Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models Paper • 2504.01137 • Published 17 days ago • 20
Scaling Analysis of Interleaved Speech-Text Language Models Paper • 2504.02398 • Published 15 days ago • 27
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources Paper • 2504.00595 • Published 17 days ago • 34 • 7
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources Paper • 2504.00595 • Published 17 days ago • 34
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model Paper • 2503.24290 • Published 18 days ago • 61
Single Image Iterative Subject-driven Generation and Editing Paper • 2503.16025 • Published 29 days ago • 13
AudioX: Diffusion Transformer for Anything-to-Audio Generation Paper • 2503.10522 • Published Mar 13 • 22
RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling Paper • 2503.09601 • Published Mar 12 • 14
Slamming: Training a Speech Language Model on One GPU in a Day Paper • 2502.15814 • Published Feb 19 • 69
Slam Collection All resources for SpeechLMs from "Slamming: Training a Speech Language Model on One GPU in a Day". We provide tokeniser, lm, and datasets • 6 items • Updated Feb 25 • 13
Slamming: Training a Speech Language Model on One GPU in a Day Paper • 2502.15814 • Published Feb 19 • 69