Skip to main content

🏢 Shanghai AI Lab

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy
·3847 words·19 mins· loading · loading
AI Generated 🤗 Daily Papers AI Applications Robotics 🏢 Shanghai AI Lab
Dita: Scales a diffusion transformer for generalist robot policies, enabling 10-shot learning in complex, real-world tasks.
$φ$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
·3341 words·16 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 Shanghai AI Lab
Φ-Decoding: Adaptive foresight sampling balances inference-time exploration and exploitation for better LLM reasoning.
Redundancy Principles for MLLMs Benchmarks
·4576 words·22 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 Shanghai AI Lab
This research proposes principles and a framework to tackle redundancy in MLLM benchmarks, enhancing efficiency and guiding future development.