Found 23 document(s)
Page 1 of 2
-
Generated videos often lose geometric consistency under camera motion: structures warp under viewpoint change, parallax becomes inconsistent, and smooth camera movement may collapse into shot-like transitions. We argue t...
-
Human video demonstrations provide rich manipulation strategies for dexterous manipulation learning. We study a setting in which a fully specified simulated scene is used to generate videos that specify the demonstrated ...
-
Meteorological downscaling is crucial for high-resolution regional climate forecasting and disaster early warning. While neural operators have emerged as a promising paradigm for modeling complex spatiotemporal mappings,...
-
Computer-aided retrosynthesis has advanced through single-step prediction, tree search and route scoring, but complex targets still require judgement over the whole route, where stereochemistry, functional-group compatib...
-
Omni-modal large language models can jointly understand video, audio, and text, yet they remain weak at temporal grounding, a capability essential for real-world audio-visual applications. To understand this limitation, ...
-
Large language models (LLMs) have recently shown strong potential for time series reasoning, while models that reason over time series are usually with long chains of thought. However, this process often consumes thousan...
-
World Action Models (WAMs) typically represent the world through latent embeddings from pretrained video models, which entangle heterogeneous aspects of the world, from how it looks (e.g., texture and color) to how it is...
-
Recommending bacterial cultivation conditions from sequence data is a challenging structured problem characterized by missing standardized benchmarks and limited use of sequence structure. To address this, we introduce D...
-
Physics-informed neural networks (PINNs) supervise on the residual of a known differential operator. Many high-stakes inference problems admit no such operator: clinical signals, behavioral measurements, materials proper...
-
Deductive verification scales to large software systems through modular reasoning, where formal contracts summarize the behavior of individual functions and enable their independent verification. Its central bottleneck i...
-
Large language models increasingly address users in the register of care: they remember personal details, adopt a first-person emotional voice, and sustain relationships across many sessions. This anthropomorphic mode of...
-
This paper introduces Spark-Audio 1.0, a speech foundation model trained on domestically produced computing infrastructure. The model accepts text and speech inputs and generates text outputs. It supports multilingual (9...
-
Digital turns in architecture are transforming undergraduate pedagogy on design thinking, tools, and methods. However, few Chinese architecture schools have adapted, prompting questions about how to systematically incorp...
-
Grasslands support the majority of global livestock production systems while providing vital ecosystem services. Expansion of the livestock sector over recent decades has however placed enormous pressure on grasslands, w...
-
Many functionally important materials, such as silicon, possess high-symmetry crystal structures that forbid even-order nonlinear optical responses, thereby limiting their application in e.g., photonics and optoelectroni...