Tag
The paper proposes a robust dual-model collaborative random vector functional link network (KRPRVFL) to improve classification accuracy in the presence of noisy labels and outliers, leveraging kernel risk-sensitive mean p-power criterion and collaborative learning.
Introduces Collate, a training framework for collaborative neural network learning that handles heterogeneous edge devices with latency constraints, achieving accuracy improvements with minimal overhead.
MOSAIC is a novel framework that uses a frozen LLM to generate semantic embeddings and hierarchical prediction prompts for knowledge tracing, achieving state-of-the-art results on multiple benchmarks.
Jim Fan announced that the team launched ENPIRE, bringing AutoResearch into the physical world for the first time, equipping 8 Codex agents with robots, GPUs, and tokens, enabling them to autonomously learn and collaborate on real hardware to complete tasks.
OpenAI presents a machine teaching approach where a teacher neural network learns to select the most illustrative examples to teach a student network to recognize concepts, producing interpretable results by grounding examples in human-understandable properties rather than arbitrary feature encodings.