arXiv:2608.05996v1 Announce Type: cross Abstract: Deep Belief Networks (DBNs) learn hierarchical generative models without class supervision. Here, we ask whether this purely unsupervised process nevertheless organizes…
arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long…
arXiv:2604.08894v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs). However, they encounter significant deficiencies in training and…
arXiv:2608.06177v1 Announce Type: cross Abstract: Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference. For binary activations, the dot products…
arXiv:2607.07144v2 Announce Type: replace Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through…
arXiv:2608.05358v1 Announce Type: new Abstract: Federated learning repeatedly incurs local optimization and model-update transmission. We study DG-FedReuse, a simulator-level mechanism that allows selected clients to contribute…
arXiv:2603.12617v2 Announce Type: replace Abstract: Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model rapidly…
arXiv:2608.05326v1 Announce Type: new Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of…
arXiv:2509.03206v2 Announce Type: replace Abstract: Learning from reward functions and imitation learning of demonstrations are the two principal approaches for training autonomous systems that interact with…
arXiv:2608.05315v1 Announce Type: new Abstract: Electroencephalography (EEG) based Brain-Computer Interfaces (BCIs) often require unsupervised domain adaptation (UDA) to generalize across subjects and sessions. While Riemannian alignment…
arXiv:2608.06250v1 Announce Type: cross Abstract: In overparameterised classification, training data can be linearly separable even when the underlying distribution is not. In this setting, gradient descent…
arXiv:2608.05265v1 Announce Type: new Abstract: Prediction of post-wildfire debris flows is critical for mitigating hazards to communities, infrastructure, and resources during intense rainfall in recently burned…
arXiv:2608.05949v1 Announce Type: cross Abstract: Vision Language Models (VLMs) and Artificial Intelligence (AI) agents have revolutionized how engineers approach complex problems in real-world applications. Their adoption…
arXiv:2608.05255v1 Announce Type: new Abstract: Retail investors lack access to the kind of personalized, tax-aware portfolio management that institutional clients take for granted -- existing robo-advisors…
arXiv:2608.04549v2 Announce Type: replace-cross Abstract: Frontier LLMs are increasingly put to use on open-ended complex questions, different in nature from the ones they are typically evaluated…
arXiv:2608.05234v1 Announce Type: new Abstract: Building reliable applications that leverage large language models (LLMs) remains a significant challenge. While LLMs offer impressive capabilities across diverse tasks,…
arXiv:2608.05238v1 Announce Type: new Abstract: Training multimodal models to align time series with language runs into a self-supervision trap. The usual recipe asks an LLM to…
arXiv:2608.05242v1 Announce Type: new Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly…
arXiv:2608.05249v1 Announce Type: new Abstract: Real-world multimodal instructions often bundle multiple requirements with unequal importance, yet most multimodal training data still reduce instruction following to answering…
arXiv:2608.05243v1 Announce Type: new Abstract: Factorized generative models commonly regularize a latent style variable z_s by matching its marginal distribution to a fixed Gaussian prior and…
arXiv:2608.05253v1 Announce Type: new Abstract: Quantized orthogonal fine-tuning (qoft) enables parameter-efficient adaptation of low-bit language models by learning structured activation rotations before frozen quantized weights. However,…
arXiv:2608.05250v1 Announce Type: new Abstract: Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach…
arXiv:2608.06366v1 Announce Type: cross Abstract: Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists'…
arXiv:2608.06130v1 Announce Type: cross Abstract: AI agents performing cryptographic operations (signing Git commits, authenticating API calls, issuing certificates) currently store private keys in software-accessible locations: plaintext…