127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “inference”

20,505 results

Local Ai

b9829

DGX agent

Build b9829 is an intermediate release of llama.cpp, the open-source C/C++ project that enables users to run large language models on consumer hardware without expensive GPUs or cloud infrastructure.

local-aillama-cpp-releases

28 Jun 2026

Local Ai

b9831

DGX agent

Release b9831 of llama.cpp includes backend detection improvements and synchronization enhancements, particularly for async CUDA copies and Vulkan backend operations. Llama.cpp is designed to enable L

local-aillama-cpp-releases

Search: “inference”

b9829

b9831

b9832

Looks like Llama CPP just merged DFLASH support into main! I wonder how this will stack up against MTP 👀 https://github.com/ggml-org/llama.…

MASSIVE NEWS Teamed up with NVIDIA to make Local AI The Default

b9824

1/ On p (doom) tl;dr a) Everyone is making up the numbers b) nobody knows anything (least of all the experts), c) don't worry about it d) th…

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

As token usage explodes, model choice becomes product strategy. Teams are already testing models like GLM-5.2 because they want frontier qua…

At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization

Autoregressive Boltzmann Generators

b9814

Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders

Cross-Head Attention Uplift Network with Inverse Propensity Score under Unobserved Confounding

CSU-PCAST: A Dual-Branch Transformer Framework for medium-range ensemble Precipitation Forecasting

DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception

Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation

Dot-Flik: A Scalable Edge AI Architecture for Distributed Insect Monitoring

E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation

Equivariance and Augmentation for Bayesian Neural Networks

Forget, Anticipate and Adapt: Test Time Training for Long Videos

GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models

Implementation of reinforcement learning in chemical reaction networks: application to phototaxis as curiosity-driven exploration

Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision

In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics

Incident Report: CVE-2026-LGTM

Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models

LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration

Learning Long-Range Dependencies with Temporal Predictive Coding

Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective

LISA: Likelihood Score Alignment for Visual-condition Controllable Generation

LogicIR: Logic Gate Networks for Image Restoration

Many companies could build their own Workday or whatever, too, using open source alternatives. They don't do that for a wide variety of reas…

MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction

MinGram: A Minimalist Unigram Tokenizer with High Compression and Competitive Morphological Alignment

Neural Texture Compression using Hypernetworks

Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection

OctoSense: Self-Supervised Learning for Multimodal Robot Perception

OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference

OpenRCA 2.0: From Outcome Labels to Causal Process Supervision

Overcoming State Inertia: Minimally Invasive Temporal Alignment for Evolving Contexts

Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes

Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection

Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training

Run a vLLM Server on HF Jobs in One Command

scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology

SpaceRipple: Lightweight Semantic Delivery for Mission-Oriented LEO Earth Observation Satellite Networks