Ferroelectric and Negative Capacitance Devices

Derniers papiers

• Derandomizing Dense Binary Hypervector Codebooks for Quantized Scalars

  Dmitri Rachkovskij, Evgeny Osipov, Olexander Volkov, Denis Kleyko, Vaclav Snasel · 1 octobre 2026

  Hyperdimensional computing and vector symbolic architectures often represent quantized scalar levels by dense binary codebooks whose level-to-level similarity is intended to follow a prescribed function of scalar separation. At finite dimensionality, randomized scalar codebook constructions deviate …

• Superposed Inference for Hyperdimensional Computing

  Quanling Zhao, Nilesh Prasad Pandey, Ye Tian, Tajana Rosing · 29 septembre 2026

  Hyperdimensional computing (HDC) is attractive for efficient and robust learning, but conventional inference still encodes every query independently, repeatedly paying the cost of high-dimensional projection. We introduce SupHDC, a new inference paradigm that processes multiple queries through a sha…

• hyperbolix: Hyperbolic Deep Learning in JAX

  Timo Klein, Thomas Lang, Yllka Velaj, Sebastian Tschiatschek · 24 septembre 2026

  We present hyperbolix, an open-source library for hyperbolic deep learning in JAX, built on Flax NNX. To our knowledge, it is the first comprehensive, general-purpose hyperbolic deep learning library in JAX. It includes six manifolds with a common interface: Euclidean space, the Poincar\'e ball, the…

• Geometry-Aware Hyperbolic Residual Quantization

  Alessio Colombo, Melika Ayoughi · 23 septembre 2026

  Residual Vector Quantization turns continuous representations into discrete, multi-level token sequences. Yet most methods operate in Euclidean space, despite the coarse-to-fine structure of the resulting codes and the latent hierarchies present in many data domains. Hyperbolic geometry offers a nat…

• NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis

  Wuche Liu, Yiran Qiao, Linlin Hou, Rui Yang, Shusen Pu, Song Wang, Jing Ma · 14 septembre 2026

  AI is rapidly advancing neuroscience, yet many laboratories fail to fully unleash its potential due to significant interdisciplinary barriers. While pre-trained neural models for physiological data are progressing quickly, their heterogeneous architectures and modality-specific constraints hinder sy…

• BiHDTrans: binary hyperdimensional transformer for efficient multivariate time series classification

  Jingtao Zhang, Yi Liu, Qi Shen, Changhong Wang · 11 septembre 2026

  The proliferation of Internet-of-Things (IoT) devices has led to an unprecedented volume of multivariate time series (MTS) data, requiring efficient and accurate processing for timely decision-making in resource-constrained edge environments. Hyperdimensional (HD) computing, with its inherent effici…

• Take What You Need: Flexible Multi-Task Semantic Communications with Channel Adaptation

  Xiang Chen, Shuying Gan, Chenyuan Feng, Xijun Wang, Tony Q. S. Quek · 10 septembre 2026

  The growing demand for efficient semantic communication systems capable of managing diverse tasks and adapting to fluctuating channel conditions has driven the development of robust, resource-efficient frameworks. This article introduces a novel channel-adaptive and multi-task-aware semantic communi…

• A Hub of Short Rows Inflates Intrinsic Dimension Estimation of Token Embeddings

  Alexandre Quemy · 1 septembre 2026

  A token-embedding table holds a hub of short rows near its origin, and we show that this cluster biases what nearest-neighbor intrinsic-dimension (ID) estimators report. Because of the concentration of measure, a token is closer to the central cluster than to any other token, so its first two neighb…

• Real-Valued Hyperdimensional Sequence Representations with Hadamard Product Binding and Shift Equivariance

  Kenny Schlegel, Dmitri A. Rachkovskij, Denis Kleyko, Amy Loutfi, Stefan Streif, Evgeny Osipov · 31 août 2026

  Encoding temporal order is a fundamental requirement for sequence representations in Hyperdimensional Computing. Fractional Power Encoding provides similarity-preserving position vectors whose inner products approximate shift-invariant kernels, and it supports shift-equivariant transformations of en…

• HCC+: Hyperbolic Guarding for Certified Attention Retrieval

  Liangchen Ge · 27 août 2026

  We study the Lipschitz stability of attention retrieval in hyperbolic spaces. Existing methods lack deterministic guarantees on attention-weight preservation under finite-precision representations. We introduce HCC+, a theoretical framework exploiting three properties of the Poincar\'e ball: exponen…

• Hyper^2: Unleashing Hyperbolic Geometry's Full Potential via Dual-Space Consistency

  Guantian Zheng, Haiyang Xu, Tianyu Gao · 25 août 2026

  HyperbolicCD pioneered hyperbolic geometry for point cloud completion by replacing the Euclidean Chamfer distance with arcosh(1+alpha||x-y||^2), but the reported gains are modest (3-7% Chamfer reduction across SeedFormer, PointAttN and PMP-Net backbones on PCN and ShapeNet-55). We argue the bottlene…

• Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization Selects

  Xin Xu · 25 août 2026

  Reasoning shortcuts are rule solutions that reach correct predictions through unintended concepts. A recent framework of Takemura, Inoue, and Nishino analyzes them through an automorphism group of value relabelings, asking when rules pin concepts down. Its key definition, one value permutation share…

• Subtract, Transport, or Replay? Auditable Deletion from Language-Model Memory

  Vishwajith Ramesh · 14 août 2026

  Exact deletion from persistent language-model memory depends on whether a record's effect remains addressable after later computation. Native Kimi Delta Attention (KDA) gives a negative result for the tested receipt interface: the corpus-pooled raw recurrent contribution changes by 12-49% with the s…

• Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

  Zunhai Su, Bohan Sun, Xialie Zhuang, Shuibai Zhang, He Xiao, Jing Xiong, Hengyuan Zhang, Zhongzhu Zhou, Tiantian Zhang, Ngai Wong, Chuan-Wei Kuo · 13 août 2026

  We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two architecture-aligned morphologies: MAs consistently spike immediately before full attention layers, forming pre-attention spikes (PAS), and can persist through intervening linear attentio…

• HYDRA: Hyperbolic Dynamic Representation Architecture for Kolmogorov-Arnold Networks

  Zhao Su, Yuxin Xia, Haoran Li, Jun Shen, Qi Zhu, Qingguo Zhou, Binbin Yong · 13 août 2026

  Kolmogorov-Arnold Networks (KANs) enhance nonlinear function approximation by replacing scalar weights with learnable univariate functions. However, assigning an independent function to every connection results in substantial parameter redundancy, limiting their scalability and efficiency. To reduce…

• Riemann GeoResolver: A Non-Euclidean Attention Framework from Euclidean Resolver to Hyperbolic-Spherical Geometry

  Liangchen Ge · 12 août 2026

  We present a theoretical foundation for inverse-distance attention, from its Euclidean prototype (Resolver) to its non-Euclidean realization (Riemann GeoResolver). The Euclidean part establishes three core theorems: (1) circuit separation---IDA achieves exact retrieval with $\mathcal{O}(1)$ resource…

• Bridging the Gap Between Hyperdimensional Computing and Kernel Methods via the Nystr\"om Method

  Quanling Zhao, Anthony Hitchcock Thomas, Ari Brin, Xiaofan Yu, Tajana Rosing · 10 août 2026

  Hyperdimensional computing (HDC) is an approach from the cognitive science literature for solving information processing tasks using data represented as high-dimensional random vectors. The technique has a rigorous mathematical backing, and is easy to implement in energy-efficient and highly paralle…

• Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems

  Kartikey Singh Bhandari, Aarya Wadhwani, Dhruv Kumar, Pratik Narang · 6 août 2026

  LLM agents that persist across sessions accumulate stored memories whose validity varies enormously by content type, yet existing memory architectures treat all memories as equally persistent and systematically contaminate retrieved context with outdated facts. We show that per-memory, type-conditio…

• Attention-based representations for multi-task computation

  Daniel Hsu, Mingyue Xu · 6 août 2026

  Multi-head attention layers produce vector representations that support multiple downstream tasks. We establish bounds on the number of heads required in two simple and concrete multi-task scenarios. In the first scenario, a vector representation is sought so that linear predictors can compute both …

• Designing a Good Virtual Node: Addressable and Cardinality-Preserving Global Memory for Message Passing Architectures

  F\'elix Marcoccia · 5 août 2026

  Virtual nodes give message-passing neural networks a simple global communication route, but the standard node--VN--node pipeline compresses the graph into one homogeneous state and broadcasts it identically to every node. Building on the Two-Radius analysis of Mishayev et al., we ask how auxiliary v…

• Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI

  Weilun Wang, Wantong Li · 4 août 2026

  Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory bottlenecks that limit scalability and deployment. In this paper, we propose Gram-Space, a compression framework that applies Gram-Schmidt orthogon…

• Bridging the Cognitive Gap: A Unified Memory Paradigm for 6G Agentic AI-RAN

  Xijun Wang, Zhaoyang Liu, Chenyuan Feng, Xiang Chen, Howard H. Yang, Tony Q. S. Quek · 4 août 2026

  As 6G evolves, the radio access network must transcend traditional automation to embrace agentic AI capable of perception, reasoning, and evolution. A fundamental cognitive gap persists in current disaggregated architectures, where interfaces force the physical layer to compress high-dimensional sta…

• On the Expressive Power of Sparse Geometric MPNNs

  Yonatan Sverdlov, Nadav Dym · 3 août 2026

  Motivated by applications in chemistry and other sciences, we study the expressive power of message-passing neural networks for geometric graphs, whose node features correspond to 3-dimensional positions. Recent work has shown that such models can separate generic pairs of non-isomorphic geometric g…

• The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale

  Wenhui Chen, Jianlin Chen, Ziyao Lin, Chi Man Vong · 3 août 2026

  The Platonic Representation Hypothesis (PRH) holds that as models scale, representations of heterogeneous networks converge toward a shared model of reality. We propose its sequel and boundary, the Capability Convergence Hypothesis (CCH): under a fixed per-token inference budget, representational co…

• SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series

  Giovanni B. Esposito, Francesco Antici, Daniele Cesarini, Andrea Bartolini · 28 juillet 2026

  Data centers and their compute nodes require accurate and flexible digital twins capable of modeling the complex interplay of workloads, environmental parameters, and physical metrics. Current machine learning approaches for HPC and its telemetry typically rely on a static subset of anonymous, fixed…