arxiv:2412.04905] DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling☆13Updated 3 months ago
- [Arxiv] Implicit Reasoning in Transformers is Reasoning through Shortcuts☆12Updated 3 weeks ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆19Updated 3 months ago
- This is a simple torch implementation of the high performance Multi-Query Attention☆16Updated last year
- [ICML 2024] Official Repository for the paper "Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models"☆9Updated 8 months ago
- PyTorch code for "ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning"☆19Updated 5 months ago
- The official implementation of Preference Data Reward-Augmentation.☆17Updated 5 months ago
- Code, results and other artifacts from the paper introducing the WildChat-50m dataset and the Re-Wild model family.☆29Updated 2 months ago
- ☆20Updated 3 months ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆24Updated 4 months ago
- ☆18Updated 8 months ago
- ☆14Updated 6 months ago
- The official implementation of ICLR 2025 paper "Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models".☆13Updated last week
- CS194-196 Course Project☆13Updated last month
- Remasking Discrete Diffusion Models with Inference-Time Scaling☆16Updated 3 weeks ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆28Updated 2 weeks ago
- Efficient Scaling laws and collaborative pretraining.☆16Updated 2 months ago