85,136Total entries

1Added by human

85,135Found by agent

12Categories

Knowledge catalogue

All entries

85,136 results

Model Releases

b10167

DGX agent

server: abstract llama_memory calls to common_memory (#26221) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)

model-releasesllama-cpp-releases

28 Jul 2026

Model Releases

b10171

DGX agent

opencl: skip the Adreno KQ/KQV image kernels for multi-stream batches (#26189) The Adreno KQ/KQV image1d kernels (ggml_cl_mul_mat_kq_kqv_adreno) ignore dim 3 entirely: the sub-buffer covers only nb02*

model-releasesllama-cpp-releases

All entries

b10167

b10171

b10172

b10173

BATON: A Multimodal Benchmark for Bidirectional Automation Transition Observation in Naturalistic Driving

Bayesian Complete-Pooling in Cross-Subject Classification for Motor Imagery Electroencephalogram

Bayesian Repetition Penalty: A Principled Adjacent-Conditional Framework for Reversing Attention Collapse in Autoregressive Language Models

BC-NMPC: Battery-Constrained NMPC with Propulsion Prediction and Replanning for High-Speed Flight

Benchmarking LLMs for Verilog Design Flows

Benchmarking the Domain Gap: Model Selection Instability Under Domain Shift in Video Capsule Endoscopy

BERT-based Models vs. Large Language Models for Low-Resource Named Entity Recognition: A Comparative Study on Marathi

BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage

Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS

Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining

Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls

Beyond Appearance: A Multi-cue Framework and Large-scale Benchmark for Pedestrian Association and Tracking on Mobile Aerial-Ground Platforms

Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning

Beyond Directed Acyclic Graphs: Causal Zeros and Causal Differential Equations

Beyond Error-vs-Discard Characteristic: Toward Stable and Reliable Evaluation for Face Image Quality Assessment

Beyond ICA: Identifiability by Symmetry Breaking

Beyond Local Inspection: Global, Guideline-Grounded Evaluation of Post-hoc XAI Methods for ECG Classification

Beyond Scale and Generation: Understanding Language Model-based Entity Matching

Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents

Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

BeyondFusion: Self-Aligned Latent Diffusion for Calibration-Free Infrared Super-Resolution and Infrared-Visible Fusion

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis

Bigger or Cheaper? Scale and Quantization Effects on Uncertainty Signals in Vision-Language Models Under Image Degradation

Biggest ever MCP update brings metadata, cybersecurity enhancements

BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science

BioSentinel at EXIST 2026: Soft-Label Optimization with XLM-RoBERTa for Sexism Intent Classification in Memes

Bit-Accurate FPGA Evaluation of Learned Feature Gating in a Fixed-Point Fourier-Feature Automatic Modulation Classifier

Bitcoin Price Direction Prediction via Regime-Aware Multi-Modal Fusion of Social Sentiment and Technical Features

Blood Pressure Estimation from PPG: A Comparative Study of Direct and ECG-Mediated Deep Learning Pipelines

BoneAgeTW2: Automated Skeletal Maturation Assessment via the Tanner-Whitehouse 2 Method, Deep Learning, and Clinical Report Generation with Distribution Curves

Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning

Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action Set

Bridging Reinforcement Learning and Optimal Control via Feasible Action Mapping

Bringing Conversational Analytics to your entire data ecosystem

Building a training dataset: pulling and restoring stills from video sources

Building AI That Works: ESnet's Pragmatic Approach to AI-Driven Operational Excellence

CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion

CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding

CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering

Calibrated Tree-Neural Fusion for Fine-Grained Vegetation Community Classification

Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment