Enhancing Language Model Reliability in Instruction-Following
Explore how nuance-oriented reliability impacts language model performance and learn about new metrics and tools to improve instruction-following accuracy.
INFORM-CT: AI for Incidental Findings in Abdominal CT Scans
Discover INFORM-CT, an AI framework integrating LLMs and VLMs to automate incidental findings detection and reporting in abdominal CT scans.
Vec-LUT: Fast Ultra-Low-Bit LLM Inference on Edge Devices
Discover Vec-LUT, a vector table lookup method boosting ultra-low-bit LLM inference speed up to 4.2x on edge devices with optimized memory usage.
Red Teaming Large Reasoning Models for Trustworthiness
Explore RT-LRM, a benchmark to evaluate the safety, truthfulness, and efficiency of Large Reasoning Models in AI development.
BINDER: Adaptive Mobile Manipulation with Open-Vocab Commands
Discover BINDER, a dual-module system enabling robots to adapt instantly to dynamic environments using open-vocabulary commands for mobile manipulation.