Tootfinder

HOComp: Interaction-Aware Human-Object Composition
Dong Liang, Jinyuan Jia, Yuhao Liu, Rynson W. H. Lau
https://arxiv.org/abs/2507.16813 https://

HOComp: Interaction-Aware Human-Object Composition
While existing image-guided composition methods may help insert a foreground object onto a user-specified region of a background image, achieving natural blending inside the region with the rest of the image unchanged, we observe that these existing methods often struggle in synthesizing seamless interaction-aware compositions when the task involves human-object interactions. In this paper, we first propose HOComp, a novel approach for compositing a foreground object onto a human-centric backgr…

Row-Column Hybrid Grouping for Fault-Resilient Multi-Bit Weight Representation on IMC Arrays
Kang Eun Jeon, Sangheum Yeon, Jinhee Kim, Hyeonsu Bang, Johnny Rhe, Jong Hwan Ko
https://arxiv.org/abs/2508.15685

Row-Column Hybrid Grouping for Fault-Resilient Multi-Bit Weight Representation on IMC Arrays
This paper addresses two critical challenges in analog In-Memory Computing (IMC) systems that limit their scalability and deployability: the computational unreliability caused by stuck-at faults (SAFs) and the high compilation overhead of existing fault-mitigation algorithms, namely Fault-Free (FF). To overcome these limitations, we first propose a novel multi-bit weight representation technique, termed row-column hybrid grouping, which generalizes conventional column grouping by introducing re…

Classical theory of electron-ion correlations at electrochemical interfaces: Closing the circuit from double-layer charging to ion adsorption
Nils Bruch, Michael Eikerling, Tobias Binninger
https://arxiv.org/abs/2507.14751

Classical theory of electron-ion correlations at electrochemical interfaces: Closing the circuit from double-layer charging to ion adsorption
The electric double layer (EDL) that forms at the interface between metals and ionic solutions is at the heart of various energy technologies. Recent experimental data have challenged our traditional understanding of the EDL charging behavior, which is based on mean-field Gouy-Chapman-Stern-type (GCS) models. In this article, we present a classical theory for the EDL, derived from first-principles statistical mechanics, that accounts for electron-ion correlation effects using the method of imag…

Information-computation trade-offs in non-linear transforms
Connor Ding, Abhiram Rao Gorle, Jiwon Jeong, Naomi Sagan, Tsachy Weissman
https://arxiv.org/abs/2506.15948

Information-computation trade-offs in non-linear transforms
In this work, we explore the interplay between information and computation in non-linear transform-based compression for broad classes of modern information-processing tasks. We first investigate two emerging nonlinear data transformation frameworks for image compression: Implicit Neural Representations (INRs) and 2D Gaussian Splatting (GS). We analyze their representational properties, behavior under lossy compression, and convergence dynamics. Our results highlight key trade-offs between INR'…

And here are the last two #photos from my bike&hike recently. the one shows one of the (in my point of view) interesting geological parts of the hike. And in the second I tried to get some more foreground into the photo
I hope you enjoy the view as much as I enjoyed the hike up there 🙂
And I wonder if we could see the home area of @…

Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatars
Marcel C. B\"uhler, Ye Yuan, Xueting Li, Yangyi Huang, Koki Nagano, Umar Iqbal
https://arxiv.org/abs/2507.15979

Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatars
We introduce Dream, Lift, Animate (DLA), a novel framework that reconstructs animatable 3D human avatars from a single image. This is achieved by leveraging multi-view generation, 3D Gaussian lifting, and pose-aware UV-space mapping of 3D Gaussians. Given an image, we first dream plausible multi-views using a video diffusion model, capturing rich geometric and appearance details. These views are then lifted into unstructured 3D Gaussians. To enable animation, we propose a transformer-based enco…

Tactile Beyond Pixels: Multisensory Touch Representations for Robot Manipulation
Carolina Higuera, Akash Sharma, Taosha Fan, Chaithanya Krishna Bodduluri, Byron Boots, Michael Kaess, Mike Lambeta, Tingfan Wu, Zixi Liu, Francois Robert Hogan, Mustafa Mukadam
https://arxiv.org/abs/2506.14754…

Tactile Beyond Pixels: Multisensory Touch Representations for Robot Manipulation
We present Sparsh-X, the first multisensory touch representations across four tactile modalities: image, audio, motion, and pressure. Trained on ~1M contact-rich interactions collected with the Digit 360 sensor, Sparsh-X captures complementary touch signals at diverse temporal and spatial scales. By leveraging self-supervised learning, Sparsh-X fuses these modalities into a unified representation that captures physical properties useful for robot manipulation tasks. We study how to effectively …

Moodifier: MLLM-Enhanced Emotion-Driven Image Editing
Jiarong Ye, Sharon X. Huang
https://arxiv.org/abs/2507.14024 https://arxiv.org/…

Moodifier: MLLM-Enhanced Emotion-Driven Image Editing
Bridging emotions and visual content for emotion-driven image editing holds great potential in creative industries, yet precise manipulation remains challenging due to the abstract nature of emotions and their varied manifestations across different contexts. We tackle this challenge with an integrated approach consisting of three complementary components. First, we introduce MoodArchive, an 8M+ image dataset with detailed hierarchical emotional annotations generated by LLaVA and partially valid…

Assessing Trustworthiness of AI Training Dataset using Subjective Logic -- A Use Case on Bias
Koffi Ismael Ouattara, Ioannis Krontiris, Theo Dimitrakos, Frank Kargl
https://arxiv.org/abs/2508.13813

Assessing Trustworthiness of AI Training Dataset using Subjective Logic -- A Use Case on Bias
As AI systems increasingly rely on training data, assessing dataset trustworthiness has become critical, particularly for properties like fairness or bias that emerge at the dataset level. Prior work has used Subjective Logic to assess trustworthiness of individual data, but not to evaluate trustworthiness properties that emerge only at the level of the dataset as a whole. This paper introduces the first formal framework for assessing the trustworthiness of AI training datasets, enabling uncert…

Hello all!
I wasn't able to process the photos of my recent trips, but I wanted to share this one from last year.
I went there on a hot day to "take a couple of photos". In the end I spent 3h just at this waterfall searching for the right composition & interpretation, the right motive etc.
I love the result, but I'm surprised how much time I spent there to get it.