KITINet: KInetic Theory Inspired Inter-Channel Information Exchange for Residual Networks
cs.LG
Submitted: 2025-05-23
Updated: 2026-10-05
Terminology
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- DSMC: A Statistical Mechanics Perspective
- OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
- How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks
- Fourier Neural Operator for Parametric Partial Differential Equations
- Transformer for Partial Differential Equations' Operator Learning
- Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias
- Convergence of Gradient Descent with Small Initialization for Unregularized Matrix Completion
- Gradient Descent Quantizes ReLU Network Features
- Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
- ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models
- OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
- Learning Mesh-Based Simulation with Graph Networks
- Hamiltonian Generative Networks
- mHC: Manifold-Constrained Hyper-Connections
- An overview of condensation phenomenon in deep learning
- ChemLLM: A Chemical Large Language Model
- MegaMath: Pushing the Limits of Open Math Corpora
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks