BitTP applies weight-only 1.58-bit quantization to LLM trajectory predictors, claiming improved ADE/FDE over BF16 baseline with reduced resource demands on edge devices.
Spectra 1.1: Scaling laws and efficient inference for ternary language models.arXiv preprint arXiv:2506.23025, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BitTP: The Lightweight Trajectory Prediction Model with BitLLM for Edge-Devices
BitTP applies weight-only 1.58-bit quantization to LLM trajectory predictors, claiming improved ADE/FDE over BF16 baseline with reduced resource demands on edge devices.