Tootfinder

from my link log —
Tuning async IO in PostgreSQL 18.
https://vondra.me/posts/tuning-aio-in-postgresql-18/
saved 2025-09-26 https://

Efficient Hyperparameter Tuning via Trajectory Invariance Principle
Bingrui Li, Jiaxin Wen, Zhanpeng Zhou, Jun Zhu, Jianfei Chen
https://arxiv.org/abs/2509.25049 https://…

Efficient Hyperparameter Tuning via Trajectory Invariance Principle
As hyperparameter tuning becomes increasingly costly at scale, efficient tuning methods are essential. Yet principles for guiding hyperparameter tuning remain limited. In this work, we seek to establish such principles by considering a broad range of hyperparameters, including batch size, learning rate, and weight decay. We identify a phenomenon we call trajectory invariance, where pre-training loss curves, gradient noise, and gradient norm exhibit invariance--closely overlapping--with respect …

🇺🇦 #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

Varför forskningen kring sötningsmedel alltid verkar oklar | Podcast https://tyngre.se/podcast/tyngre-traningssnack/varfor-forskningen-kring-sotningsmedel-alltid-verkar-oklar

Varför forskningen kring sötningsmedel alltid verkar oklar | Podcast
Förra veckan var det dags för nya rubriker kring sötningsmedel

SDD: Self-Degraded Defense against Malicious Fine-tuning
Zixuan Chen, Weikai Lu, Xin Lin, Ziqian Zeng
https://arxiv.org/abs/2507.21182 https://arxiv.org/pd…

SDD: Self-Degraded Defense against Malicious Fine-tuning
Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To counter this, we theoretically uncover why malicious fine-tuning succeeds and identify potential defense strategies. Building on the theoretical analysis, we introduce the Self-Degraded Defense (SDD) framework. SDD encourages LLMs to produce high-quality but irr…

from my link log —
Timing conclusions: GPS, NTP, PTP timing with Linux.
https://scottstuff.net/posts/2025/06/10/timing-conclusions/
saved 2025-08-25

Timing Conclusions
This is the 13th article that I’ve written lately on NTP and PTP timing with Linux. I set out to answer a couple questions for myself and ended up spending two months swimming in an ocean of nanosecond-scale measurements. When I started, I saw a lot of misinformation about NTP and PTP online. Things like: Conventional wisdom said that NTP was good for millisecond-scale timing accuracy. I expected that to be rather pessimistic, and expected to see low microsecond to high nanosecond-range synci…

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Aayush Mishra, Daniel Khashabi, Anqi Liu
https://arxiv.org/abs/2509.22621 https://arxiv…

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Supervised Fine-Tuning (SFT) is used to specialize model behavior by training weights to produce intended target responses for queries. In contrast, In-Context Learning (ICL) adapts models during inference with instructions or demonstrations in the prompt. ICL can offer better generalizability and more calibrated responses compared to SFT in data scarce settings, at the cost of more inference compute. In this work, we ask the question: Can ICL's internal computations be used to improve the qual…

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
David Gonz\'alez Mart\'inez
https://arxiv.org/abs/2509.25136 https://

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
Neural network compression techniques typically require expensive fine-tuning or search procedures, rendering them impractical on commodity hardware. Inspired by recent LLM compression research, we present a general activation-aware factorization framework that can be applied to a broad range of layers. Moreover, we introduce a scalable budgeted rank allocator that allows flexible control over compression targets (e.g., retaining 50% of parameters) with no overhead. Together, these components f…

TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion
Sophia Tang, Yuchen Zhu, Molei Tao, Pranam Chatterjee
https://arxiv.org/abs/2509.25171 https://

TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion
Reinforcement learning with stochastic optimal control offers a promising framework for diffusion fine-tuning, where a pre-trained diffusion model is optimized to generate paths that lead to a reward-tilted distribution. While these approaches enable optimization without access to explicit samples from the optimal distribution, they require training on rollouts under the current fine-tuned model, making them susceptible to reinforcing sub-optimal trajectories that yield poor rewards. To overcom…