模型与评测

Poisson Disk Sampling

Post-Training Language Models for Gold-Medal Performance in Coding Competitions

Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We

Post-Training Language Models for Gold-Medal Performance in Coding Competitions

Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We

ProbeMatchDTI: Probe-Driven Multi-Scale Biochemical Pattern Matching for Drug-Target Interaction Prediction

Drug-target interaction (DTI) prediction is an important task in AI-driven drug discovery. Although recent biochemical representation learning methods have improved DTI prediction,

Proper Scoring Rules Shape LLM Forecasting

Protocols for People: AI, the Internet and the IETF

Python 3.15.0 candidate 2 is here!

Python 3.15.0 candidate 2 is here! Hugo van Kemenade (release manager for Python 3.14 and 3.15) announces the final release candidate for Python 3.15, scheduled for release in Octo

Qantas Airbus A380 engine failure in 2010 (2023)

Quoting Andrew Digby

325 #kakapo! The chicks from this year's record breeding season are now juveniles and so have been added to the population. In 1995 there were just 51 kākāpō left. Recovery of crit

Quoting Rick Brewster

Direct2D has always been the biggest hurdle for Paint.NET on WINE, and it's clear that it will never be completed enough for Paint.NET's use. And I can't just "disable" the use of

Quoting Tarn Adams

They took the letters from me! I have to talk about dwarf behavior now. I can't even talk about dwarf AI. It doesn't exist. It's dwarf behavior , and they misbehave sometimes — Tar

Qwen3.8-Max-0902 登顶 Code Arena 并以 $5/MToken 领跑 Pareto 前沿

通义千问发布 Qwen3.8-Max-0902，在 Code Arena： WebDev 以 1，691 分首次亮相即排名总榜第一，并以混合价 $5/MToken 成为 Pareto 前沿上得分最高的模型，现已可在 QwenCloud 试用。 🔗 阅读原文 via AIHOT · https://aihot.virxact.com/items/cmtjimz

RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection

Zero-shot graph anomaly detection seeks to deploy a detector trained on source graphs to unseen, unlabeled targets, yet domain shift can make source-derived notions of normality un

RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models

Large vision-language models have achieved remarkable success in vision-language tasks. However, they remain prone to Visual Hallucinations (VHs), undermining their reliability in

ReFlowSET：SAR 转到光学图像

表示对齐的潜在流匹配，做 SAR→EO。

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and ve

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and ve

Repo-To-Skill：仓库蒸馏成技能

把 GitHub 仓库压成可复用的 AI4AI skill。

SMELT：MoE 循环 Transformer 缩放律

计算匹配下的 MoE looped transformer 缩放。

SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment

The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to safety risks in both harmfu

Selected GitHub Copilot models deprecated

As of today, September 1, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code

Show HN: AI coach that adapts workouts and meals to your injuries and

Show HN: Dehurdle – Real-Time AI Voice Simulations for High-Stakes Conversations

Show HN: I put four persistent AI minds in a room and let them change each other