Tagged articles

LIBERO

2 articles · Page 1 of 1

Aug 3, 2026 · Artificial Intelligence

Does VLA Action Prediction Need an LLM? TurboVLA Achieves 32 Hz with 0.2 B Params on RTX 4090

TurboVLA, a real‑time vision‑language‑action model from Huazhong University of Science and Technology and Huawei, bypasses the large language model bottleneck by directly fusing visual and language features, achieving 32 Hz online action prediction on a single RTX 4090 with only 0.2 B parameters and 0.9 GB VRAM, while maintaining high success rates across LIBERO, RoboTwin 2.0, and real‑robot tasks.

LIBEROLLMRTX 4090

0 likes · 11 min read

Does VLA Action Prediction Need an LLM? TurboVLA Achieves 32 Hz with 0.2 B Params on RTX 4090

Machine Heart

Apr 18, 2026 · Artificial Intelligence

Eliminating ‘Think‑Then‑Act’ Stalls: StreamingVLA Boosts VLA Speed by 2.4×

StreamingVLA introduces action‑flow matching and adaptive early observation to parallelize generation, execution, and perception in vision‑language‑action models, cutting per‑action latency from 49.9 ms to 31.6 ms, reducing stall time 6.5‑fold, and achieving up to 2.4× end‑to‑end speedup in LIBERO benchmarks and real‑world robot tests.

LIBEROStreamingVLAVision-Language-Action

0 likes · 13 min read

Eliminating ‘Think‑Then‑Act’ Stalls: StreamingVLA Boosts VLA Speed by 2.4×

LIBERO

Does VLA Action Prediction Need an LLM? TurboVLA Achieves 32 Hz with 0.2 B Params on RTX 4090

Eliminating ‘Think‑Then‑Act’ Stalls: StreamingVLA Boosts VLA Speed by 2.4×

Does VLA Action Prediction Need an LLM? TurboVLA Achieves 32 Hz with 0.2 B Params on RTX 4090