arXiv Computer Vision
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 27
Supervising the Visible State: Separating Representation from View Selection in Streaming Video
arXiv:2610.34926v1 Announce Type: new Abstract: An action seen once and the same action seen three times receive the same action-recognition label, so that supervision does not require a model to cou...
Hugging Face Trending Papers
Oct 26
Supervising the Visible State: Separating Representation from View Selection in Streaming Video
An action seen once and the same action seen three times receive the same action-recognition label, so that supervision does not require a model to count. Answers shared across histories that differ i...
arXiv Computer Vision
Oct 1
Uruqi: Learning Spatial Cognition from Visual Experience
arXiv:2609.39195v1 Announce Type: new Abstract: Spatial intelligence requires maintaining a coherent understanding of the world as the embodied agent moves. Like humans, the agent must use its own mo...
arXiv Computer Vision
Aug 27
OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs
OVO‑S‑Bench is a fully human‑annotated benchmark designed to evaluate streaming spatial intelligence in multimodal large language models (MLLMs). It contains 1,680 questions derived from 348 source videos, each with a query timestamp and evidence interval, and tests models on four levels of abstraction: instantaneous egocentric perception, spatiotemporal context tracking, generative spatial reasoning, and allocentric spatial mapping. Across 38 MLLMs, Gemini‑3.1‑Pro scored 59.2 versus 92.2 for human experts, with allocentric spatial mapping identified as the main challenge, and the benchmark reveals that chain‑of‑thought reasoning can worsen spatial errors when not grounded in the stream.
arXiv AI
Oct 16
Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation
Anvil is a unified framework for embodied spatial intelligence that integrates data generation, training, and benchmarking. It introduces three components: Anvil-Gen, a heterogeneous data flywheel that generates and verifies cross‑stage consistency; Anvil-Ben, which provides scene‑aligned supervision and assessments to separate stage competence from error propagation; and Anvil‑MOPD, a 9B student model that distills spatial knowledge from specialist teachers using semantic‑first fault routing and stage normalization. The system builds 5.8 M source‑grounded records, trains on 5.22 M, and evaluates on 580 K, outperforming state‑of‑the‑art models on seven public benchmarks.
arXiv Computer Vision
Sep 2
StreamScout: Learning When to Look Deeper for Streaming Video Understanding
arXiv:2609.00291v1 Announce Type: new Abstract: Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily...