pytorch_geometric — Graph Neural Network Library for PyTorch
transformerlab-appは、AI研究者に、ローカルハードウェアとGPUクラスタ間でモデルを平滑にトレーニング、評価、およびスケールさせることができる、オープンソースの研究環境です。
deep-learning
MLINFO COLLECTION
深層学習
記事一覧
28 / 45Behind Aggregate Scores: What Systematically Varying Arena-Hard's LLM Judge Reveals
LLM judges are used to determine which of two answers is better. Trusting these verdicts requires knowing how repeatable they are and how much they depend on the judge's instructions.
deep-learning
Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3
A generally intelligent system acquires new skills efficiently without requiring humans to redesign its software scaffold for every new task. Yet language models rarely act alone.
deep-learning
Why Bother Me Again? Benchmarking Personal Agent Memory for Interaction Preferences
Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction…
deep-learning
AVAtt: A Free-Viewing Eye-Tracking Dataset and Benchmark for Visual Attention on Paintings
Saliency and scanpath models are developed almost exclusively on natural photographs, yet paintings are composed by artists to guide the viewer's eye and differ from photographs in texture, colour…
deep-learning
FIGFLEX: A Mixed-Precision FP-INT GEMM Accelerator Co-Designed with Low-Bit LLM Quantization
Weight-only quantization keeps LLM activations in floating point and stores weights as low-bit integers, turning the dominant workload into floating-point-integer (FP-INT) general matrix…
deep-learning
Externalise the Memory: A Pre-Registered Study of Where an Embodied Agent's Experience Should Live
Should an embodied agent's experience be baked into its policy weights, or kept external and retrieved at inference? A memory-augmented teacher (a VLM that retrieves lessons, with their episode…
deep-learning
SplatLab: Autonomous Scientific Discovery for 3DGS Research
Reproducing a published 3DGS paper takes weeks of expert engineering before any extension can be proposed. Prior autonomous-research systems read papers, draft hypotheses, and write code, but are…
deep-learning
Flow-based Spectral Kernel Learning for Nonstationary Attention
Kernelized attention provides a useful perspective for understanding self-attention as a similarity-based aggregation mechanism, but existing approaches often rely on fixed or stationary kernels,…
deep-learning
Integrated Longitudinal and Lateral Control for High-Speed Platooning of Articulated Vehicles
This paper presents an integrated control framework for high-speed platooning of articulated vehicles, combining advanced longitudinal and lateral control strategies to address the challenges of safe…
deep-learning
Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models
Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information. However, existing search agents often lack…
deep-learning
Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibration
Recently, electroencephalography (EEG)-based brain--computer interfaces (BCIs) have gained traction as portable neural measurement systems. However, the practical deployment of these instruments is…
deep-learning
High-Value Training Data from Noisy, Diverse Sources
Training state-of-the-art models increasingly requires learning from large, heterogeneous datasets whose examples vary in quality, domain relevance, and source of supervision.…
deep-learning
AcoustiPrint: Physics-Guided Neural Design of Manufacturable Acoustic Structures
Recent work in additive manufacturing and neural inverse design enables the creation of complex three-dimensional structures to manipulate physical fields, yet these designs must also adhere to…
deep-learning
The Limits of Price Discrimination When the Market Is Unknown
Bergemann, Brooks, and Morris (2015) characterize the consumer and producer surplus pairs that segmentation can produce when the distribution of values is known. I fix only the set of possible values…
deep-learning
Escaping the Phylogenetic Trap: Persistent Homology Enables Cross-Species Ion Channel Classification via Multimodal Graph Neural Networks
Protein classifiers are highly sensitive to evaluation protocol: random train/test splits induce phylogenetic leakage, allowing models to exploit taxon-specific correlations and substantially…
deep-learning
Latent Space Jam: Layout Guided Video Synthesis
Adding control to video generation often requires training, which demands additional computational resources, data, or architectural changes. We propose a training-free approach that utilizes…
deep-learning
A Transformer-based Approach for Real-time Multi-agent Path Planning with Varying Initial/Final Conditions
We address the problem of real-time multi-agent path planning under prescribed initial and final configurations, formulated as a high-dimensional optimal control problem subject to inter-agent…
deep-learning
Climbing the Ladder: Automating Data Pipelines and Reproducing Baselines in Low-Resource Settings
The massively multilingual translation systems that now include Sicilian learned it from noisy, non-standardised web text. To obtain better translation quality, we redevelop the small neural machine…
deep-learning
Cutting a Cake For Human Consumption: An Elementary $n$-agent Cake Cutting Protocol
We give a bounded envy-free cake-cutting protocol for any number $n$ of agents in the Robertson--Webb model, with a short, self-contained, and elementary correctness proof. The protocol uses $2^{O(n…
deep-learning
Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs
Large language models often apply complex reasoning indiscriminately, leading to overthinking on simple tasks and underthinking on harder ones. We present Route-and-Generate (Rouge), a hierarchical…
deep-learning
AQL-Lite: Enabling Efficient Knowledge Acquisition for Arabic LLMs via Data-Centric Continual Pretraining
Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality…
deep-learning
Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles
We introduce Foundation4D, a unified feed-forward model for geometry estimation, 3D detection, semantic occupancy, and Gaussian reconstruction from multi-camera driving video. A shared backbone uses…
deep-learning
Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications
In recent years, Spiking Neural Networks (SNNs) have gained massive attention as an energy-efficient neural computing paradigm due to their event-driven and sparse computing capability. However,…
deep-learning