About
Research & Development
AI Agents and Market Dynamics: Unpacking Collusion in LLM-Driven Auctions
TLDR: This research paper investigates the propensity of Large Language Model (LLM) agents to collude in simulated continuous double auction markets. It finds that...
Research & Development
EdgeLoRA: Boosting LLM Performance on Edge Devices
TLDR: EdgeLoRA is a new system that significantly improves the efficiency of serving Large Language Models (LLMs) with multiple fine-tuned adapters on resource-constrained edge...
Research & Development
Unveiling cRID: A New AI Framework for Enhanced Privacy in Person Re-Identification
TLDR: A new research paper introduces cRID, a cross-modal AI framework that combines Large Vision-Language Models and Graph Attention Networks to improve person re-identification...
Research & Development
AI Model Learns to Compose and Perform Classical Piano with Expressive Nuances
TLDR: This research introduces the Expressive Music Variational AutoEncoder (XMVAE), a novel AI model designed to generate classical piano performances from scratch. It uses...
Research & Development
Automating Data and AI Workflows with the Data Agent Architecture
TLDR: The research paper introduces the 'Data Agent,' a comprehensive architecture designed to autonomously orchestrate Data+AI ecosystems. By integrating large language models (LLMs), Data...
Research & Development
Efficient Image Creation: A New Approach to Autoregressive Models
TLDR: New research introduces LASADGen, an autoregressive image generator that uses a novel Linear Attention with Spatial-Aware Decay (LASAD) mechanism. This innovation overcomes the...