AIQB
ResearchOrdinary

Two $\operatorname{ReLU}$ Layers is All You Need

Source: arXiv·

Summary

We prove that every $\operatorname{ReLU}$ network can be exactly simulated by a $\operatorname{ReLU}$ network with two hidden layers. We present two proofs: one that is based on fillings in homological algebra and a direct combinatorial proof.
CategoryAI Research & Papers
TierOrdinary
Published
Indexed by AIQB
SourcearXiv
AIQB record IDintel-c25a01f06ad67706dde8074b
Read original source ↗View data sourceMore Research

Related stories

Matched by category, entity tags and source

ResearchOrdinary
Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs
Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond pixels: to animate a specific 3D asset and replay the animation in its 3D scene. For instance, a video model can show a mon…
Source: arXiv · NVIDIA
ResearchOrdinary
GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discovery
Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending them to domain-intensive mechanistic investigations remains challenging. Here, we present…
Source: arXiv
ResearchOrdinary
Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking
Dexterous multi-finger hands hold promise to unlock diverse skills like functional grasps, in-hand reorientation, and dynamic handover that the human-designed world assumes, yet existing learning recipes force a trade-off. Goal-reaching re…
Source: arXiv
ResearchOrdinary
UniWALM: Unified World Action Language Model for Embodied Robot Control
Motivated by the human ability to integrate experience across language, perception, and action, we introduce UniWALM, a unified world-action-language model that learns video, action, and language in a single shared representation, where ea…
Source: arXiv
ResearchOrdinary
Industrial ReMEmbR: Scaling Spatiotemporal Memory to Robot Fleets
Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs. For example, explaining recurring aisle blo…
Source: arXiv · NVIDIA
ResearchOrdinary
Planning under Noise with Neural Operators
Planning under uncertain control execution noise requires reliable feedback policies across diverse environments. We introduce Planning Under Noise (PUN), a neural operator that learns noise-aware value fields for planning in unseen geomet…
Source: arXiv
ResearchOrdinary
MindView: Benchmarking Generative Multi-View Spatial Intelligence
Spatial intelligence has recently been assessed through generative tasks such as spatially grounded image editing, yet language-guided generation of spatially consistent views from partial multi-view observations remains underexplored. We …
Source: arXiv
ResearchOrdinary
Adaptive Multi-Token Prediction: How far should we go?
Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. However, the best speculation horizon changes with context: longer drafts offer greater amorti…
Source: arXiv · Qwen / Llama
ResearchOrdinary
Efficient Edge-aware Attention Network for Graph Generation
Graph generative models commonly use graph-specific Transformer architectures to jointly update node and edge features. However, these architectures do not directly benefit from recent hardware-aware attention implementations, limiting the…
Source: arXiv
ResearchOrdinary
NarraSpace: Multimodal Scene-Grounded Evidence for Picture-Description Dementia Classification
Picture-description dementia classification uses a shared visual scene, but a transcript-level prediction alone does not identify the scene evidence underlying its inputs. NarraSpace links words and speech times to named picture elements a…
Source: arXiv