Why Fine-Tuning Encourages Hallucinations and How to Fix It
Paper • 2604.15574 • Published • 23
toread
-
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper • 2604.24763 • Published • 68 -
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Paper • 2604.24819 • Published • 86 -
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 98 -
Large Language Models Explore by Latent Distilling
Paper • 2604.24927 • Published • 72 -
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
Paper • 2604.26779 • Published • 13