Fundamental Utilization
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
The Utility and Complexity of in- and out-of-Distribution Machine Unlearning
arXiv:2412.09119v3 Announce Type: replace Abstract: Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment. Despite this importance, existing approaches are often heuristic and lack formal guarantees. In this paper, we analyze the fundamental utility, time, and space complexity trade-offs of approximate unlearning, providing rigorous certification analogous to differential...
ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics
arXiv:2604.01313v2 Announce Type: replace Abstract: High-fidelity simulations and complex inverse problems, such as detector modeling and unfolding, are computationally intensive bottlenecks across subatomic physics, yet essential for accurate physical interpretation. While Conditional Flow Matching (CFM) offers a robust acceleration approach, we demonstrate its standard training loss is fundamentally misleading. Specifically, utilizing a Jefferson Lab Nuclear Physics (NP) kinematic dataset...
ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics
arXiv:2604.01313v2 Announce Type: replace-cross Abstract: High-fidelity simulations and complex inverse problems, such as detector modeling and unfolding, are computationally intensive bottlenecks across subatomic physics, yet essential for accurate physical interpretation. While Conditional Flow Matching (CFM) offers a robust acceleration approach, we demonstrate its standard training loss is fundamentally misleading. Specifically, utilizing a Jefferson Lab Nuclear Physics (NP) kinematic...
Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
Announce Type: new Abstract: Unlearning in diffusion models aims to remove undesirable data or concepts while preserving the utility of pretrained models -- two fundamentally conflicting objectives. We propose a principled constrained optimization framework that formulates unlearning as minimizing the deviation from a pretrained model, subject to explicit separation constraints from the unlearning distributions. Specifically, we formulate three constrained optimization problems based on...
First observation of the $\gamma$-ray beam production by the backward Compton scattering of reflected synchrotron radiation in the extreme ultraviolet range
Announce Type: replace Abstract: Compton scattering of photons off high-energy electrons is a fundamental quantum mechanical process widely utilized to produce a $\gamma$-ray beam for scientific research. Instead of injecting laser light into a storage ring as a conventional way, we have developed an innovative method to achieve drastically higher energies approaching the ring energy by the backward Compton scattering of extreme ultraviolet (EUV) light. In this method, $92$ $\mathrm{eV}$...
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
arXiv:2605.24535v2 Announce Type: replace Abstract: Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving benign utility. However, existing steering methods are fundamentally supervised and tied to a static, limited training set, whereas real jailbreaks evolve and are often out-of-distributed from the training set, leading to...
Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses
new Abstract: Although large language models (LLMs) have shown considerable progress in pragmatic language understanding, prior research has focused mainly on their comprehension of verbal behavior. Nonetheless, non-verbal behavior remains a fundamental component of human communication, especially when deliberately utilized in isolation to convey indirect meanings. In this work, we present the first systematic evaluation of LLMs' ability to infer pragmatic meaning in dialogue consisting...
GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution
Announce Type: new Abstract: Scalable data attribution methods typically assign isolated utility scores to individual training examples. This prevalent additive assumption fundamentally fails to capture critical subset dynamics, including data redundancy and complementary coverage. In this work, we reframe attribution as subset-level counterfactual utility prediction and introduce GRASP, an interaction-aware surrogate.
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
Announce Type: replace Abstract: As the foundational architecture of modern machine learning, Transformers have driven remarkable progress across diverse AI domains. Despite their transformative impact, a persistent challenge across various Transformers is Attention Sink (AS), in which a disproportionate amount of attention is focused on a small subset of specific yet uninformative tokens. AS complicates interpretability, significantly affecting the training and inference dynamics, and...
Axial encoding unlocks up to eightfold faster 3D microscopy with less light
A research team from HKU Engineering has pioneered a fundamentally new imaging strategy known as AIMED (Arbitrary illumination microscopy with encoded depth), which utilizes a sub-sampling approach. By integrating innovations in axial optical encoding with advanced computational image reconstruction, the AIMED technology enables a substantial increase in 3D imaging speed while enhancing photon safety, all with minimal additional system complexity. This breakthrough demonstrates significant...