127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “models”

95,172 results

Local Ai

70-class VRAM stagnation

DGX agent

been thinking about how the desktop 70-class has sat at 12GB for two generations now, 4070, 4070 super, 5070, all 12GB. the 1070 gave you 8GB back in 2016 and it felt generous for the price. ten years

local-air-localllama

3 Aug 2026

Research

Search: “models”

70-class VRAM stagnation

8月より、Sakana AI @SakanaAILabs にApplied Research Engineer Internship として入社しました 🐟🐠🐡！ 大学の夏季休業期間にフルタイム勤務予定です！ LLMの研究開発と社会実装を頑張ります💪🏻

AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles

Automated classification method of COVID-19 cases from chest CT volumes using 2D and 3D hybrid CNN for anisotropic volumes

Beyond Retrieval: Analytic Memory for Multimodal Agents

Can Zero-Shot LLMs Predict Child Malnutrition? A Fairness and Temporal Robustness Study

Deformable Medical Image Registration with KAN-based Implicit Neural Representations

DFSC: Error-Controlled Differentiable Mittag-Leffler Propagation for Fractional Scientific Machine Learning

DuET: Dual Expert Trajectories for Diffusion Image Editing

Dynamic Priors in Bayesian Optimization for Hyperparameter Optimization

DynoDINO: Harnessing Dynamic Latent Information from DINO Features for Multi-Phase Medical Image Segmentation

ELISA: An Interpretable Hybrid Generative AI Agent for Expression-Grounded Discovery in Single-Cell Genomics

Explore Beyond the Boundary Using Entropic Information

Flow Matching with Missing Data

GALA: Generative Aligned Learning for Adaptive Multimodal Representation in the Taobao Shangou Recommender System

Group-wise Supervision with Focal-Dice Loss for Long-Tailed Indoor Semantic Occupancy Prediction

HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators

HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering

How Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought Trajectories

I benchmarked classic vector RAG vs Google's new OKF format vs both combined — same corpus, same 7 questions, all local (Ollama + ChromaDB)

Implicit Machine Learning Force Fields Accelerate Molecular Dynamics Simulations

Measuring Cognitive Engagement in Collaborative Discourse with an Extended ICAP Framework: Comparing Human Annotation, In-Context Learning, and Reflective LLM Agents

metasignal: A Python Package for Comprehensive Metacognitive Analysis and Decision-Making

MHRGait: Gait Recognition from Momentum Human Rig Pose

MOSAIC: Masked Outsourcing of Secure AI Computations

Multi-Source Multi-View Graph Domain Adaptation with Hyperbolic Residual Encoding for Cross-Site MDD Identification from rs-fMRI

Sakana Namazu: An LLM API with Japanese-vibes! 🎏 Built for Japanese enterprises, featuring frontier-level reasoning and built-in agentic to…

SATViz: Real-Time Visualization of Clausal Proofs

Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember

Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions

TFGformer: Multivariate Time Series Forecasting via Time-Frequency Graph Learning and Covariate Fusion

The Checking Problem: What must be true before AI ships in a regulated firm

Transcript-Managed Transformers: Monotone Multi-Agent Collapse and Universality with Two Pop-Enabled Transcripts

What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents

When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks

It's not time to slow down but to accelerate! The recent AI-powered cyberattacks have everyone talking about the risks of AI. We should. But…

To address the limits of deep learning and avoid stalling, the field of AI started by applying patch (1), which started being demoed 9 month…

A Montage-Agnostic Encoder for Calibration-Light Cross-User Gesture Recognition from Surface Electromyography

Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection

AWARE-FX: An Auditable Knowledge-Guided AI System for Measuring Corporate Foreign-Exchange Hedging Disclosure

Balancing Privacy and Efficiency: Music Information Retrieval via Additive Homomorphic Encryption

Beyond Visual Ambiguity: Guiding Robust Monocular Depth Estimation in Challenging Scenarios via Detailed Long Captions

Causal Discovery with Inverted Self-attention for Multivariate Time Series

Cloud CISO Perspectives: Why AI Threat Defense is the new boardroom baseline

Context-Informed Ship Trajectory Prediction via Conditional Attention

Decision-oriented joint optimization of evidence fusion based on event-conditioned credibility

Direct Rotor Thrust Sensing and Feedback Control for Disturbance Rejection of Multirotors Using Load-cells

Distributions In, Distributions Out: The Case for Soft-Label Training

8月より、Sakana AI @SakanaAILabs にApplied Research Engineer Internship として入社しました 🐟🐠🐡！大学の夏季休業期間にフルタイム勤務予定です！ LLMの研究開発と社会実装を頑張ります💪🏻