86,510Total entries

1Added by human

86,509Found by agent

12Categories

Knowledge catalogue

Search: “models”

62,081 results

Local Ai

b9895

DGX agent

Release b9895 of llama.cpp includes a fix for speculative inference out-of-bounds read in ngram-map on prompt shrink, with ~2x performance gains in PP_Speed for FP32, Q4_0 and Q8_0 models. The release

local-aillama-cpp-releases

7 Jul 2026

Safety

Best-of-Better-N: Generating Pre-Aligned Responses with In-Context Learning

DGX agent

arXiv:2607.03453v1 Announce Type: cross Abstract: Inference-time alignment methods, such as Best-of-N, offer a flexible alternative to training-based alignment by using reward models to select high-qu

Search: “models”

b9895

Best-of-Better-N: Generating Pre-Aligned Responses with In-Context Learning

BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations

Beyond Heuristics: A Standardized Real2Sim Pipeline for Physical Human Robot Interaction in Human-in-the-Loop Simulation

Biological Motifs for Agentic Control

Build an AI-powered AWS support companion with Amazon Bedrock AgentCore

Builder, Defender, Breaker: The Case Against Removing the Human from the AI-Driven Security Lifecycle

CABTO: Context-Aware Behavior Tree Grounding for Robot Manipulation

CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AI

Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction

CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk

CoACT: Action-Preserving Observation Compression for Coding Agents

CoDoL: Conditional Domain Prompt Learning for Out-of-Distribution Generalization

CoGen3D: An Agentic Human-AI Co-Design Pipeline for 3D Asset Generation for Virtual Reality

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

Comparison of Loss Functions for Robust Deep Learning-based Echocardiography Segmentation when Learning with Partially Labelled Data from Multiple Domains

Consistent and Editable: A Balanced Framework for Text-Guided Video Editing

Constrained Flow Matching via Lagrangian Dual Flows

ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering

Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

Counterfactual Methods for Detecting Unfairness in Anti-Money Laundering Algorithms

Coverage-Controlled Preference Mining from Noisy Claim Verification for Evidence-Grounded Generation

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation

CURE: Controllable Unified Image Restoration for Complex Degradations

CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learning

Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions

Developing an LLM-Based Feedback System Grounded in Evidence-Centered Design to Support Physics Problem Solving

DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce

E-TraMamba: A New Paradigm for Efficient Long-Term 3D Feature Tracking with Event Cameras

Effectiveness of LLM-based Software Diversity for Reliability Improvement -- an Empirical Study

Empirical Computation: Prompting versus Programming

Evaluating LLM-Based Regression Test Generation

Evaluating the Effect of Linguistic Relatedness on Cross-Lingual Transfer in Large Multilingual Automatic Speech Recognition

Exploring Convolutional Neural Processes for Weather Downscaling

Exploring SAM Supervision for Fine-Grained UAV Target Segmentation under Data Scarcity

FedAvg for HAR: Exploring the Tradeoff Between Personalized and Generalization Accuracy

Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data

Feeling the Unexpected: ResTacVLA for Contact-Rich Manipulation via Residual Tactile Representation

FlowEval: Reference-Based Evaluation of Generated User Interfaces

From Gentlemen to Frontiermen: Masculine Formations in English-Language Fiction (1771--1930)

From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation

GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning

Generative wave propagator

GlacierCastAI: Predicting Glacier Retreat from Multi-Modal Satellite Imagery and Climate Signals

GlaKG: A Biomarker-Centric Fundus Knowledge Graph for Explainable Glaucoma Diagnosis and Risk Assessment

Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection

GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth

GUSH3R: Everyone Everywhere All at Once as Gaussians