Related papers: SSR: A Training-Free Approach for Streaming 3D Rec…

Streaming recurrent models enable efficient 3D reconstruction by maintaining persistent state representations. However, they suffer from catastrophic forgetting over long sequences due to balancing historical information with new…

Streaming 3D reconstruction maintains a persistent latent state that is updated online from incoming frames, enabling constant-memory inference. A key failure mode is the state update rule: aggressive overwrites forget useful history, while…

In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes agents notoriously sample-inefficient, since…

Many deployed learning systems must update models on streaming data under memory constraints. The default strategy, sequential fine-tuning on each new phase, is architecture-agnostic but often suffers catastrophic forgetting when later…

Streaming feed-forward 3D reconstruction enables real-time joint estimation of scene geometry and camera poses from RGB images. However, without explicit dynamic reasoning, streaming models can be affected by moving objects, causing…

We consider the problem of estimating a linear time-invariant (LTI) dynamical system from a single trajectory via streaming algorithms, which is encountered in several applications including reinforcement learning (RL) and time-series…

Streaming 3D perception is well suited to robotics and augmented reality, where long visual streams must be processed efficiently and consistently. Recent recurrent models offer a promising solution by maintaining fixed-size states and…

We present an explicit-grid based method for efficiently reconstructing streaming radiance fields for novel view synthesis of real world dynamic scenes. Instead of training a single model that combines all the frames, we formulate the…

Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. As a result, SSL holds the promise to learn representations from data in-the-wild, i.e., without the…

State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. However, their evolving internal states pose challenges in adapting them under Continual…

Recent feed-forward reconstruction models like VGGT and $\pi^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming…

A Recurrent Neural Network (RNN) for Video Super Resolution (VSR) is generally trained with randomly clipped and cropped short videos extracted from original training videos due to various challenges in learning RNNs. However, since this…

We address the problem of learning reusable state representations from streaming high-dimensional observations. This is important for areas like Reinforcement Learning (RL), which yields non-stationary data distributions during training. We…

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

We present Online3R, a new sequential reconstruction framework that is capable of adapting to new scenes through online learning, effectively resolving inconsistency issues. Specifically, we introduce a set of learnable lightweight visual…

We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global…

Online monocular 3D reconstruction enables dense scene recovery from streaming video but remains fundamentally limited by the stability-adaptation dilemma: the reconstruction model must rapidly incorporate novel viewpoints while preserving…

Reinforcement learning (RL) is rapidly reaching and surpassing human-level control capabilities. However, state-of-the-art RL algorithms often require timesteps and reaction times significantly faster than human capabilities, which is…

Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…

Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world…