127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

127,604 results

Local Ai

b9222

DGX agent

B9222 is a llama.cpp release that adds support for the TRI (Triangle) operation in the Hexagon HTP backend with HVX kernel additions . The release includes optimizations for Hexagon hardware accelerat

local-aillama-cpp-releases

19 May 2026

Agents

Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

DGX agent

arXiv:2605.16725v1 Announce Type: new Abstract: Executable world models can be read, edited, executed, and reused for planning, but only if the program captures the environment's transition law rather

All entries

b9222

Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling

BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting

Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity

Bayesian-Monte Carlo Schedule Updating for Construction Digital Twins: A Probabilistic Framework for Dynamic Project Forecasting

Bayesian Networks for Path-Based Sensors: Gathering Information and Path Planning in Communication Denied Environments

Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models

Becoming AI-native is no longer a path to success — it’s an operational prerequisite

Before enterprises can run with agentic AI, they need to learn to walk with their data

BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering

Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations

Benchmarking inference at scale: coding agents

Benchmarking Mythos-Linked Bug Rediscovery

Benchmarking Recurrent Event-Based Object Detection for Industrial Multi-Class Recognition on MTevent

Benchmarking transferability of SSL pretraining to same and different modality segmentation tasks

BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation

Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives

Best Segmentation Buddies for Image-Shape Correspondence

Better Together: Evaluating the Complementarity of Earth Embedding Models

Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs

Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models

Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP

Beyond Compliance: How AI Could Help Creative Writers by Refusing Them

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training

Beyond Detection: A Structure-Aware Framework for Scene Text Tracking

Beyond Euclidean Prototypes: Spectral Disentanglement and Geodesic Matching for Few-Shot Medical Image Segmentation

Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation

Beyond Geometry: Efficient Topologically-Grounded Navigation in Complex 3D Environments

Beyond Imperfect Alternatives with Rulemapping: A Neuro-Symbolic Case Study on Online Hate Speech

Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers

Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE

Beyond MMSE: Enhancing PnP Restoration with ProxiMAP

Beyond Morphology: Quantifying the Diagnostic Power of Color Features in Cancer Classification

Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment

Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation

Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers

Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning

Beyond RLHF: A Unified Theoretical Framework of Alignment

Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehicles

Beyond Scaling: Agents Are Heading to the Edge

Beyond Sentiment Classification: A Generative Framework for Emotion Intensity Evaluation in Text

Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs

Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection

Beyond the Next Port: A Multi-Task Transformer for Forecasting Future Voyage Segment Durations