TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 2 days ago • 122
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published 13 days ago • 137
The Signs Were Always There: Training-Free Concept Detection and Steering in Raw Transformer Dimensions Paper • 2606.12629 • Published 23 days ago • 2
LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning Paper • 2606.01336 • Published May 31 • 8
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published May 22 • 82
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196