paper-with-me

홈 › Papers

tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

2026-02-23 · Chen Wang, Hao Tan, Wang Yifan, Zhiqin Chen, Yuheng Liu, Kalyan Sunkavalli, Sai Bi, Lingjie Liu, Yiwei Hu arxiv

We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability. Our framework efficiently compresses multiple image observations into the fast weights of the TTT layer, forming an implicit 3D representation in the latent space that can be decoded into various explicit formats, such as Gaussian Splats (GS) for downstream applications. The online learning variant of our model supports progressive 3D reconstruction and refinement from streaming observations. We demonstrate that pretraining on novel view synthesis tasks effectively transfers to explicit 3D modeling, resulting in improved reconstruction quality and faster convergence. Extensive experiments show that our method achieves superior performance in feedforward 3D Gaussian reconstruction compared to state-of-the-art approaches on both objects and scenes.

📄 PDF Abstract BibTeX arXiv:2602.20160

Code (0)

등록된 구현이 없습니다.

Tasks

Novel View Synthesis3D Reconstruction

Similar Papers 제목 키워드 기반

EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering

2026-06-05 · Xiaopeng Yuan, Zebin Wang, Suwen Wang, Zongxin Yang 외 arxiv

Long-context question answering (QA) remains challenging for smaller language models even when answer-bearing evidence is already present in the input. Existing within-context retrieval methods localize and expose candid…

Test-time AdaptationQuestion Answering

End-to-End Test-Time Training for Long Context

2025-12-29 · Arnuv Tandon, Karan Dalal, Xinhao Li, Daniel Koceja 외 arxiv

We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard architecture -- a Transformer with sliding-window attention. …

Continual Learning

PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning

2025-07-08 · Zeming Chen, Angelika Romanou, Gail Weiss, Antoine Bosselut arxiv

Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. Previous research shows that using test-time learning to encode context directly into model parameters can e…

Self-Guided Test-Time Training for Long-Context LLMs

2026-07-10 · Xinyu Zhu, Zhe Xu, Xiaohan Wei, Yunchen Pu 외 arxiv

Long-context processing has become increasingly important for large language models (LLMs), but simply extending the context window does not guarantee effective utilization of long inputs. As input length grows, accuracy…

Understanding the Role of Training Data in Test-Time Scaling

2025-10-04 · Adel Javanmard, Baharan Mirzasoleiman, Vahab Mirrokni arxiv

Test-time scaling improves the reasoning capabilities of large language models (LLMs) by allocating extra compute to generate longer Chains-of-Thoughts (CoTs). This enables models to tackle more complex problem by breaki…