paper-with-me

Papers

NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving

2026-03-06 · Kai Luo, Xu Wang, Rui Fan, Kailun Yang arxiv

Generalizing across unknown targets is critical for open-world perception, yet existing 3D Multi-Object Tracking (3D MOT) pipelines remain limited by closed-set assumptions and ``semantic-blind'' heuristics. To address this, we propose Next-step Open-Vocabulary Autoregression (NOVA), an autoregressive association formulation that shifts the data association stage from fragmented distance-based matching toward trajectory-conditioned spatio-semantic modeling. NOVA reformulates 3D trajectories as structured spatio-temporal semantic sequences, enabling the simultaneous encoding of physical motion continuity and deep linguistic priors. By leveraging the autoregressive capabilities of Large Language Models (LLMs), we transform the tracking task into a principled process of next-step sequence completion. This mechanism allows the model to explicitly utilize the hierarchical structure of language space to resolve fine-grained semantic ambiguities and maintain identity consistency across complex long-range sequences through high-level commonsense reasoning. Extensive experiments on nuScenes, V2X-Seq-SPD, and KITTI demonstrate the superior performance of NOVA. Notably, on the nuScenes dataset, NOVA achieves an AMOTA of 22.41% for Novel categories, yielding a significant 20.21% absolute improvement over the baseline. These gains are realized through a compact 0.5B autoregressive model. Code will be available at https://github.com/xifen523/NOVA.

📄 PDF Abstract BibTeX arXiv:2603.06254

Code (0)

등록된 구현이 없습니다.

Tasks

3D Multi-Object TrackingAutonomous Driving

Similar Papers 제목 키워드 기반

FAIR Metadata: A Community-driven Vocabulary Application

2021-11-06 · Christopher B. Rauch, Mat Kelly, John A. Kunze, Jane Greenberg

FAIR metadata is critical to supporting FAIR data overall. Transparency, community engagement, and flexibility are key aspects of FAIR that apply to metadata. This paper presents YAMZ (Yet Another Metadata Zoo), a commun…

Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models

2023-12-11 · Haoran Wei, Lingyu Kong, Jinyue Chen, Liang Zhao 외

Modern Large Vision-Language Models (LVLMs) enjoy the same vision vocabulary -- CLIP, which can cover most common vision tasks. However, for some special vision task that needs dense and fine-grained vision perception, e…

Chart UnderstandingDecoderOptical Character Recognition (OCR)Visual Question Answering

Projected Autoregression: Autoregressive Language Generation in Continuous State Space

2026-01-08 · Oshri Naparstek arxiv

Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable aut…

Continuous Control

Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

2024-09-06 · Zhuoyan Luo, Fengyuan Shi, Yixiao Ge, Yujiu Yang 외

We present Open-MAGVIT2, a family of auto-regressive image generation models ranging from 300M to 1.5B. The Open-MAGVIT2 project produces an open-source replication of Google's MAGVIT-v2 tokenizer, a tokenizer with a sup…

Image GenerationImage Reconstruction

Renovating Names in Open-Vocabulary Segmentation Benchmarks

2024-03-14 · Haiwen Huang, Songyou Peng, Dan Zhang, Andreas Geiger

Names are essential to both human cognition and vision-language models. Open-vocabulary models utilize class names as text prompts to generalize to categories unseen during training. However, the precision of these names…

Segmentation