A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs. It centres on Inference, and also names Benchmarks and GitHub. Reported by arXiv.

Source: arXiv9 Sept 2026Read original

AI Agents28

The Athlete as a Scientist of One: Agentic Bayesian Experimental Design for Individualized Physiology from Consumer Wearables

The story centres on Benchmarks. Reported by arXiv.

Source: arXivYesterdayRead original

AI Agents22

EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation

It centres on Benchmarks, and also names Inference and GitHub. Reported by arXiv.

Source: arXiv4 days agoRead original

AI Regulation22

Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation

It centres on RAG, and also names Fine-tuning and Benchmarks. Reported by arXiv.

Source: arXiv24 Sept 2026Read original

AI Research21

AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

It centres on Benchmarks, and also names Hugging Face and GitHub. Reported by arXiv.

Source: arXiv9 Oct 2026Read original

AI Research21

On-Board Anomaly Detection for Efficient Marine Environmental Monitoring

The story centres on Microsoft. Reported by arXiv.

Source: arXiv2 Oct 2026Read original

AI Hardware22

GTFormer: A Syntax-Free Graph Network Alternative to Transformers for 8192$\times$ Length Extrapolation in Linear Time

The story centres on Benchmarks. Reported by arXiv.

Source: arXiv3 days agoRead original

AI Research21

VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift

It centres on Microsoft, and also names Benchmarks. Reported by arXiv.

Source: arXiv21 Oct 2026Read original

What’s Trending in AI?

What’s Trending in AI?

Results for “Benchmarks”

Asking a Multimodal LLM Whether Someone Fell: Zero-Shot Screening of Low-Resolution Thermal Video in a Laboratory and an Occupied Home

Evaluating In-Context Learning and Retrieval Strategies for Devanagari Post-OCR Correction

SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

The Athlete as a Scientist of One: Agentic Bayesian Experimental Design for Individualized Physiology from Consumer Wearables

EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation

Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation

AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

On-Board Anomaly Detection for Efficient Marine Environmental Monitoring

GTFormer: A Syntax-Free Graph Network Alternative to Transformers for 8192$\times$ Length Extrapolation in Linear Time

VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift

AI Resources

How this page works

Building with AI?