Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning
Research
Research News
New papers, breakthroughs and academic AI research
Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT
Research
PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation
Research
GeoPID: Decomposing and Steering Visual Information in Vision-Language Models
Research
Learning a Mixture of GFlowNets
Research
Mechanistic Interpretability of Atmospheric Rivers in GraphCast
Research
Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
Research
UniCounting: Instance-Aware Proposal Consolidation for Image-Query-Free Multi-Category Counting
Research
Preserving Unstable Modes Through Inverse Dynamics in JEPA World Models
Research
In With the Old: Enhancing 'Classical' Document Automation with Generative AI
Research
Stateless Language Agents: Scaling Long-Horizon Automated Research
Research
A Stevens's Power Law Check-up of GPT-5.5's Image-Based Visualization Reading
Research