Layer 2
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent
arXiv:2606.02596v1 Announce Type: new Abstract: The curvature exponent $\alpha$ in $h_k \propto \sigma_k^\alpha$ -- governing how Hessian eigenvalues scale with gradient singular values -- varies systematically across layer types ($\alpha \approx 2$ for convolutions, $\approx 1$ for transformer attention, $< 1$ for MLP up-projections). We prove the Spectral Alignment Decomposition: $\alpha = 2 + d\log\Phi_k / d\log\sigma_k$, where $\Phi_k$ measures alignment between Kronecker factor...
$p$-Robust Trace Liftings for Discrete Harmonic Extensions and Boundary-Preserving $hp$ Interpolation on Tetrahedral Meshes
arXiv:2606.02086v1 Announce Type: new Abstract: We construct p-robust polynomial trace liftings on three-dimensional tetrahedral meshes. The prescribed trace is a continuous piecewise polynomial function on a boundary face patch; the tetrahedra touching this patch have one common degree, while the interior degrees may be arbitrary. The lifting is degree-preserving, supported in the corresponding boundary layer, and satisfies both an H^1 estimate and a scaled boundary-layer L^2 estimate with...
A Visible-Frequency Excitonic Reststrahlen Band in (PEA)$_2$PbI$_4$ Slabs
Announce Type: cross Abstract: Layered halide perovskites host exceptionally strong excitons, whose optical signatures are usually interpreted as absorptive resonances on a smooth dielectric background. Strong excitons, however, can also reshape the dielectric response itself and drive the real permittivity negative, opening a reflective band: the visible, excitonic analogue of an infrared Reststrahlen band. Whether bare (PEA)$_2$PbI$_4$ slabs reach this regime has remained unclear.
Archaeologists uncover centuries of history beneath Notre-Dame square
Archaeologists at Notre-Dame Cathedral are unconvering Roman relics and medieval ruins as Paris digs 4m deep to create a greener square by 2028. Tourists queue in the heat outside Paris’ Notre-Dame Cathedral, while just metres below them, archaeologists are digging into centuries of history. Four metres beneath the forecourt, a team is uncovering layers of history stretching back nearly 2,000 years, from medieval Paris to the Roman-era city once known as Lutetia.
A thalamus–brainstem attractor network drives history-biased decisions
Abstract Natural environments often change gradually, making it adaptive to bias decisions on the basis of the recent past — a phenomenon known as serial dependence1,2,3. Large-scale recordings during behaviour have identified that serial dependence is a common motif for decision-making, with neural representations of past experiences found throughout the brain4,5,6,7,8,9,10,11. However, it remains unclear whether this bias arises from dedicated neural circuits with history-specific...
Dielectric-Anisotropy-Induced Quasi-BIC Activation for Spatial Differentiation in All-Dielectric Metasurfaces
arXiv:2606.01983v1 Announce Type: new Abstract: Quasi-BICs in dielectric metasurfaces are typically obtained through geometric symmetry breaking. Here, a 20\,nm BeS insert is placed in the gap of a symmetric TiO$_2$ nanobar pair. The anisotropy of the BeS layer ($\Delta\varepsilon \approx 0.27$) relaxes the dipole-cancellation condition and gives rise to a quasi-BIC resonance.
Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data
arXiv:2606.04238v1 Announce Type: new Abstract: Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degradation. These gains are particularly relevant for edge and on-device deployment, where memory capacity and bandwidth are primary constraints. In this work, we extend Recover-LoRA -- a lightweight, data-free accuracy recovery method originally developed for general...
GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation
arXiv:2606.01412v1 Announce Type: new Abstract: Post-training quantization is widely used for compressing large neural networks, but aggressive low-bit quantization can significantly degrade model quality. A common remedy is to augment the quantized weights with a low-rank correction, leading to approximations of the form $W\approx Q+LR$. In this paper, we study this low-precision plus low-rank representation through the layer-wise reconstruction objective $\|XW-X(Q+LR)\|_F^2$, where $X$ is...
Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection
arXiv:2606.08403v1 Announce Type: new Abstract: Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views. We study a reproducible LLM01-style indirect prompt/content-injection failure mode where that assumption breaks: a payload caught in plain English slips past the same detector when it is transported as structured float parameters and reconstructed only as fragmented telemetry. Across 14,400 attacked real-model trials on three...
The Three-Ring Architecture: Governing Agents in the Era of On-Platform Organisations
arXiv:2606.07119v1 Announce Type: new Abstract: The current phase of enterprise AI deployment faces a structural failure: organisations are acquiring agentic capability without the infrastructure to govern it. The result is expected to reproduce the error of the first wave of AI deployment: decentralised intelligence without a federation layer leading to a 95% project failure rate. This paper formalises the Three-Ring Architecture as the governing infrastructure of the on-platform organisation.