Related papers: Rethinking the State Update Gate for Long-Sequence…

View-conditioned 3D generators such as SAM 3D, TRELLIS and Hunyuan3D produce high-quality object reconstructions from a single view, but real-world visual observation often arrives as long monocular streams. Naively applying these…

Recurrent neural networks can be difficult to train on long sequence data due to the well-known vanishing gradient problem. Some architectures incorporate methods to reduce RNN state updates, therefore allowing the network to preserve…

We introduce the State Stream Transformer (SST), a novel LLM architecture that reveals emergent reasoning behaviours and capabilities latent in pretrained weights through addressing a fundamental limitation in traditional transformer…

Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the…

Anomaly detection in videos is a significant yet challenging problem. Previous approaches based on deep neural networks employ either reconstruction-based or prediction-based approaches. Nevertheless, existing reconstruction-based methods…

Reconstruction is a fundamental task in 3D vision and a fundamental capability for spatial intelligence. Particularly, streaming 3D reconstruction is central to real-time spatial perception, yet existing recurrent online models often suffer…

Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has…

Streaming 3D reconstruction demands long-horizon state updates under strict latency constraints, yet stateful recurrent models often suffer from geometric drift as errors accumulate over time. We revisit this problem from a Grassmannian…

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…

Dynamic streams from news feeds, social media, sensor networks, and financial markets challenge static RAG frameworks. Full-scale indices incur high memory costs; periodic rebuilds introduce latency that undermines data freshness; naive…

Recent feed-forward geometry foundation models have demonstrated impressive generalization by recovering depth and poses in a single forward pass. However, these models are typically constrained by a global coordinate frame assumption. This…

Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global attention prevents long context application. StreamVGGT enables streaming with causal…

Streaming visual transformers like StreamVGGT achieve strong 3D perception but suffer from unbounded growth of key value (KV) memory, which limits scalability. We propose a training-free, inference-time token eviction policy that bounds…

Although multi-scale concepts have recently proven useful for recurrent network architectures in the field of optical flow and stereo, they have not been considered for image-based scene flow so far. Hence, based on a single-scale recurrent…

Dense 3D reconstruction from continuous image streams requires both accurate geometric aggregation and stable long-term memory management. Recent feed-forward reconstruction frameworks integrate observations through persistent memory…

Recurrent Neural Networks (RNNs) play a major role in the field of sequential learning, and have outperformed traditional algorithms on many benchmarks. Training deep RNNs still remains a challenge, and most of the state-of-the-art models…

Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal variants of VGGT address this challenge through a key-value (KV) cache mechanism, the cache grows…

Traditional SLAM systems, which rely on bundle adjustment, struggle with highly dynamic scenes commonly found in casual videos. Such videos entangle the motion of dynamic elements, undermining the assumption of static environments required…

A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors. We hypothesize that many of…

We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To…