2024-10-21

《美国反无人机系统未来趋势报告（2024-2029 年）》

【大模型】2024人工智能国外大模型使用手册解读-51页附下载

Latent Action Pretraining for General Action models (LAPA): An Unsupervised Method for Pretraining Vision-Language-Action (VLA) Models without Ground-Truth Robot Action Labels

Meta AI Releases Meta’s Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models

淘宝百亿补贴“全家桶”桶桶五折！天猫双11今晚8点现货开卖

苹果内部员工自揭其短：生成式AI研发竟已落后两年多

Microplastic pollution is everywhere, even in the exhaled breath of dolphins

一键免费获取前沿AI论文，一站式解决论文搜索、带读和写作！

Build a Sci-Fi Aerial Display

Fungi finding: mushroom hunters seek new species and recognition

aiXcoder-7B: A Lightweight and Efficient Large Language Model Offering High Accuracy in Code Completion Across Multiple Languages and Benchmarks

还是原装Transformer好！北大清华团队同时揭示Mamba等推理短板

Nature子刊，北大陈语谦团队提出多模态单细胞数据整合和插补的深度学习方法

Male stalk-eyed flies with short eyestalks are less attractive to females but fight more fiercely, scientists discover

AI and Radar Seek to Unsnarl a 500-Year-Old Traffic Jam

NeurIPS 2024 | 标签噪声下图神经网络有了首个综合基准库，还开源

空间飞行器轨迹优化与控制技术发展现状与展望

视频、图像、文本，只需基于下一个Token预测：智源Emu3发布，验证多模态模型新范式

Argentina’s researchers face continued catastrophe under Javier Milei

This AI Research from Cohere for AI Compares Merging vs Data Mixing as a Recipe for Building High-Performant Aligned LLMs

RealHumanEval: A Web Interface to Measure the Ability of LLMs to Assist Programmers

Directing group facilitates catalytic breakdown of high-performance polymer

【TPAMI2024】结构化时空对齐视频-语言表示

Open Collective Releases Magnum/v4 Series Models From 9B to 123B Parameters

速度提高1000万倍，AI快速准确预测等离子体加热，助力核聚变研究

Scientists are getting serious about UFOs. Here’s why

Researchers to explore light and ultrasound therapy for melanoma treatment in pigs

This Machine Learning Research Discusses How Task Diversity Shortens the In-Context Learning (ICL) Plateau

UN biodiversity summit opens with call for 'significant' funding

黄仁勋新访谈：OpenAI是这个时代最具影响力公司之一，马斯克19天创造工程奇迹

Investigating the impact of ultralight dark matter on gravitational wave signals

突破视频多模态大模型瓶颈！「合成数据」立大功，项目已开源

集智网最新科研新闻

2024-10-20

All-optical switch device paves way for faster fiber-optic communication

Stretchable transistors used in wearable devices enable in-sensor edge computing

【普林斯顿博士论文】通过稀疏性解锁可信的机器学习，206页pdf

SAM 2.1上新、Lingua代码库发布，一大波Meta开源工具来袭

Research team develops key n-type thermoelectric semiconductor technology to recycle waste heat

Nobel economics prize: How colonial history explains why strong institutions are vital to a country's prosperity

MMed-RAG: A Versatile Multimodal Retrieval-Augmented Generation System Transforming Factual Accuracy in Medical Vision-Language Models Across Multiple Domains

This year's Nobel prize exposes economics' problem with colonialism

Meta AI Releases Cotracker3: A Semi-Supervised Tracker that Produces Better Results with Unlabelled Data and Simple Architecture

UN biodiversity conference: what's at stake?

Cat's Eye Camera Can See Through Camouflage

Can China Challenge SpaceX's Starlink?

Challengers Are Coming for Nvidia’s Crown

Worms and snails handle the pressure 2,500m below the Pacific surface

又快又准，即插即用！清华8比特量化Attention，两倍加速于FlashAttention2，各端到端任务均不掉点！

Differentiable Rendering of Robots (Dr. Robot): A Robot Self-Model Differentiable from Its Visual Appearance to Its Control Parameters

Learn more about IEEE →

Rethinking Direct Alignment: Balancing Likelihood and Diversity for Better Model Performance

Hurricane Helene shut down NC mine that is pivotal to world's semiconductor supply

Harnessing Introspection in AI: How Large Language Models Are Learning to Understand and Predict Their Behavior for Greater Accuracy

TSMC’s Energy Demand Drives Taiwan’s Geopolitical Future

Self-Data Distilled Fine-Tuning: A Solution for Pruning and Supervised Fine-tuning Challenges in LLMs

Scientists find southern killer whales of the Pacific have access to enough food, deepening mystery of their struggles

视频生成模型变身智能体：斯坦福Percy Liang等提出VideoAgent，竟能自我优化

Amazon's Secret Weapon in Chip Design Is Amazon

化学空间导航仪：流生成式AI引导分子属性控制

Download PDF (5.4 MB) ↓

mate change, do not understand climate justice

Embed-then-Regress: A Versatile Machine Learning Approach for Bayesian Optimization Using String-Based In-Context Regression

Jurgen、曼宁等大佬新作：MoE重塑6年前的Universal Transformer，高效升级

See the full collection →

Nvidia AI Introduces the Normalized Transformer (nGPT): A Hypersphere-based Transformer Achieving 4-20x Faster Training and Improved Stability for LLMs

132年未解开的李雅普诺夫函数谜题，被Symbolic Transformer攻克了

Ocean eddy currents funnel extreme heat and cold to the life-filled depths

NeurIPS 2024 Oral | 小参数，大作为！揭秘非对称 LoRA 架构的高效性能

封面文章|黄维院士团队：钝化晶界缺陷提升钙钛矿电池的效率和稳定性

Helping your cat overcome 'megacolon'

CREAM: A New Self-Rewarding Method that Allows the Model to Learn more Selectively and Emphasize on Reliable Preference Data

Taiwan's AI Goals Will Need More Tech Talent

Meta’s New AR Glasses Come at a High Cost

Partial Automation Doesn't Make Vehicles Safer

This AI Paper Explores If Human Visual Perception can Help Computer Vision Models Outperform in Generalized Tasks

集智网最新科研新闻