Tootfinder

🇺🇦 #NowPlaying on KEXP's #ElSonido
Juana Aguirre:
🎵 lo_divino
#JuanaAguirre
https://juanaaguirre.bandcamp.com/track/lo-divino
https://open.spotify.com/track/20SlD6QDxPlOd1Ip0NvsdG

Der #JungeRat #Kiel wird gewählt.
12- bis 19-Jährige können sich bis zum 29. September bewerben.

Junger Rat in Kiel wird gewählt – Nachwuchspolitiker gesucht
In Kiel steht die Wahl des Jungen Rats an. Jugendliche haben dabei die Chance, politische Erfahrung zu sammeln. Bewerbungen sind bis zum 29. September möglich. Welche Vorteile bietet die Teilnahme an diesem Gremium?

Im eiskalten Wasser - Junger Mann ertrinkt nach Unfall in seinem Auto #News #Nachrichten

NIRVANA: Structured pruning reimagined for large language models compression
Mengting Ai, Tianxin Wei, Sirui Chen, Jingrui He
https://arxiv.org/abs/2509.14230 https://

NIRVANA: Structured pruning reimagined for large language models compression
Structured pruning of large language models (LLMs) offers substantial efficiency improvements by removing entire hidden units, yet current approaches often suffer from significant performance degradation, particularly in zero-shot settings, and necessitate costly recovery techniques such as supervised fine-tuning (SFT) or adapter insertion. To address these critical shortcomings, we introduce NIRVANA, a novel pruning method explicitly designed to balance immediate zero-shot accuracy preservatio…

Reference Points in LLM Sentiment Analysis: The Role of Structured Context
Junichiro Niimi
https://arxiv.org/abs/2508.11454 https://arxiv.org/pdf/2508.1145…

Reference Points in LLM Sentiment Analysis: The Role of Structured Context
Large language models (LLMs) are now widely used across many fields, including marketing research. Sentiment analysis, in particular, helps firms understand consumer preferences. While most NLP studies classify sentiment from review text alone, marketing theories, such as prospect theory and expectation--disconfirmation theory, point out that customer evaluations are shaped not only by the actual experience but also by additional reference points. This study therefore investigates how the conte…

🇺🇦 #NowPlaying on #BBC6Music's #CraigCharles
John Grant:
🎵 All That School For Nothing (Instrumental)
#JohnGrant
https://johngrantmusic.bandcamp.com/track/all-that-school-for-nothing
https://open.spotify.com/track/1Gn11B0GFzjUvFMe03rP0w

Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
Gang Cheng, Xin Gao, Li Hu, Siqi Hu, Mingyang Huang, Chaonan Ji, Ju Li, Dechao Meng, Jinwei Qi, Penchong Qiao, Zhen Shen, Yafei Song, Ke Sun, Linrui Tian, Feng Wang, Guangyuan Wang, Qi Wang, Zhongjian Wang, Jiayu Xiao, Sheng Xu, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhang, Jingren Zhou, Lian Zhuo

Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the character in the video to generate high-fidelity character videos. Alternatively, it can integrate the animated character into the reference video to replace the original character, replicating the scene's lighting and color tone to achieve seamless environmental i…

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
Wenhao Zhang, Yuexiang Xie, Yuchang Sun, Yanxi Chen, Guoyin Wang, Yaliang Li, Bolin Ding, Jingren Zhou
https://arxiv.org/abs/2508.11408

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are two prominent post-training paradigms for refining the capabilities and aligning the behavior of Large Language Models (LLMs). Existing approaches that integrate SFT and RL often face the risk of disrupting established model patterns and inducing overfitting to expert data. To address this, we present a novel investigation into the unified view of SFT and RL through an off-policy versus on-policy lens. We propose CHORD, a framewor…