SMC forgets its initial condition geometrically in the jump chain and as 1/ℓ in continuous genetic distance, justifying independent-locus approximations.
hub
The computational limits of deep learning
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Quantum neural networks exhibit membership privacy leakage that a proposed quantum machine unlearning framework with three mechanisms can mitigate in simulations and cloud device tests.
RBDC trains wide vision models by recursive block-diagonal coupling of narrower pre-trained models, reducing training FLOPs by 30% at similar ImageNet accuracy for DeiT and ResNet while outperforming model growth baselines.
DUET is a photonic tensor core paradigm that uses structural symmetry in VODICs to support arbitrary signed operands directly, experimentally tested on image classification, segmentation, and Transformer tasks.
MoHGE achieves standard MoE performance with 20% fewer parameters and balanced GPU utilization via grouped heterogeneous experts, two-level routing, and specialized auxiliary losses.
STRIDe cross-coupled STT-MRAM improves sense margin up to 3.86x and read disturb margin up to 27.6% for XNOR and AND IMC, achieving near-software DNN inference accuracy on CIFAR10 despite process variations.
Dense ReLU networks under natural weight and dimension constraints fail to approximate certain Lipschitz functions, unlike unrestricted networks.
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.
The paper introduces OptiLookUp, a reconfigurable photonic ROM using integrated microring resonators in banked sub-arrays with optical decoding and transistor selectors, simulated on GlobalFoundries 45SPCLO platform to operate at 12.5 GHz for activation functions.
Blockchain and AI integration for network security has strong conceptual fit but mostly prototype-level evidence; the paper offers a taxonomy, integration patterns, and the BASE evaluation checklist to organize the field.
The authors cast auxiliary-loss-free load balancing as a primal-dual assignment solver, prove structural properties in deterministic and online regimes, and report experiments on 1B-parameter DeepSeekMoE models.
A system using auto-relational reasoning solves IQ test problems at 98.03% rate without any prior knowledge, reaching top 1% human performance.
Position paper claiming that distributed training across massive edge devices can overcome data depletion and centralized compute monopolies in LLM scaling.
citing papers explorer
-
Rates of forgetting for the sequentially Markov coalescent
SMC forgets its initial condition geometrically in the jump chain and as 1/ℓ in continuous genetic distance, justifying independent-locus approximations.
-
From Membership-Privacy Leakage to Quantum Machine Unlearning
Quantum neural networks exhibit membership privacy leakage that a proposed quantum machine unlearning framework with three mechanisms can mitigate in simulations and cloud device tests.
-
Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models
RBDC trains wide vision models by recursive block-diagonal coupling of narrower pre-trained models, reducing training FLOPs by 30% at similar ImageNet accuracy for DeiT and ResNet while outperforming model growth baselines.
-
General-Purpose Photonic Computing Primitive for Contemporary Artificial Intelligence
DUET is a photonic tensor core paradigm that uses structural symmetry in VODICs to support arbitrary signed operands directly, experimentally tested on image classification, segmentation, and Transformer tasks.
-
Mixture of Heterogeneous Grouped Experts for Language Modeling
MoHGE achieves standard MoE performance with 20% fewer parameters and balanced GPU utilization via grouped heterogeneous experts, two-level routing, and specialized auxiliary losses.
-
STRIDe: Cross-Coupled STT-MRAM Enabling Robust In-Memory-Computing for Deep Neural Network Accelerators
STRIDe cross-coupled STT-MRAM improves sense margin up to 3.86x and read disturb margin up to 27.6% for XNOR and AND IMC, achieving near-software DNN inference accuracy on CIFAR10 despite process variations.
-
Neural Networks With Dense Weights Are Not Universal Approximators
Dense ReLU networks under natural weight and dimension constraints fail to approximate certain Lipschitz functions, unlike unrestricted networks.
-
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
-
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.
-
OptiLookUp: An Optical ROM-Based Lookup Table Engine for Photonic Accelerators
The paper introduces OptiLookUp, a reconfigurable photonic ROM using integrated microring resonators in banked sub-arrays with optical decoding and transistor selectors, simulated on GlobalFoundries 45SPCLO platform to operate at 12.5 GHz for activation functions.
-
Blockchain and AI: Securing Intelligent Networks for the Future
Blockchain and AI integration for network security has strong conceptual fit but mostly prototype-level evidence; the paper offers a taxonomy, integration patterns, and the BASE evaluation checklist to organize the field.
-
A Theoretical Framework for Auxiliary-Loss-Free Load Balancing of Sparse Mixture-of-Experts in Large-Scale AI Models
The authors cast auxiliary-loss-free load balancing as a primal-dual assignment solver, prove structural properties in deterministic and online regimes, and report experiments on 1B-parameter DeepSeekMoE models.
-
Auto-Relational Reasoning
A system using auto-relational reasoning solves IQ test problems at 98.03% rate without any prior knowledge, reaching top 1% human performance.
-
Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices
Position paper claiming that distributed training across massive edge devices can overcome data depletion and centralized compute monopolies in LLM scaling.