Tootfinder

Is Extending Modality The Right Path Towards Omni-Modality?
Tinghui Zhu, Kai Zhang, Muhao Chen, Yu Su
https://arxiv.org/abs/2506.01872 https://

Is Extending Modality The Right Path Towards Omni-Modality?
Omni-modal language models (OLMs) aim to integrate and reason over diverse input modalities--such as text, images, video, and audio--while maintaining strong language capabilities. Despite recent advancements, existing models, especially open-source ones, remain far from true omni-modality, struggling to generalize beyond the specific modality pairs they are trained on or to achieve strong performance when processing multi-modal inputs. We study the effect of extending modality, the dominant te…

🇺🇦 Auf radioeins läuft...
Matilda Mann:
🎵 Just Because
#NowPlaying #MatildaMann
https://matildamann.bandcamp.com/track/just-because
https://open.spotify.com/track/1DwmNjO23qRsGsgmxfADfC

"#OpenAccess and #Citation #Impact: Modality, Funding, Publisher, and Disciplinary Trends at the University of Kentucky"

Parenting can be tough. That's why shows like Adolescence are worth watching, because watching something difficult is better than dealing with nightmare scenarios in real life.
https://arnel.bearblog.dev/adolescence-2025/

Adolescence: Healthy dose of fear for better parenting
I watched a show called Adolescence. It made me want to puke and hug my child at the same time, preferably not to puke on her

Self-Supervised Spatial Correspondence Across Modalities
Ayush Shrivastava, Andrew Owens
https://arxiv.org/abs/2506.03148 https://arx…

Self-Supervised Spatial Correspondence Across Modalities
We present a method for finding cross-modal space-time correspondences. Given two images from different visual modalities, such as an RGB image and a depth map, our model identifies which pairs of pixels correspond to the same physical points in the scene. To solve this problem, we extend the contrastive random walk framework to simultaneously learn cycle-consistent feature representations for both cross-modal and intra-modal matching. The resulting model is simple and has no explicit photo-con…

Hi #MutualAid, @… needs your help!
If you live in the EU and have strong feelings about video games, whether you love them or hate them, this is your chance to make an impact.
Boost this post now, join the conversation everyone is t…

A New 5 bit/2D-symbol Modulation Format for Relative Intensity Noise-dominated IM-DD Systems
Felipe Villenas, Kaiquan Wu, Yunus Can G\"ultekin, Jamal Riani, Alex Alvarado
https://arxiv.org/abs/2506.01761

A New 5 bit/2D-symbol Modulation Format for Relative Intensity Noise-dominated IM-DD Systems
We propose a novel 5-bit/2D-symbol modulation format based on PAM-6 optimized for IM-DD systems dominated by relative intensity noise. The proposed modulation scheme improves SNR by 0.94 dB compared to conventional PAM-6 and achieves near-optimal BER performance.

I used to drink 8-9 coffees per day, five of which were before noon. I didn't have a problem drinking a coffee late in the evening. I thought to myself, if I can fall asleep, there's no problem.
https://arnel.bearblog.dev/one-coffee/

Why I Started Drinking Only One Coffee Per Day
A post about coffee, pooping, and napping.

Steam Summer Sale, what are you all grabbing?
Suggestions for games, especially indie ones, are very welcome.
#IndieGames #VideoGames #Gaming

I have a question for the #MetalHeadClub community, as well as the wider #fediverse and #mastodon communities, especially those who follow me.
I've always noticed that Mastodon is less u…