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 3 months ago
Alternatives and similar repositories for Superposition-Transformer:
Users that are interested in Superposition-Transformer are comparing it to the libraries listed below
- Control LLM☆14Updated 2 weeks ago
- Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆15Updated last month
- [ICLR 2025] Weighted-Reward Preference Optimization for Implicit Model Fusion☆13Updated last month
- [ICML 2024] Official Repository for the paper "Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models"☆9Updated 9 months ago
- Official implementation of ECCV24 paper: POA☆24Updated 8 months ago
- This repo contains code for the paper "Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM"☆13Updated 3 weeks ago
- Code for "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"☆14Updated 2 weeks ago
- This repository contains the code for AdaCLIP, a computation and latency-aware system for pragmatic multimodal video retrieval.☆10Updated 10 months ago
- LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models☆17Updated 3 weeks ago
- [CVPR] MergeVQ: A Unified Framework for Visual Generation and Representation with Token Merging and Quantization☆21Updated 3 weeks ago
- The official code for MedAgent_Pro☆19Updated this week
- ☆14Updated last month
- Official PyTorch Implementation for Task Vectors are Cross-Modal☆22Updated 4 months ago
- Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)☆20Updated 8 months ago
- ☆15Updated 2 weeks ago
- Official Repository of Are Your LLMs Capable of Stable Reasoning?☆25Updated last month
- Do Vision and Language Models Share Concepts? A Vector Space Alignment Study☆14Updated 5 months ago
- The official code of "PixelWorld: Towards Perceiving Everything as Pixels"☆13Updated 2 months ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆25Updated 5 months ago
- [NAACL 2025] Representing Rule-based Chatbots with Transformers☆20Updated 2 months ago
- [WACV 2025] Official implementation of "Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation" by Xiwen Wei, Guihong L…☆35Updated 5 months ago
- A benchmark dataset and simple code examples for measuring the perception and reasoning of multi-sensor Vision Language models.☆18Updated 3 months ago
- The official implementation of ICLR 2025 paper "Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models".☆13Updated this week
- [CVPR'25] Official repository for "Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Eva…☆11Updated last week
- Official implementation of Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More☆17Updated 2 months ago
- ☆20Updated 4 months ago
- ☆16Updated 9 months ago
- A list of language models with permissive licenses such as MIT or Apache 2.0☆24Updated last month
- ☆17Updated 3 months ago
- official implementation of "CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusi…☆16Updated 7 months ago