Related papers: The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness

Related papers

$\mathbfλ$-VAE: Variance Equalization for Posterior Collapse [0.0]
Variational Autoencoders (VAEs) frequently suffer from posterior collapse, a failure mode in which the approximate posterior converges to the prior.<n>We identify and formalize two logically independent but coupled causes.
arXiv Detail & Related papers (2026-07-06T18:07:46Z)
Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders [9.291632832739822]
We introduce two sparsity regularizers compatible with the Top-$k$ architecture.<n>Our central finding is that hard architectural sparsity and soft sparsity regularization are complementary rather than mutually exclusive.
arXiv Detail & Related papers (2026-06-25T17:34:39Z)
Hidden-State Privacy Has an Empty Middle [51.56484100374058]
We prove a complementary Fisher-ball lower bound: every full-rank Gaussian release at $O(1)$ Fisher utility admits a direction whose Mahalanobis signal grows linearly in hidden width.<n>A split-memory transformer trained from scratch reaches $G_mathrmMah in [20, 33]$ at 90M and maintains a $6$--$24times$ advantage over same-budget GPT baselines from 30M to 1B at a fixed-token language loss penalty.
arXiv Detail & Related papers (2026-05-21T20:12:09Z)
Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons [27.855778669417592]
Cortical neurons are complex, multi-timescale processors wired into recurrent circuits.<n>Machine learning predominantly builds models extremely simple units, a default inherited from early neural-network theory.<n>We introduce the ELM Network, whose recurrent layer is built from Expressive Memory (ELM) neurons.
arXiv Detail & Related papers (2026-05-12T12:29:33Z)
Learning Hippo: Multi-attractor Dynamics and Stability Effects in a Biologically Detailed CA3 Extension of Hopfield Networks [0.0]
We present a biologically detailed extension of the classical Hopfield/Marr auto-associative memory model for CA3.<n>We implement ten populations (two asymmetric pyramidal subtypes, eight GABAergic interneuron classes), forty-seven compartments, multi-rule plasticity, and a bimodal cholinergic encoding/consolidation cycle.
arXiv Detail & Related papers (2026-04-22T15:28:17Z)
DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks [54.32016216994156]
We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise.<n>To overcome memory scaling, CLWM features a Dual-State Test-Time Training (TTT) Memory that guarantees a strict $mathcalO(1)$ footprint for long-horizon tasks.<n>We present EmbodiChain, an online framework that establishes the Efficiency Law by injecting an infinite flow of physics-grounded trajectories during training.
arXiv Detail & Related papers (2026-04-13T03:19:36Z)
Persistent Memory Through Triple-Loop Consolidation in a Non-Gradient Dissipative Cognitive Architecture [0.0]
We introduce Deep Memory, a non-gradient persistent memory mechanism operating through a triple-loop consolidation cycle.<n>We demonstrate that discrete expert routing via Mixture-of-Experts (MoE) gating is a causal prerequisite for DM.<n>These results establish DM as a falsifiable mechanism for persistent memory in non-gradient cognitive systems, with functional parallels to hippocampal consolidation.
arXiv Detail & Related papers (2026-03-28T08:29:48Z)
Body-Reservoir Governance in Repeated Games: Embodied Decision-Making, Dynamic Sentinel Adaptation, and Complexity-Regularized Optimization [0.0]
We propose a three-layer Body-Reservoir Governance architecture.<n> Strategy complexity cost is defined as the KL divergence between the reservoir's state distribution and its habituated baseline.<n>Body governance reduces this cost, with action variance decreasing up to $1600times$ with dimension $d$.<n>Overriding the body incurs thermodynamic cost proportional to internal state distortion.
arXiv Detail & Related papers (2026-02-24T12:36:41Z)
R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training [65.13759782915164]
Self-play LLM reasoning through an iterative Challenger bootstrapr loop.<n>R-Diverse sustains gains over more iterations and consistently outperforms prior self-play methods.
arXiv Detail & Related papers (2026-02-13T17:07:42Z)
INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
arXiv Detail & Related papers (2025-11-16T20:14:28Z)
Multiscale Astrocyte Network Calcium Dynamics for Biologically Plausible Intelligence in Anomaly Detection [0.48700127614643884]
Ca$2+$-modulated learning framework draws inspiration from astrocytic Ca$2+$ signaling in the brain.<n>Our approach couples a multicellular astrocyte dynamics simulator with a deep neural network (DNN)
arXiv Detail & Related papers (2025-11-06T02:24:51Z)
Discovery of Fatigue Strength Models via Feature Engineering and automated eXplainable Machine Learning applied to the welded Transverse Stiffener [0.0]
This research introduces a unified approach combining Automated Machine Learning (AutoML) with Explainable Artificial Intelligence (XAI)<n>It integrates expert-driven feature engineering with algorithmic feature creation to enhance accuracy and explainability.<n>It bridges data-driven modeling with engineering validation, enabling AI-assisted design and assessment.
arXiv Detail & Related papers (2025-07-01T21:57:12Z)
Tensor Decomposition Networks for Fast Machine Learning Interatomic Potential Computations [63.945006006152035]
tensor decomposition networks (TDNs) achieve competitive performance with dramatic speedup in computations.<n>We evaluate TDNs on PubChemQCR, a newly curated molecular relaxation dataset containing 105 million DFT-calculated snapshots.
arXiv Detail & Related papers (2025-07-01T18:46:27Z)
Policy-Based Radiative Transfer: Solving the $2$-Level Atom Non-LTE Problem using Soft Actor-Critic Reinforcement Learning [0.0]
We present a novel reinforcement learning (RL) approach for solving the classical 2-level atom non-LTE radiative transfer problem.<n>The agent's policy is optimized entirely via reward-based interactions with a radiative transfer engine.<n>We show through experiment that a simple feedforward neural network trained greedily cannot solve for SE, possibly due to the moving target nature of the problem.
arXiv Detail & Related papers (2025-04-22T08:03:09Z)
UniF$^2$ace: A Unified Fine-grained Face Understanding and Generation Model [62.66515621965686]
We introduce a novel theoretical framework with a Dual Discrete Diffusion (D3Diff) loss, unifying masked generative models with discrete score matching diffusion.<n>This D3Diff significantly enhances the model's ability to synthesize high-fidelity facial details aligned with text input.<n>We construct UniF$2$aceD-1M, a large-scale dataset comprising 130K fine-grained image-caption pairs and 1M visual question-answering pairs.
arXiv Detail & Related papers (2025-03-11T07:34:59Z)
Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls [83.89771461061903]
Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>We identify two key challenges contributing to this inefficiency: $textitover-exploration$ due to redundant states with semantically equivalent content, and $textitunder-exploration$ caused by high variance in verifier scoring.<n>We propose FETCH, a flexible, plug-and-play system compatible with various tree search algorithms.
arXiv Detail & Related papers (2025-02-16T16:12:01Z)
Simple ReFlow: Improved Techniques for Fast Flow Models [68.32300636049008]
Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps. We propose seven improvements for training dynamics, learning and inference. We achieve state-of-the-art FID scores (without / with guidance, resp.) for fast generation via neural ODEs.
arXiv Detail & Related papers (2024-10-10T11:00:55Z)
On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [58.79302663733703]
Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents.<n>The impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored.<n>This paper investigates what is the resilience of various system structures under faulty agents on different downstream tasks.
arXiv Detail & Related papers (2024-08-02T03:25:20Z)
Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression [21.849997443967705]
Two-layer regression problem has been well-studied in prior works. First layer is activated by a ReLU unit, and the second layer is activated by a softmax unit. We prove that the loss function for the Hessian matrix is positive definite and Lipschitz continuous under certain assumptions.
arXiv Detail & Related papers (2023-11-26T19:19:02Z)
A Unified Scheme of ResNet and Softmax [8.556540804058203]
We provide a theoretical analysis of the regression problem: $| langle exp(Ax) + A x, bf 1_n rangle-1 ( exp(Ax) + Ax ) This regression problem is a unified scheme that combines softmax regression and ResNet, which has never been done before.
arXiv Detail & Related papers (2023-09-23T21:41:01Z)
Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards [33.88533898709351]
VIPeR amalgamates the randomized value function idea with the pessimism principle. It implicitly obtains pessimism by simply perturbing the offline data multiple times. It is both provably and computationally efficient in general Markov decision processes (MDPs) with neural network function approximation.
arXiv Detail & Related papers (2023-02-24T17:52:12Z)
Spatially heterogeneous learning by a deep student machine [0.0]
Deep neural networks (DNN) with a huge number of adjustable parameters remain largely black boxes. We study supervised learning by a DNN of width $N$ and depth $L$ consisting of $NL$ perceptrons with $c$ inputs by a statistical mechanics approach called the teacher-student setting. We show that the problem becomes exactly solvable in what we call as 'dense limit': $N gg c gg 1$ and $M gg 1$ with fixed $alpha=M/c$ using the replica method developed in (H. Yoshino, (
arXiv Detail & Related papers (2023-02-15T01:09:03Z)
Improved Convergence Guarantees for Shallow Neural Networks [91.3755431537592]
We prove convergence of depth 2 neural networks, trained via gradient descent, to a global minimum. Our model has the following features: regression with quadratic loss function, fully connected feedforward architecture, RelU activations, Gaussian data instances, adversarial labels. They strongly suggest that, at least in our model, the convergence phenomenon extends well beyond the NTK regime''
arXiv Detail & Related papers (2022-12-05T14:47:52Z)
Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
arXiv Detail & Related papers (2021-07-08T18:01:02Z)
Improved Sample Complexity for Incremental Autonomous Exploration in MDPs [132.88757893161699]
We learn the set of $epsilon$-optimal goal-conditioned policies attaining all states that are incrementally reachable within $L$ steps. DisCo is the first algorithm that can return an $epsilon/c_min$-optimal policy for any cost-sensitive shortest-path problem.
arXiv Detail & Related papers (2020-12-29T14:06:09Z)
Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
arXiv Detail & Related papers (2020-10-01T17:51:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.