About
Research & Development
ShishuLM: A New Design for Efficient Small Language Models
TLDR: ShishuLM is a novel language model architecture that significantly reduces memory and latency in Small Language Models (SLMs) by employing a hybrid decoder-MLP...
Research & Development
GenCellAgent: A New Approach to Cellular Image Segmentation Without Retraining
TLDR: GenCellAgent is a training-free, multi-agent AI framework that automates and improves cellular image segmentation. It intelligently selects tools, adapts to new imaging conditions,...
Research & Development
Decoding Finetuned LLMs: How Narrow Training Leaves Clear Traces in AI’s Inner Workings
TLDR: A new research paper demonstrates that finetuning Large Language Models (LLMs) on narrow domains leaves strong, readable biases in their internal activations. Using...
Research & Development
Understanding How AI Agents Collaborate: A Deep Dive into Communication Trade-offs
TLDR: This research paper introduces a theoretical framework to analyze multi-agent AI systems, focusing on how communication impacts their ability to solve complex problems....
Research & Development
MAFA: JP Morgan Chase’s Multi-Agent AI System for Smarter Annotation
TLDR: MAFA (Multi-Agent Framework for Annotation) is a production-deployed AI system by JP Morgan Chase that automates and enhances enterprise-scale data annotation. It uses...
Research & Development
Optimizing Multi-stage Reasoning in Small Language Models with LiteStage
TLDR: LiteStage is a new framework that speeds up multi-stage reasoning in small language models by intelligently skipping layers and stopping redundant token generation...