24 results for: research

An arXiv paper introduces a DKPS-based approach that uses cached model outputs to predict benchmark scores while substantially reducing the number of queries.

A physics-informed foundation model called PIGMENT learns a universal microstructure prior and adapts zero-shot to individual diffusion MRI scans, enabling reliable maps from sparse and heterogeneous data.

An arXiv preprint introduces MPMMine, a benchmark suite built to supply the domain artifacts and structured data constraint-acquisition methods need for reproducible evaluation.

A new ATOM analysis of about 1,500 open language models maps downloads, derivatives, inference share and performance, and reports Chinese models surpassed U.S.

A position paper argues AI evaluation must publish item-level benchmark responses and ships OpenEval - 10M model responses across 155k items - to prove the point.

What is new here is that tilde Research Introduces Aurora: A Leverage-Aware Optimizer That Fixes a Hidden Neuron Death Problem in Muon.

OpenClassGen introduces a comprehensive dataset of Python classes, enhancing LLM evaluation.

RPC-Bench addresses gaps in understanding academic papers for AI models with a new benchmark.

A new framework aims to improve the assessment of medical AI benchmarks, addressing key shortcomings.

A novel LLM-based framework provides flexible evaluation of mathematical reasoning, addressing limitations of symbolic methods.

A new test-time matching method improves compositional reasoning in AI models, achieving state-of-the-art results.

DenoiseRank leverages diffusion models for a fresh generative angle on learning to rank tasks.

OpenCLAW-P2P v6.0 introduces advanced subsystems for decentralized AI peer review, improving paper resilience and retrieval.

ml-intern is an open-source agent that automates literature review, dataset discovery, training script runs, and iterative evaluation for LLM post-training work.

OpenAI has announced that verified U.S. physicians, nurse practitioners, and pharmacists can now access ChatGPT for Clinicians at no charge.

Mozilla patched 271 vulnerabilities after an initial security evaluation that used an early Claude Mythos Preview in collaboration with Anthropic.

An arXiv paper introduces a quantitative-plus-error-analysis benchmark for Vietnamese legal text, comparing GPT-4o, Claude 3 Opus, Gemini 1.5 Pro and Grok-1.

An arXiv study uses perturbation-based attribution to compare FFT, LoRA, and quantized LoRA across model sizes and finds FFT yields more focused interpretive patterns.

Simon Willison turned Anthropic’s published Claude system prompts into per-model Markdown files with fake git commits so changes can be browsed on GitHub.

NVIDIA introduced Ising, a family of open-source quantum AI models intended to help researchers and enterprises design quantum processors that can run useful applications.

OpenAI introduced GPT‑Rosalind, a frontier reasoning model aimed at speeding drug discovery, genomics, protein reasoning, and scientific workflows.