Tootfinder

Schäden an Startrampe russischer Raketen könnten Versorgung der ISS gefährden
Nach erfolgreichem Sojus-Raketenstart zur ISS wurden Schäden am Launchpad festgestellt. Offenbar war ein tonnenschwerer Teil nicht ausreichend gesichert.

Reason Emerges for Trevon Diggs’ Release By Cowboys – Report https://heavy.com/sports/nfl/dallas-cowboys/trevon-diggs-reason-realease-timing/

This is frickin' brilliant: #TimMinchin, you lil' beauty.

Efficient Construction of Large Search Spaces for Auto-Tuning
Floris-Jan Willemsen, Rob V. van Nieuwpoort, Ben van Werkhoven
https://arxiv.org/abs/2509.26253 https://

Efficient Construction of Large Search Spaces for Auto-Tuning
Automatic performance tuning, or auto-tuning, accelerates high-performance codes by exploring vast spaces of code variants. However, due to the large number of possible combinations and complex constraints, constructing these search spaces can be a major bottleneck. Real-world applications have been encountered where the search space construction takes minutes to hours or even days. Current state-of-the-art techniques for search space construction, such as chain-of-trees, lack a formal foundati…

One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
Rui Ming, Haoyuan Wu, Shoubo Hu, Zhuolun He, Bei Yu
https://arxiv.org/abs/2509.26313 https://

One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity stems not just from the loss function, but from a more fundamental difference: SFT learns from a fixed, pre-collected dataset, whereas RL utilizes on-policy data sampled from the current policy. Building on this hypothesis, we introduce one-token rollout (OTR), …

Remembering #SnowLeopard seing the #Tahoe (after a 18GB download) is sobering. And expectations were low to begin with.
Money spoils good products.
P.S.: #TimeMachine U…

🇺🇦 #NowPlaying on KEXP's #DriveTime
Tomo Nakayama:
🎵 Blue
#TomoNakayama
https://tomomusic.bandcamp.com/track/blue
https://open.spotify.com/track/2pHApgc1zROGhdESpJsX6S

Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement Learning
Ma\"el Macuglia, Paul Friedrich, Giorgia Ramponi
https://arxiv.org/abs/2509.26605 https…

Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement Learning
Deploying reinforcement learning (RL) in robotics, industry, and health care is blocked by two obstacles: the difficulty of specifying accurate rewards and the risk of unsafe, data-hungry exploration. We address this by proposing a two-stage framework that first learns a safe initial policy from a reward-free dataset of expert demonstrations, then fine-tunes it online using preference-based human feedback. We provide the first principled analysis of this offline-to-online approach and introduce…

🇺🇦 #NowPlaying on KEXP's #AfternoonShow
Tomo Nakayama:
🎵 With the Radio On
#TomoNakayama
https://tomomusic.bandcamp.com/track/with-the-radio-on
https://open.spotify.com/track/2hKXQvMGrANa6wMBjrFNPI

Noch einige der zuletzt hier besonders häufig geteilten #News:
Schäden an Startrampe russischer Raketen könnten Versorgung der ISS gefährden