127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

127,664 results

Local Ai

b8925

DGX agent

B8925 is an intermediate build release of llama.cpp, the C/C++ library for efficient large language model inference. Llama.cpp releases follow a continuous build cycle rather than traditional versioni

local-aillama-cpp-releases

24 Apr 2026

Research

Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation

DGX agent

arXiv:2604.21772v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods

All entries

b8925

Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation

Back to the Future: The Role of Past and Future Context Predictability in Incremental Language Production

BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models

Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks

Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways

Beyond Accuracy: A Stability-Aware Metric for Multi-Horizon Forecasting

Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions

Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling

Beyond Pixels: Introspective and Interactive Grounding for Visualization Agents

Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts

Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos

Biomedical systems biology workflow orchestration and execution with PoSyMed

BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature

BiTDiff: Fine-Grained 3D Conducting Motion Generation via BiMamba-Transformer Diffusion

Bounding the Black Box: A Statistical Certification Framework for AI Risk Regulation

Brazil's Finance Minister Dario Durigan says the country has blocked prediction market platforms and tightened derivatives rules to curb 'bet-like' products (Reuters)

Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs

🚨BREAKING: Hugging Face just open-sourced an AI intern that reads ML papers, trains models, and ships the final model for you. It’s called …

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models

Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection

Bridging the Training-Deployment Gap: Gated Encoding and Multi-Scale Refinement for Efficient Quantization-Aware Image Enhancement

Brief chatbot interactions produce lasting changes in human moral values

btw the hot skills of today become the posttrain targets of tomorrow

Build with DeepSeek V4 Using NVIDIA Blackwell and GPU-Accelerated Endpoints

Building a Precise Video Language with Human-AI Oversight

Building my own Agentic Environment from scratch, in Go, for sandbox-per-agent usage

Building Workforce AI Agents with Visier and Amazon Quick

Built by the community, for the community. 🤝

But without racism, who will fund the Southern Poverty Law Center (and all the other thousands of far-left non-profits)?

C-SHAP for time series: An approach to high-level temporal explanations

Calibeating Prediction-Powered Inference

Can MLLMs 'Read' What is Missing?

Canada's Cohere and Germany's Aleph Alpha agree to a merger deal valuing the combined group at ~$20B to work on sovereign AI; both governments support the deal (Financial Times)

CAP: Controllable Alignment Prompting for Unlearning in LLMs

Capabilities and Evaluation Biases of Large Language Models in Classical Chinese Poetry Generation: A Case Study on Tang Poetry

CARE: Counselor-Aligned Response Engine for Online Mental-Health Support

CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation

Causal Disentanglement for Full-Reference Image Quality Assessment

CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Certified Coil Geometry Learning for Short-Range Magnetic Actuation and Spacecraft Docking Application

Channel-Free Human Activity Recognition via Inductive-Bias-Aware Fusion Design for Heterogeneous IoT Sensor Environments

Check out OpenRouters' new guide on getting the most out of Openrouter x Hermes Agent

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models

China’s DeepSeek previews new AI model a year after jolting US rivals

China's top market regulator says it is launching a six-month crackdown on the country's online ad sector, targeting malpractices including the misuse of AI (Ben Jiang/South China Morning Post)

CHRep: Cross-modal Histology Representation and Post-hoc Calibration for Spatial Gene Expression Prediction

CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents