Presents breakthrough compression technique that inverts traditional quality-loss relationship in model quantization
Researchers introduce -Aware Healing, producing a 4-bit compressed model that outperforms its original full-precision version on most benchmarks.
Researchers conducted a layer-wise MBTI personality analysis of quantized LLMs, finding personality is emergent and quantization-sensitive rather than static.
A research paper presents an autonomous AI agent that designed a machine learning algorithm for cell-edge power control in wireless networks, achieving strong performance with minimal human input.
Researchers developed PlanSightRAG, a visual-first multimodal RAG system that achieves 91.47% recall on zero-shot retrieval for civil engineering plan compliance checking.
Researchers apply sparse autoencoders to interpret latent representations in a neutrino foundation model, discovering underutilized physical concepts that improve angular resolution from 20.2° to 3.2°.
Google researchers present an autonomous AI system that synthesizes multimodal geospatial data and outperforms expert baselines across health, disaster risk, and food security prediction tasks.
