BenChaliah / Superposition-TransformerLinks
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.
☆43Updated 5 months ago
Alternatives and similar repositories for Superposition-Transformer
Users that are interested in Superposition-Transformer are comparing it to the libraries listed below
Sorting:
- ☆12Updated 3 weeks ago
- Repo of FocusedAD☆12Updated 2 months ago
- Control LLM☆16Updated 2 months ago
- [ACM MM 2023] Official PyTorch implementation of "Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Reco…☆11Updated last year
- [ICML 2024] Official Repository for the paper "Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models"☆10Updated 11 months ago
- Code for "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"☆15Updated 2 months ago
- Official Code for "Rethinking Diffusion Model in High Dimension"☆15Updated last month
- Interface Design for Self-Supervised Speech Models, Accepted to Interspeech2024☆15Updated 7 months ago
- Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)☆22Updated 10 months ago
- The open source implementation of the cross attention mechanism from the paper: "JOINTLY TRAINING LARGE AUTOREGRESSIVE MULTIMODAL MODELS"☆30Updated last year
- ☆47Updated last month
- RewardAnything: Generalizable Principle-Following Reward Models☆22Updated 2 weeks ago
- ☆14Updated 6 months ago
- AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation☆15Updated 6 months ago
- An official repo for the paper "Adapting Language-Audio Models as Few-Shot Audio Learners"☆31Updated 2 years ago
- Do Vision and Language Models Share Concepts? A Vector Space Alignment Study☆15Updated 7 months ago
- Official Repository of IJCAI 2024 Paper: "BATON: Aligning Text-to-Audio Model with Human Preference Feedback"☆28Updated 3 months ago
- [NCMMSC'2024] Emotion-Aware Prosodic Phrasing for Expressive Text-to-Speech☆22Updated 10 months ago
- The official repo for LIFT: Language-Image Alignment with Fixed Text Encoders☆18Updated 2 weeks ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆14Updated last year
- Code for paper "Table-R1: Inference-Time Scaling for Table Reasoning"☆18Updated 3 weeks ago
- ☆14Updated 11 months ago
- ☆13Updated last year
- Towards Fine-grained Audio Captioning with Multimodal Contextual Cues☆68Updated 3 weeks ago
- Repository for "TESS-2: A Large-Scale, Generalist Diffusion Language Model"☆36Updated 4 months ago
- UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model☆22Updated 10 months ago
- Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆45Updated 3 weeks ago
- Collection of works for evaluating (and analyzing) large audio-language models (LALMs)☆28Updated last week
- Official PyTorch implementation for "MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens…☆31Updated 2 weeks ago
- ☆11Updated 4 months ago