The paper proposes CoMet, a method for uncertainty estimation in multimodal large language models, which decomposes uncertainty into context-specific and multiplicity-specific terms.

The paper introduces COMET, a novel PLS-SVD framework, to analyze the audio-text modality gap in CLAP models, showing that shared concepts are captured by a small subset of axes, and proposes a spectr…

The paper presents an initial implementation of a quantized, integer-only transformer for jet tagging on the AMD Versal AI Engine using a reusable software framework.

This paper proposes a method to describe dynamical systems using molecular and reaction concepts, making three key decisions: number of places, species determination, and transitions.

The paper presents BoxTwin, an interactive digital twin framework that learns the full dynamics of elastoplastic articulated objects from videos and accurately tracks joint trajectories and reproduces…

DELOS is a novel contrastive-learning framework that efficiently and sensitively detects shallow, intermediate-to-long-period exoplanet transits in Kepler photometry, significantly outperforming tradi…

The paper introduces Science Earth, a planet-scale scientific runtime that enables diverse, siloed AI capabilities to connect and collaborate dynamically, demonstrating that scientific discovery can b…

The paper introduces SPARROW, an autonomous, open-source platform that uses solar power, edge AI, and satellite communication to enable continuous, scalable biodiversity monitoring in remote global ec…

VESTA introduces a novel agent framework that enhances Visual Language Models (VLMs) by equipping them with a dynamic, reusable toolkit of diagnostic and statistical tools, significantly improving aut…

This paper introduces a machine learning model, RuBR, and a methodology to reliably distinguish genuine astronomical transients from spurious detections for the upcoming Roman Space Telescope's data p…

This paper introduces tap, a file-based collaboration protocol enabling LLM agents from different vendors to collaborate on a shared codebase without shared memory or identical runtimes.

The paper introduces AxDafny, a verifier-guided repair framework that improves verification success in Dafny by generating implementations, invariants, assertions, and termination arguments.

HydraCollab is a new adaptive collaborative-perception framework that selectively transmits informative sensor features and dynamically employs collaboration strategies to minimize communication overh…

This paper proposes methods for intrinsic decomposition of radiance fields using Gaussian splatting, enabling adaptive modeling, disentanglement, and editing of textures in images.

The paper proposes HADT, a novel transformer-based architecture using differential attention and relational tokenization, to enable adaptive and real-time autonomous resource management for heterogene…

This paper demonstrates that fusing multi-viewpoint data from multiple satellites significantly enhances the accuracy of space object detection in congested LEO constellations, establishing multi-view…

SolarChain is a platform that ensures verifiable trust in decentralized solar energy markets by anchoring digital energy credits to the hard physical limits of solar yield, thereby preventing data man…