Tootfinder

Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
Jiashuo Wang, Kaitao Song, Chunpu Xu, Changhe Song, Yang Xiao, Dongsheng Li, Lili Qiu, Wenjie Li
https://arxiv.org/abs/2506.21497

Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
Enhancing user engagement through interactions plays an essential role in socially-driven dialogues. While prior works have optimized models to reason over relevant knowledge or plan a dialogue act flow, the relationship between user engagement and knowledge or dialogue acts is subtle and does not guarantee user engagement in socially-driven dialogues. To this end, we enable interactive LLMs to learn user engagement by leveraging signals from the future development of conversations. Specificall…

NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs
Khuram Naveed, Bruna Neves de Freitas, Ruben Pauwels
https://arxiv.org/abs/2506.19387

NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs
Convolutional denoising autoencoders (DAEs) are powerful tools for image restoration. However, they inherit a key limitation of convolutional neural networks (CNNs): they tend to recover low-frequency features, such as smooth regions, more effectively than high-frequency details. This leads to the loss of fine details, which is particularly problematic in dental radiographs where preserving subtle anatomical structures is crucial. While self-attention mechanisms can help mitigate this issue by …

This one is around the corner from my office. I never suspected what it might look like on the inside.
https://www.instagram.com/zillowgonewild/p/DMMMikYumtR/

Zillow Gone Wild 🏡 on Instagram: "me: lets go to Versailles Mother: we literally have Versailles at home Follow @zillowgonewild to never miss a wild home! Link in bio for the full listing! $4,000,000 | Alexandria, VA 6 bd, 5 ba | 3,183 sq ft | 2,042 sq ft lot Currently listed via @andrea.courduvelis and @nihalala @ttrsir Zillow Gone Wild season two premieres Friday, July 18, at 9:30 pm ET/PT on HGTV and streams the next day on discovery+ and HBO Max Thanks for submitting @ratchelbuff!! Found a wild home? Submit it for a chance to be featured at zillowgonewild.com/submit!! If you see an agent posting a listing we should feature TAG US IN THEIR COMMENTS!! MID YEAR SUPPORTER DRIVE!! Patreon.com/zillowgonewild or link in bio!! If Zillow gone wild brings you joy please support us for as low as $1 a month!! We are looking for our first 100 supporters 🙏🏼🙏🏼🙏🏼"
7,636 likes, 461 comments - zillowgonewild on July 16, 2025: "me: lets go to Versailles Mother: we literally have Versailles at home Follow @zillowgonewild to never miss a wild home! Link in bio for the full listing! $4,000,000 | Alexandria, VA 6 bd, 5 ba | 3,183 sq ft | 2,042 sq ft lot Currently listed via @andrea.courduvelis and @nihalala @ttrsir Zillow Gone Wild season two premieres Friday, July 18, at 9:30 pm ET/PT on HGTV and streams the next day on discovery+ and HBO M…

Und hier haben wir es: eine logisch-semantische Injektion: unmarkierte Modifikationen der Funktionsweise von LLMs, die unser Denken nudgen und damit unsere logisch-semantische Souveränität untergraben: https://toot.cafe/@baldur/113934035009657696
Hintergrund:

EXPO: Stable Reinforcement Learning with Expressive Policies
Perry Dong, Qiyang Li, Dorsa Sadigh, Chelsea Finn
https://arxiv.org/abs/2507.07986 https://arxiv.org/pdf/2507.07986 https://arxiv.org/html/2507.07986
arXiv:2507.07986v1 Announce Type: new
Abstract: We study the problem of training and fine-tuning expressive policies with online reinforcement learning (RL) given an offline dataset. Training expressive policy classes with online RL present a unique challenge of stable value maximization. Unlike simpler Gaussian policies commonly used in online RL, expressive policies like diffusion and flow-matching policies are parameterized by a long denoising chain, which hinders stable gradient propagation from actions to policy parameters when optimizing against some value function. Our key insight is that we can address stable value maximization by avoiding direct optimization over value with the expressive policy and instead construct an on-the-fly RL policy to maximize Q-value. We propose Expressive Policy Optimization (EXPO), a sample-efficient online RL algorithm that utilizes an on-the-fly policy to maximize value with two parameterized policies -- a larger expressive base policy trained with a stable imitation learning objective and a light-weight Gaussian edit policy that edits the actions sampled from the base policy toward a higher value distribution. The on-the-fly policy optimizes the actions from the base policy with the learned edit policy and chooses the value maximizing action from the base and edited actions for both sampling and temporal-difference (TD) backup. Our approach yields up to 2-3x improvement in sample efficiency on average over prior methods both in the setting of fine-tuning a pretrained policy given offline data and in leveraging offline data to train online.
toXiv_bot_toot

FCPO: Federated Continual Policy Optimization for Real-Time High-Throughput Edge Video Analytics
Lucas Liebe, Thanh-Tung Nguyen, Dongman Lee
https://arxiv.org/abs/2507.18047 htt…

FCPO: Federated Continual Policy Optimization for Real-Time High-Throughput Edge Video Analytics
The growing complexity of Edge Video Analytics (EVA) facilitates new kind of intelligent applications, but creates challenges in real-time inference serving systems. State-of-the-art (SOTA) scheduling systems optimize global workload distributions for heterogeneous devices but often suffer from extended scheduling cycles, leading to sub-optimal processing in rapidly changing Edge environments. Local Reinforcement Learning (RL) enables quick adjustments between cycles but faces scalability, know…

DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance
Maximilian Du, Shuran Song
https://arxiv.org/abs/2506.13922 https://

DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance
Deploying large, complex policies in the real world requires the ability to steer them to fit the needs of a situation. Most common steering approaches, like goal-conditioning, require training the robot policy with a distribution of test-time objectives in mind. To overcome this limitation, we present DynaGuide, a steering method for diffusion policies using guidance from an external dynamics model during the diffusion denoising process. DynaGuide separates the dynamics model from the base pol…

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.

In This Thread: denizens of debian-user mailing list who refuse to accept that there are people who do creative work without wanting to use email.
Apparently it is only "kids" who "don't understand what is important", who "have a mobile phone glued to their hand" and "don't care about their computer as long as it plays their games."

This https://arxiv.org/abs/2411.18970 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

FiRe: Fixed-points of Restoration Priors for Solving Inverse Problems
Selecting an appropriate prior to compensate for information loss due to the measurement operator is a fundamental challenge in imaging inverse problems. Implicit priors based on denoising neural networks have become central to widely-used frameworks such as Plug-and-Play (PnP) algorithms. In this work, we introduce Fixed-points of Restoration (FiRe) priors as a new framework for expanding the notion of priors in PnP to general restoration models beyond traditional denoising models. The key ins…