Efficient Tool Use with Chain-of-Abstraction Reasoning
Paper
• 2401.17464 • Published
• 21
LLM
-
-
Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation
Paper • 2401.15688 • Published • 11 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 73 -
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
Paper • 2401.15071 • Published • 37 -
Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI
Paper • 2401.14019 • Published • 23 -
ChatQA: Building GPT-4 Level Conversational QA Models
Paper • 2401.10225 • Published • 36 -
Do Large Language Models Latently Perform Multi-Hop Reasoning?
Paper • 2402.16837 • Published • 29 -
Divide-or-Conquer? Which Part Should You Distill Your LLM?
Paper • 2402.15000 • Published • 23 -
Linear Transformers with Learnable Kernel Functions are Better In-Context Models
Paper • 2402.10644 • Published • 81 -
DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows
Paper • 2402.10379 • Published • 31 -
Chain-of-Thought Reasoning Without Prompting
Paper • 2402.10200 • Published • 109 -
Generative Representational Instruction Tuning
Paper • 2402.09906 • Published • 54 -
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Paper • 2402.03620 • Published • 117 -
Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
Paper • 2402.04248 • Published • 32 -
Rethinking Optimization and Architecture for Tiny Language Models
Paper • 2402.02791 • Published • 13 -
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 85 -
Can Large Language Models Understand Context?
Paper • 2402.00858 • Published • 24 -
Can large language models explore in-context?
Paper • 2403.15371 • Published • 33 -
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Paper • 2406.04271 • Published • 29 -
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
Paper • 2406.06563 • Published • 20 -
Instruction Pre-Training: Language Models are Supervised Multitask Learners
Paper • 2406.14491 • Published • 96 -
Unlocking Continual Learning Abilities in Language Models
Paper • 2406.17245 • Published • 30 -
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
Paper • 2406.15334 • Published • 9 -
A Closer Look into Mixture-of-Experts in Large Language Models
Paper • 2406.18219 • Published • 17 -
Characterizing Prompt Compression Methods for Long Context Inference
Paper • 2407.08892 • Published • 11 -
Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
Paper • 2407.18248 • Published • 33 -
jina-embeddings-v3: Multilingual Embeddings With Task LoRA
Paper • 2409.10173 • Published • 34