-
ContextCite: Attributing Model Generation to Context
Paper • 2409.00729 • Published • 13 -
Residual Stream Analysis with Multi-Layer SAEs
Paper • 2409.04185 • Published -
Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models
Paper • 2408.06663 • Published • 15 -
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
Paper • 2408.05147 • Published • 36
Collections
Discover the best community collections!
Collections including paper arxiv:2404.03592
-
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 83 -
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Paper • 2404.10667 • Published • 15 -
Instruction-tuned Language Models are Better Knowledge Learners
Paper • 2402.12847 • Published • 24 -
DoRA: Weight-Decomposed Low-Rank Adaptation
Paper • 2402.09353 • Published • 24
-
The Unreasonable Ineffectiveness of the Deeper Layers
Paper • 2403.17887 • Published • 77 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 103 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 86 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 59
-
Jamba: A Hybrid Transformer-Mamba Language Model
Paper • 2403.19887 • Published • 103 -
sDPO: Don't Use Your Data All at Once
Paper • 2403.19270 • Published • 38 -
ViTAR: Vision Transformer with Any Resolution
Paper • 2403.18361 • Published • 51 -
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Paper • 2403.18814 • Published • 44