The Archive

DiMuRe framework for robotic agents uses diagnosis-guided recovery with MLLMs to select task reuse or predefined skills when disturbances occur during execution.

Q64 candidate-scoring system reuses frozen Qwen3.8-27B document representations with adapted readout for repeated QA over shared context; developed via ZiYor.

Open-source LLMs fail on long retrieval tasks due to attention competition, not length; neutral filler preserves accuracy to 32K tokens.

Nonparametric neural estimator for GARCH-type processes with minimax-optimal finite-sample variance bounds.

GPT-6 Astra directly read and edited Qwen3.5-0.8B weights to improve math capability, demonstrating LLM weight manipulation.

Comments

Chain-of-Thought (CoT) generation has substantially improved the performance of Large Language Models (LLMs) on complex reasoning tasks, including code generation, data analysis, and exam-style question answering. Despite these advances, purely neural LLMs continue to struggle with elementary logical reasoning problems and lack the determinism, soundness, and reliability characteristic of symbolic reasoning systems. Conversely, classical symbolic methods such as SAT solving and exact cover guarantee correctness and completeness, but require problems to be expressed in highly specialized forma...

Communication is important for our well-being, but it can be impaired by disabilities, such as locked-in syndrome (LIS), cerebral palsy (CP), and dysarthria. Non-invasive brain-to-text brain-computer interfaces (BCIs) offer a promising solution by providing an alternative communication pathway for people with communication disabilities. However, most recent breakthroughs have relied on large, cumbersome, and costly neuroimaging modalities, such as functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG). Numerous studies have attempted decoding using the lighter and cheap...

A model is only half of an AI agent system. The other half is the inference strategy: the reasoning procedure that turns model calls into a response. Today that second half is written by hand, and the experience of building one strategy never carries to the next. We introduce Strategist, a meta-agent that evolves inference strategies across tasks. Each strategy is written as a blueprint,executable code that other strategies can reuse, and together the blueprints form a library. Given a task and a small development set, Strategist retrieves related blueprints, writes candidate strategies, test...

Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the human brain. We propose a structured visual representations landscape and design an activation-based prior that allows us to effectively regularize the landscape with activations from brain regions or neural network units. Our model Vis-Lens integrates a variational autoencoder and a diffusion model into an image gene...

Neural operators provide efficient surrogates for computational fluid dynamics (CFD), but most are designed for static geometries and are not equipped to model unsteady flows induced by continuously moving boundaries. We study dynamic-boundary 4D CFD prediction for articulated moving geometries and introduce RoboCFD-4D, a temporally resolved robotic CFD benchmark spanning diverse morphologies and flow conditions. To address the computational and autoregressive challenges of this setting, we propose DynaSolver, a neural operator that explicitly conditions on boundary evolution and causal flow ...

We present a variational functional neural network (vfNN) algorithm that optimizes physically motivated continuum functionals in integral form (e.g., Lagrangian, Hamiltonian, or free energy) to find the states of a system. That way, vfNN bypasses solving the equations of motion (a.k.a. the Euler-Lagrange equations), which are in the form of differential equations. To this end, our approach is fundamentally different from conventional physics-informed neural networks (PINN) that solve differential equations by minimizing a phenomenological loss function involving higher order derivatives and a...

Skin cancer diagnosis, particularly differentiating melanoma from benign nevi, is challenging due to the visual similarity between lesions. Although convolutional neural networks (CNNs) and vision transformers (ViTs) have shown promising performance, their effectiveness often deteriorates on data from heterogeneous clinical sources. Conventional domain adaptation methods address domain shift but require access to source data during adaptation, which is often infeasible due to privacy regulations. Multi-source-free unsupervised domain adaptation (MSFDA) addresses this limitation by leveraging ...

Computer programmers chain together the same reusable computational primitives, for example, conditional statements or loops, but in different orders to implement different algorithms. In contrast, existing language model architectures always execute their layers in the same order. We introduce Library of Layers (LoL), an architecture that dynamically orders its layers during inference to solve the problem at hand. LoL has a single hyperparameter, the size of its global library of transformer blocks, that allows it to transition seamlessly between parameter reuse and sparsity, generalizing th...

Matrix multiplication dominates both PHY signal processing and Deep Neural Network (DNN) inference, yet these domains place opposing demands on the matrix engine. Signal processing requires low-latency execution of relatively small matrix operations, whereas DNN inference, particularly at large batch sizes, prioritizes high throughput and energy efficiency for large matrix multiplications. While offering efficient memory access profile, a Systolic Array (SA) adds fill and drain delays per matrix. Those can be amortized for large matrices but not for small matrices. Conversely, a tensor unit c...

The shear piezoelectric coefficient $e_{15}$ governs the shear-mode electromechanical coupling in piezoelectric micromachined ultrasonic transducers (PMUTs) and surface acoustic wave (SAW) devices, but measuring it typically requires destructive resonance testing on dedicated specimens. On simulated data, $e_{15}$ can instead be recovered non-destructively from sparse, noisy subsurface wavefield observations using a constrained physics-informed neural network (PINN). By building exact spatial distance functions and temporal multipliers directly into the network output, the clamped, grounded b...

Hybrid models and neural differential equations (NDEs) are becoming increasingly important for modelling physical systems; however, they often encounter stability and accuracy issues during long-term integration. Training on unrolled trajectories is known to limit these divergences but quickly becomes too computationally expensive due to the need to compute gradients over an iterative process, making this method impractical for large-scale physical systems (e.g. weather and climate forecasting). Two popular paradigms for improving the stability of learned dynamics are to train on interpolated...

Hamiltonian neural networks provide a principled framework for learning conservative dynamics. A scalar Hamiltonian is parameterized by a neural network and the vector field is derived using Hamilton's equations. However, preserving Hamiltonian structure does not guarantee that the energy function itself is represented accurately. When modeled by a conventional multilayer perceptron, the Hamiltonian inherits the spectral bias of coordinate-based neural representations, favoring smooth over fine-scale structure. These fine-scale errors can be amplified by differentiation when computing the dyn...

Despite their widespread success across machine learning, the learning dynamics and generalization properties of neural networks remain poorly understood. The neural tangent kernel (NTK) provides an analytical characterization of the learning dynamics of infinitely wide neural networks and serves as a useful proxy for finite-width networks in supervised learning. In this work, we extend the NTK framework to reinforcement learning (RL) by introducing a temporal-difference (TD) flow formulation that accommodates time-varying mini-batches and TD targets, yielding a closed-form solution for value...

Putin mandates Russian data center operators reserve 10% capacity for state IT infrastructure following Ukrainian drone strikes.

ComplianceAtlas automates EU AI Act compliance auditing for high-risk systems using agentic taxonomy-driven gap analysis and remediation.

Graph neural network beamforming for MIMO ISAC systems under CSI errors and clutter uncertainty; domain-specific telecom infrastructure.

Marvell acquires Lumentum for $115B to compete with Broadcom in optical networking; Nvidia holds stakes in both.

Self-supervised video diffusion method synthesizes pseudo-labels from single images to preserve identity in pose-driven generation.

PlagiaCorpus: 198K Arabic-English dataset for detecting LLM-generated plagiarism and cross-lingual reuse across five difficulty levels.

Anthropic plans $3.5B funding round from Japanese investors as part of US IPO.

South Korea pledges $15.97B for AI, semiconductors, robotics, and data centers in 2027 budget—double 2026 spending.

Framework for explainability in neural auction mechanisms via decision rule mapping for auditability.

LegoEnv framework enables agents to learn across self-evolving tasks by composing and reusing modular environment components.