-
Iterative Reasoning Preference Optimization
Paper • 2404.19733 • Published • 46 -
Better & Faster Large Language Models via Multi-token Prediction
Paper • 2404.19737 • Published • 73 -
ORPO: Monolithic Preference Optimization without Reference Model
Paper • 2403.07691 • Published • 59 -
KAN: Kolmogorov-Arnold Networks
Paper • 2404.19756 • Published • 108
Collections
Discover the best community collections!
Collections including paper arxiv:2405.09673
-
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 182 -
Flora: Low-Rank Adapters Are Secretly Gradient Compressors
Paper • 2402.03293 • Published • 4 -
PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation
Paper • 2401.11316 • Published • 1 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 45
-
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Paper • 2403.09611 • Published • 123 -
Evolutionary Optimization of Model Merging Recipes
Paper • 2403.13187 • Published • 49 -
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
Paper • 2402.03766 • Published • 12 -
LLM Agent Operating System
Paper • 2403.16971 • Published • 64
-
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Paper • 2403.08763 • Published • 48 -
Jamba: A Hybrid Transformer-Mamba Language Model
Paper • 2403.19887 • Published • 103 -
Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs
Paper • 2403.20041 • Published • 34 -
Advancing LLM Reasoning Generalists with Preference Trees
Paper • 2404.02078 • Published • 43
-
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Paper • 2402.14083 • Published • 43 -
Linear Transformers are Versatile In-Context Learners
Paper • 2402.14180 • Published • 6 -
Training-Free Long-Context Scaling of Large Language Models
Paper • 2402.17463 • Published • 19 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 590
-
BitDelta: Your Fine-Tune May Only Be Worth One Bit
Paper • 2402.10193 • Published • 17 -
StructLM: Towards Building Generalist Models for Structured Knowledge Grounding
Paper • 2402.16671 • Published • 26 -
LoRA Learns Less and Forgets Less
Paper • 2405.09673 • Published • 86 -
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
Paper • 2405.17428 • Published • 16
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 25 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 12 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 36 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 19
-
How to Train Data-Efficient LLMs
Paper • 2402.09668 • Published • 38 -
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
Paper • 2403.15042 • Published • 24 -
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Paper • 2403.03194 • Published • 12 -
Orca-Math: Unlocking the potential of SLMs in Grade School Math
Paper • 2402.14830 • Published • 24
-
Can Large Language Models Understand Context?
Paper • 2402.00858 • Published • 21 -
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 78 -
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 140 -
SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity
Paper • 2401.17072 • Published • 25