Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Paper
•
2401.08417
•
Published
•
37
Papers-to-read
-
-
PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models
Paper • 2401.05252 • Published • 50 -
BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
Paper • 2402.04291 • Published • 51 -
FiT: Flexible Vision Transformer for Diffusion Model
Paper • 2402.12376 • Published • 49 -
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Paper • 2402.14083 • Published • 49 -
Synth^2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings
Paper • 2403.07750 • Published • 24 -
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
Paper • 2403.13372 • Published • 87 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 15 -
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 30