research note
This paper tackles a very specific inverse-problem pain point in image-based transport modeling: if you try to reconstruct flow and clearance fields directly from noisy spatiotemporal imaging, the …
research note
This work addresses limitations in reinforcement learning (RL) for continuous control where policy updates typically rely on local gradients that do not explicitly leverage the global geometry of t…
research note
This study addresses the critical question of how much historical Electronic Health Record (EHR) data is needed to optimally predict 30-day unplanned hospital readmissions following hip and knee ar…
research note
This paper addresses a crucial but underexplored aspect of tool-augmented large language models (LLMs): the decision of whether to invoke an external tool for a given task instance
research note
This paper addresses the ICASSP 2025 GenDARA / Room Acoustics and Speaker Distance Estimation challenge, where the core bottleneck is sparse and mismatched room impulse response (RIR) data for trai…
research note
This paper addresses the challenge of unsupervised single-image deraining, where paired rainy-clean training data is unavailable, making optimization difficult due to under-constrained objectives a…
research note
AEGIS introduces a comprehensive benchmark designed specifically for forensic analysis of AI-generated academic images, addressing a critical gap left by existing generic forensic datasets
research note
This paper targets a very specific failure mode of PINNs: when the PDE forcing is extremely localized and large in magnitude, the residual loss can dwarf boundary/initial losses by many orders of m…
research note
This paper tackles a nuanced and underexplored challenge in audio-visual DeepFake detection: semantic mismatch between authentic audio and video streams
research note
This paper tackles Night Photography Rendering (NPR), a RAW-to-RGB problem where the scene contains both severely underexposed regions and bright point light sources, creating a difficult mix of no…
research note
This paper addresses a specific gap in topology-aware image segmentation: classical simple-point topology is defined on binary images and is non-differentiable, which makes it awkward to use with m…
research note
Fake3DGS tackles a gap the 2D deepfake literature mostly ignores: once scene edits happen in a 3D representation, the resulting renders can stay geometrically and photometrically consistent across …
