127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “models”

95,135 results

Model Releases

Memory Attention

DGX agent

arXiv:2609.28399v1 Announce Type: new Abstract: Language models typically construct attention values from contextual hidden states, even when some of their content may be reusable across contexts. We

model-releasesarxiv-cs-lg

24 Sept 2026

Applications

NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolution

DGX agent

arXiv:2609.26841v1 Announce Type: cross Abstract: High-capacity neural network models have achieved state-of-the-art performance across diverse classification tasks, yet they frequently operate as bla

Search: “models”

Memory Attention

NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolution

PBLH Estimation from Satellite Radiances via a Dual-Encoder Transformer

Qwen3.8-Flash-Next on 12GB VRAM - 65 tokens per second

SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference

Spatiality-Frequency Domain Video Forgery Detection System Based on ResNet-LSTM-CBAM and DCT Hybrid Network

Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms

VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark

Annual Earth-observation embeddings encode wildfire disturbance and support simplified burned area mapping

Can We Predict Anomaly Detection Performance from Embedding-Space Geometry?

Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves

Domain-Adaptive Pretraining Enhances Water Treatment Semantic Representation for Large-Scale Structured Literature Mining

DUMA-Bench: A Dual-Control Multi-Agent Benchmark for Evaluating LLM Agent Security

Efficient Iterative Retrieval with Heterogeneous Batching

EquivSVA: A Formally Verified Dataset of Behavioral Assertions Across Equivalent RTL Implementations

Evidence-gated multimodal parsing and vectorization of architectural floor plans

Extending FunctionGemma for Practical On-Device Mobile Function Calling

Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach

Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs

FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering

From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs

From Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM Serving

Hierarchical Sparse Bayesian Multitask Learning for Disease Prediction in Pooled Microbiome Studies

Latent Commonality Expectation-Maximisation for Box-supervised Tree Crown Instance Segmentation

LIMIT: Less Is More for Instruction Tuning in Text-to-SQL

Magnitude Profile Pruning: Calibration-Free Structured Attention Head Removal for Transformer Compression

MCPGen: Benchmarking LLMs on Executable MCPWorkflow Development

Modular Norm RandOpt: Population-Efficient Ensembling through Architecture-Aware Perturbations

Partner-Specific Affective Precision in Social Active Inference

RankCert: When Can Simulated Learners Safely Select an AI Tutor? Robust Decision Certification Under Structural Uncertainty

Robust, Estimator-Agnostic Dynamic 3DGS Compression

Same Chart, Different Story: Bias in Vision-Language Chart Interpretation

stuntd: a local Jev-compatible server on Laya that learns from your own traffic (no API key needed)

Toward Auditable and Calibrated AI for Dementia-Related Crash Severity Prediction: A Selective Deferral Framework to Support Human Review

Towards Adaptive Federated Graph Clustering: A Global Community-aware Contrastive Learning-based Approach

TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection

TRACE: Transparent Retrieval for Abstract Concept Evaluation

Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance

VLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning

Adapting Tree-Structured Speculative Decoding to DeepSeek-V4 for Efficient Inference

AirGC-CD: Gaussian-Circulant Precoding for Exactly Debiasable PAPR Reduction in Over-the-Air Federated Learning

Anthropic says Opus 5.5 matches Fable 5.1 'on most tasks' while costing about 40% less to run than Opus 5; Opus 5.5 costs 4/1M input and 20/1M output tokens (Matthias Bastian/The Decoder)

As part of our efforts to pace the frontier, we’re committed to supporting independent assessments with deep levels of access across trainin…

Authority-Preserving Evaluation of Medical Vision-Language Assistants

Beyond Accuracy and Surface Fluency: Risk-Sensitive Evaluation of LLMs for Legal Clause Generation

Beyond Point Prediction: Artificial Representative Trees with Uncertainty

Can Coding Agents Reproduce Official Statistics? Metadata, Retry Budget and the Limits of Execution Feedback in a Controlled Eurostat Benchmark

ChartJudgeBench: Evaluating LMM Judges for Chart-to-Code Generation