Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Paper
•
2401.01335
•
Published
•
68
Interesting new techniques
-
-
Lumiere: A Space-Time Diffusion Model for Video Generation
Paper • 2401.12945 • Published • 86 -
Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU
Paper • 2403.06504 • Published • 55 -
Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs
Paper • 2403.20041 • Published • 35 -
OmniGen: Unified Image Generation
Paper • 2409.11340 • Published • 116 -
Kolmogorov-Arnold Transformer
Paper • 2409.10594 • Published • 46 -
Multimodal Latent Language Modeling with Next-Token Diffusion
Paper • 2412.08635 • Published • 46 -
A3: Android Agent Arena for Mobile GUI Agents
Paper • 2501.01149 • Published • 22 -
Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
Paper • 2501.03218 • Published • 37 -
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
Paper • 2503.05179 • Published • 46 -
Modifying Large Language Model Post-Training for Diverse Creative Writing
Paper • 2503.17126 • Published • 37 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 120 -
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
Paper • 2504.17432 • Published • 39 -
Parallel Scaling Law for Language Models
Paper • 2505.10475 • Published • 82 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 36 -
Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions
Paper • 2505.11614 • Published -
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
Paper • 2505.15045 • Published • 55 -
Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models
Paper • 2504.05258 • Published -
LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
Paper • 2506.00411 • Published • 30 -
Aligning Latent Spaces with Flow Priors
Paper • 2506.05240 • Published • 25 -
Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs
Paper • 2506.05629 • Published • 35 -
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
Paper • 2506.20452 • Published • 18 -
Lizard: An Efficient Linearization Framework for Large Language Models
Paper • 2507.09025 • Published • 10