Fidelity Decay
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
arXiv:2605.30833v1 Announce Type: new Abstract: On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identify a critical bottleneck, \textbf{Supervision Fidelity Decay (SFD)}: as student-generated prefixes lengthen, the teacher's next-token distribution becomes less confident and less discriminative. Consequently, the teacher-dependent corrective signal in reverse-KL...
Characterizing the energy resolution of the MicroBooNE LArTPC at the MeV scale using monoenergetic features of $^{208}$Tl decays
arXiv:2605.30709v1 Announce Type: new Abstract: A detailed understanding of the capabilities and fidelity of low-energy reconstruction is crucial for taking advantage of MeV-scale neutrino physics opportunities in liquid argon time projection chambers (LArTPCs). This study presents a measurement of the resolution of reconstructed energy in the MicroBooNE LArTPC at $\approx 1.5$ MeV. The characterization is performed using monoenergetic signals generated by $2.614$ MeV $\gamma$-rays from...
A variable-coefficient model for decay of isotropic turbulence capturing effects of finite cascade time and Reynolds number
arXiv:2606.03642v1 Announce Type: new Abstract: We study isotropic turbulence decay in the context of the k-epsilon model, which solves the dissipation and kinetic energy equations. In modeling the dissipation equation, the coefficient C_epsilon2, suggested by Hanjalic and Launder [Journal of Fluid Mechanics, 1972]
WildCat: Near-Linear Attention in Theory and Practice
arXiv:2602.10056v2 Announce Type: replace Abstract: We introduce WildCat, a high-accuracy, low-cost approach to compressing the attention mechanism in neural networks. While attention is a staple of modern network architectures, it is also notoriously expensive to deploy due to resource requirements that scale quadratically with the input sequence length $n$. WildCat avoids these quadratic costs by only attending over a small weighted coreset. Crucially, we select the coreset using a fast...
From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing
Announce Type: new Abstract: Rule-following agents tasked with executing policies and regulations often fail via Silent Scope Omission (SSO): a model applies a general rule but silently drops nested exceptions or counter-exceptions, producing outputs that appear compliant yet break on important edge cases. Although such failures are often framed as an agentic-systems problem, the underlying bottleneck is statutory and policy understanding, a capability typically studied in legal NLP....
Prisma-World: Camera-Controllable Multi-Agent Video World Model
arXiv:2606.09507v1 Announce Type: new Abstract: Video world models have made rapid progress in generating controllable visual experiences, but most of them still simulate the world from a single observer. Extending such models to multiple agents raises a central challenge: if each agent's future state is generated independently, overlapping views may instantiate different versions of the same scene, leading to inconsistent objects, layouts, and appearances across agents. Conventional camera...
LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization
Announce Type: new Abstract: Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work. We present LeanMarathon, a multi-agent harness for reliable research-level Lean autoformalization. Its core abstraction is an evolving blueprint: a Lean file that serves simultaneously as formal proof skeleton, natural-language proof graph, and shared system of record.
Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting
arXiv:2606.02661v1 Announce Type: cross Abstract: Accurate precipitation nowcasting is vital for disaster mitigation, but deep learning methods face a key trade-off: regression models produce over-smoothed, spectrally decaying predictions that blur convective details and violate turbulence power laws; diffusion models generate realistic yet unanchored hallucinations lacking physical grounding. We propose Spectral-Decoupled Iterative Refinement (SDIR), a deterministic framework that...
Scale-Adaptive Generative Flows for Multiscale Scientific Data
arXiv:2509.02971v2 Announce Type: replace-cross Abstract: Flow-based generative models can face numerical challenges on scientific data with multiscale Fourier spectra, often producing large errors at fine scales. We approach this problem within the flow matching and stochastic interpolants framework, through the principled design of noise distributions and interpolation schedules. Working in function space ensures that the generative model remains well defined as the resolution is refined;...
Couple separated, lived 15 years apart: SC says amounts to cruelty to both
The Supreme Court has directed that a prolonged period of separation between spouses, with the absence of any genuine effort to rebuild the marriage, can amount to mental cruelty and it becomes a valid ground for divorce under the Hindu Marriage Act. The judgment came in a case where the couple, both doctors in government service had been living separately for over 15 years after a marriage that lasted barely two to three months of actual cohabitation. The Supreme Court upheld the divorce...