127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “inference”

20,509 results

Research

Sequential Membership Inference Attacks

DGX agent

arXiv:2602.16596v2 Announce Type: replace Abstract: Modern AI models are not static. They go through multiple updates in their lifecycles. We propose to design Sequential Membership Inference (SeMI) a

researcharxiv-cs-lg

12 May 2026

Model Releases

Search: “inference”

Sequential Membership Inference Attacks

This NVIDIA remains the strongest platform for large-model inference at scale. Prefill/decode disaggregation, Blackwell-native quantization,…

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation

CARMEN: CORDIC-Accelerated Resource-Efficient Multi-Precision Inference Engine for Deep Learning

Inference of Qualitative Models from Steady-State Data via Weighted MaxSMT

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference

Reformulating KV Cache Eviction Problem for Long-Context LLM Inference

Deploy and inference any model from HuggingFace

open models got good enough right as frontier inference pricing started creeping up

Serving DeepSeek-V4: why million-token context is an inference systems problem

Apple dominate local inference 6/10 This is completely opposite to enterprise/data-center adoption where Nvidia is king. Huge market Nvidia …

Learn how to structure your AI stack. Our co-founder @the_bunny_chen talks with @theinfrapod's @tnachen and @ianlivingstone about inference …

Welcome to DS4, a specialized inference engine for DeepSeek v4 Flash. https://github.com/antirez/ds4 This project would have been impossible…

CoVSpec: Efficient Device-Edge Co-Inference for Vision-Language Models via Speculative Decoding

Gated Subspace Inference for Transformer Acceleration

Google releases Multi-Token Prediction drafters for its Gemma 4 models, which use a form of speculative decoding to guess future tokens for faster inference (Ryan Whitwam/Ars Technica)

inference >>>

Introducing TokenSpeed, a speed-of-light LLM inference engine. > TensorRT LLM level performance > vLLM level usability > Built by a lean and…

IRIS: Intent Resolution via Inference-time Saccades for Open-Ended VQA in Large Vision-Language Models

Why are four of the top 10 trending vendors AI inference platforms? Companies are getting selective about which model handles which task, an…

Deep Variational Inference Symbolic Regression

Excited to introduce Gemma 4 Multi-Token Prediction Drafters⚡️Accelerated inference right in your pockets - Up to a 3x speedup - Same qualit…

Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction

Inference is 80-90% of the lifetime cost of a production AI system. Most AI-native teams are leaving performance and margin on the table. He…

LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference

MiniMax-M2.7 is now available across six inference providers on Artificial Analysis, with significant differentiation in speed and price @Sa…

Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time

STAR: Decode-Phase Rescheduling for LLM Inference

Unsupervised full-field Bayesian inference of orthotropic hyperelasticity from a single biaxial test: a myocardial case study

Foundational research powering efficient inference at scale

🤯 Ollama now supports Claude Desktop via Claude’s built-in third party inference. ollama launch claude-desktop This allows all models from …

Peek2: Regex-free Byte-level Byte-Pair Encoding Pretokenizer for LLM Inference on Edge Devices

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference

Sources: Anthropic is in early talks to buy AI inference chips from UK-based Fractile when they become available in 2027 (The Information)

A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics

Cloud computing provider Nebius agrees to buy Eigen AI, which optimizes the performance of chips running AI inference tasks, for $615M in stock and cash (Dina Bass/Bloomberg)

Context as Prior: Bayesian-Inspired Intent Inference for Non-Speaking Agents with a Household Cat Testbed

EdgeFM: Efficient Edge Inference for Vision-Language Models

Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference

With this integration, teams can optimize data, launch fine-tuning, evaluate results, and deploy on Together AI inference through a tighter …

As models, contexts, and workloads grow, hidden assumptions in inference infrastructure can surface as output anomalies. Reliability require…

Compute Aligned Training: Optimizing for Test Time Inference

Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing

Learning with Embedded Linear Equality Constraints via Variational Bayesian Inference

Our cofounder @the_bunny_chen joined @GregorVand to talk about open models, production inference, and how RFT is unlocking model customizati…

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference

GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval