Tootfinder

FURINA: Free from Unmergeable Router via LINear Aggregation of mixed experts
Jiayi Han, Liang Du, Yinda Chen, Xiao Kang, Weiyang Ding, Donghong Han
https://arxiv.org/abs/2509.14900

FURINA: Free from Unmergeable Router via LINear Aggregation of mixed experts
The Mixture of Experts (MoE) paradigm has been successfully integrated into Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning (PEFT), delivering performance gains with minimal parameter overhead. However, a key limitation of existing MoE-LoRA methods is their reliance on a discrete router, which prevents the integration of the MoE components into the backbone model. To overcome this, we propose FURINA, a novel Free from Unmergeable Router framework based on the LINear Aggregation o…

MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration
Yuanxin Wei, Lansong Diao, Bujiao Chen, Shenggan Cheng, Zhengping Qian, Wenyuan Yu, Nong Xiao, Wei Lin, Jiangsu Du
https://arxiv.org/abs/2508.12691

MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration
Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality video generation. However, their multi-step iterative denoising process incurs high computational cost and inference latency. Caching, a widely adopted optimization method in DiT models, leverages the redundancy in the diffusion process to skip computations in different granularities (e.g., step, cfg, block). Nevertheless, existing caching methods are limited …

MEGAN: Mixture of Experts for Robust Uncertainty Estimation in Endoscopy Videos
Damola Agbelese, Krishna Chaitanya, Pushpak Pati, Chaitanya Parmar, Pooya Mobadersany, Shreyas Fadnavis, Lindsey Surace, Shadi Yarandi, Louis R. Ghanem, Molly Lucas, Tommaso Mansi, Oana Gabriela Cula, Pablo F. Damasceno, Kristopher Standish
https://arxiv.org/ab…

MEGAN: Mixture of Experts for Robust Uncertainty Estimation in Endoscopy Videos
Reliable uncertainty quantification (UQ) is essential in medical AI. Evidential Deep Learning (EDL) offers a computationally efficient way to quantify model uncertainty alongside predictions, unlike traditional methods such as Monte Carlo (MC) Dropout and Deep Ensembles (DE). However, all these methods often rely on a single expert's annotations as ground truth for model training, overlooking the inter-rater variability in healthcare. To address this issue, we propose MEGAN, a Multi-Expert Gati…

Nice!
One of the better #litrpg webnovels I've read, Worth the Candle by Alexander Wales, is being made into a #manhwa / #manga!
Already enjoying the story! 😄

K3 and me had been on a concert in the next village on the weekend. There was a band of four women playing live. They opened with a song from The Black Keys and I was immediately sold. They rocked the barn so hard it was amazing. All four of them were amazing performers and super lovely too. My video capture doesn't really do their energy justice but maybe gives an impression: Stella Rockt

Eu jš mostrei meu #Beholder pra vocês aqui? #dnd #DungeonsAndDragons

Series B, Episode 12 - The Keeper
JENNA: Gola, don't kill him, please. [Vila is heard shrieking protests off stage]
GOLA: We'll see, we'll see.
[THE DUNGEONS - Blake hides as Vila is dragged in.]
https://blake.torpidity.net/m/212/362 B7B4

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Nonparametric predictive inference for discrete data via Metropolis-adjusted Dirichlet sequences
Davide Agnoletto, Tommaso Rigon, David B. Dunson
https://arxiv.org/abs/2507.08629 …

Nonparametric predictive inference for discrete data via Metropolis-adjusted Dirichlet sequences
This article is motivated by challenges in conducting Bayesian inferences on unknown discrete distributions, with a particular focus on count data. To avoid the computational disadvantages of traditional mixture models, we develop a novel Bayesian predictive approach. In particular, our Metropolis-adjusted Dirichlet (MAD) sequence model characterizes the predictive measure as a mixture of a base measure and Metropolis-Hastings kernels centered on previous data points. The resulting MAD sequence…

Series B, Episode 05 - Pressure Point
VERON: No!
GAN: It's all right, it's all right. We won't hurt you. [Hands her pill he has taken from a container.] Take this.
VERON: No.
GAN: Please.
VERON: [Swallows pill] Who are you?
https://blake.torpidity.net/m/205/255

MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds
Junxi Wu, Jinpeng Wang, Zheng Liu, Bin Chen, Dongjian Hu, Hao Wu, Shu-Tao Xiu
https://arxiv.org/abs/2509.02499

MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds
The rapid advancement of large language models has intensified public concerns about the potential misuse. Therefore, it is important to build trustworthy AI-generated text detection systems. Existing methods neglect stylistic modeling and mostly rely on static thresholds, which greatly limits the detection performance. In this paper, we propose the Mixture of Stylistic Experts (MoSEs) framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation. M…