Tootfinder

edit: yes i already know what's up with this image yall can stop explaining in increasingly shitty condescending unhelpful ways

CoMemo: LVLMs Need Image Context with Image Memory
Shi Liu, Weijie Su, Xizhou Zhu, Wenhai Wang, Jifeng Dai
https://arxiv.org/abs/2506.06279 https://…

CoMemo: LVLMs Need Image Context with Image Memory
Recent advancements in Large Vision-Language Models built upon Large Language Models have established aligning visual features with LLM representations as the dominant paradigm. However, inherited LLM architectural designs introduce suboptimal characteristics for multimodal processing. First, LVLMs exhibit a bimodal distribution in attention allocation, leading to the progressive neglect of middle visual content as context expands. Second, conventional positional encoding schemes fail to preser…

Bridging Electrostatic Screening and Ion Transport in Lithium Salt-Doped Ionic Liquids
Hyungshick Park, Bong June Sung, Jeongmin Kim
https://arxiv.org/abs/2506.08476

Bridging Electrostatic Screening and Ion Transport in Lithium Salt-Doped Ionic Liquids
Alkali salt-doped ionic liquids are emerging as promising electrolyte systems for energy applications, owing to their excellent interfacial stability. To address their limited ionic conductivity, various strategies have been proposed, including modifying the ion solvation environment and enhancing the transport of selected ions (e.g., Li$^+$). Despite the pivotal role of electrostatic interactions in determining key physicochemical properties, their influence on ion transport in such systems ha…

Ein Win auf den wir gerade richtig stolz sind. 🥹
Beim größten SEO-Wettbewerb Deutschlands von Agenturtipp.de mit über 100 teilnehmenden Agenturen haben wir mit HECHT INS GEFECHT ⚓️ nicht nur den dritten Platz 🥉 geholt – sondern auch den Sonderpreis für die höchste Sichtbarkeit in KI-Suchmaschinen eingesackt! ❤️‍🔥

DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling
Hangyu Ji
https://arxiv.org/abs/2506.05297 https://

DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling
Accurate 3D medical image segmentation demands architectures capable of reconciling global context modeling with spatial topology preservation. While State Space Models (SSMs) like Mamba show potential for sequence modeling, existing medical SSMs suffer from encoder-decoder incompatibility: the encoder's 1D sequence flattening compromises spatial structures, while conventional decoders fail to leverage Mamba's state propagation. We present DM-SegNet, a Dual-Mamba architecture integrating direct…

Hey, folks who understand alt text and limited vision accessibility:
I have need to write alt text for the diagram below. The alt text needs to be comprehensible to somebody who is encountering this kind of diagram for the ••very first time••. I could describe the images using the relevant jargon, but that would only serve people who already know the thing this activity is teaching them!
Any suggestions for how I could write good alt text for something like this? Is it possible? (The horizontal black bars are minus signs, i.e. subtraction. This is clear from context in the text, but probably not clear in the image.)
PLEASE NOTE: I am looking for people with ••relevant accessibility expertise••, not just random best shots from people who (like me) don’t really know much about this kind of problem.

10:42—Good Morning #Fediverse!
Being #ActuallyAutistic, I am currently hyperfixated on this image. I have been staring at it for an extended period, analyzing every detail.
I keep noticing new things every time I look at it. My brain is in “info-dump mode” and I could pr…

Isn’t that the shortwave time station in Boulder? https://mastodon.social/@dirtypair/114592561887178563

Dirty Pair: Zero Context (@dirtypair@mastodon.social)
Attached: 1 image

This https://arxiv.org/abs/2505.21863 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning
Publicly significant images from events hold valuable contextual information, crucial for journalism and education. However, existing methods often struggle to extract this relevance accurately. To address this, we introduce GETReason (Geospatial Event Temporal Reasoning), a framework that moves beyond surface-level image descriptions to infer deeper contextual meaning. We propose that extracting global event, temporal, and geospatial information enhances understanding of an image's significanc…

DACN: Dual-Attention Convolutional Network for Hyperspectral Image Super-Resolution
Usman Muhammad, Jorma Laaksonen
https://arxiv.org/abs/2506.05041 https:…

DACN: Dual-Attention Convolutional Network for Hyperspectral Image Super-Resolution
2D convolutional neural networks (CNNs) have attracted significant attention for hyperspectral image super-resolution tasks. However, a key limitation is their reliance on local neighborhoods, which leads to a lack of global contextual understanding. Moreover, band correlation and data scarcity continue to limit their performance. To mitigate these issues, we introduce DACN, a dual-attention convolutional network for hyperspectral image super-resolution. Specifically, the model first employs au…