multimodal benchmarks

6 papers

• Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
• Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
• Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
• Learning to Instruct for Visual Instruction Tuning
• NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
• Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions