2024-12-08

青岛理工朱晓阳/华南理工章圆方《Prog. Mater. Sci.》顶刊综述

This AI Paper from UCSD and CMU Introduces EDU-RELAT: A Benchmark for Evaluating Deep Unlearning in Large Language Models

上交大梁正/颜徐州JACS：超耐用且快释放的超分子粘结剂用于高性能、可持续硅基负极

Snowflake Releases Arctic Embed L 2.0 and Arctic Embed M 2.0: A Set of Extremely Strong Yet Small Embedding Models for English and Multilingual Retrieval

开源社区参数量最大的文生视频模型来了，腾讯版Sora免费使用

Google DeepMind Researchers Advance Game AI: From Hallucination-Free Moves to Grandmaster Play

Brain Stimulation Helps People ​Walk After Spinal Injury

Videos capture orcas’ tricks for taking down the largest fish on Earth

Critic-RM: A Self-Critiquing AI Framework for Enhanced Reward Modeling and Human Preference Alignment in LLMs

NeurIPS 2024｜拆解高复杂运筹问题的砖石，打破数据稀缺的瓶颈，中科大提出高质量运筹数据生成方法

Here’s how to give a good gift, according to science

困扰数学家近60年的搬沙发难题疑似被解决！119页论文证明最优解，百万网友围观

Stability AI Releases Arabic Stable LM 1.6B Base and Chat Models: A State-of-the-Art Arabic-Centric LLMs

UC Berkeley Researchers Explore the Role of Task Vectors in Vision-Language Models

Adaptive Attacks on LLMs: Lessons from the Frontlines of AI Robustness Testing

OpenAI的强化微调：RL+Science 创造新神还是灭霸？

Exploring Adaptivity in AI: A Deep Dive into ALAMA’s Mechanisms

Meet DataLab: A Unified Business Intelligence Platform Utilizing LLM-Based Agents and Computational Notebooks

Composition of Experts: A Modular and Scalable Framework for Efficient Large Language Model Utilization

o give a good gift, according to science

Meet GRAPE: A Plug-and-Play Algorithm to Generalize Robot Policies via Preference Alignment

太阳能电池重大突破！最新Nature Energy！

Auto-RAG: An Autonomous Iterative Retrieval Model Centered on the LLM’s Powerful Decision-Making Capabilities

Microsoft Introduces Florence-VL: A Multimodal Model Redefining Vision-Language Alignment with Generative Vision Encoding and Depth-Breadth Fusion

集智网最新科研新闻

2024-12-07

VBench直接干到了第一！这一次，视频生成「压番」全场的是家央企

ICLR 惊现[10,10,10,10]满分论文，ControlNet 作者新作，Github 5.8k 颗星

Global-MMLU: A World-class Benchmark Redefining Multilingual AI by Bridging Cultural and Linguistic Gaps for Equitable Evaluation Across 42 Languages and Diverse Contexts

NVIDIA AI Introduces NVILA: A Family of Open Visual Language Models VLMs Designed to Optimize both Efficiency and Accuracy

Top 20 Guardrails to Secure LLM Applications

OpenAI 12连发第2弹：强化微调，少量样本就能训练自己的专家模型

CPU-GPU I/O-Aware LLM Inference Reduces Latency in GPUs by Optimizing CPU-GPU Interactions

12V Battery Charger Circuits [using LM317, LM338, L200, Transistors]

2024年企业AI大模型应用落地白皮书

种瓜得瓜种豆得豆:“种位错”实现钙钛矿氧化物室温破纪录压缩塑性

用LLaVA解读数万神经元，大模型竟然自己打开了多模态智能黑盒

刚刚，2025 IEEE Fellow名单出炉：戴琼海、姜大昕、尹首一、翟广涛、褚晓文等人入选

This AI Paper from UCLA Unveils ‘2-Factor Retrieval’ for Revolutionizing Human-AI Decision-Making in Radiology

Retrieval-Augmented Reasoning Enhancement (RARE): A Novel Approach to Factual Reasoning in Medical and Commonsense Domains

Cooler breakthrough using the Thomson effect.

IEEE’s Partnership With Onsemi Boosts Semiconductor Education

突破！自然语言强化学习(NLRL)：一个可处理语言反馈的强化学习框架

Google DeepMind’s Patent Transforming Protein Design Through Advanced Atomic-Level Precision and AI Integration

Cohere AI Introduces INCLUDE: A Comprehensive Multilingual Language Understanding Benchmark

Vega C Successfully Launches for First Time in Nearly Two Years

2 Mosquito Swatter Bat Circuits Explained

Power Interruption Alarm Circuit for Instant Power Failure Indications

华南理工章圆方/青岛理工朱晓阳Prog. Mater. Sci.综述：《电热激活软材料：机理、方法与应用》

Expanding the library of high-quality thin films.

LeCun团队新作：在世界模型中导航

U.S. Airlines Eyeing Air Taxis for Airport Shuttle Service

除了深度学习，你需要知道AI技术的23个方向 | 机器之心首份技术报告

AI4Bharat and Hugging Face Released Indic Parler-TTS: A Multimodal Text-to-Speech Technology for Multilingual Inclusivity and Bridging India’s Linguistic Digital Divide

Alibaba Speech Lab Releases ClearerVoice-Studio: An Open-Sourced Voice Processing Framework Supporting Speech Enhancement, Separation, and Target Speaker Extraction

Advancing Large Multimodal Models: DocHaystack, InfoHaystack, and the Vision-Centric Retrieval-Augmented Generation Framework

Proposed time limits on anesthesia may have jeopardized patient safety

关于计算机视觉中的自回归模型，这篇综述一网打尽了

Planetary boundaries and scientific societies.

Theoretically grounded approaches to account for polarization effects in fixed-charge force fields

重磅！《人工智能行业应用建设发展参考架构》发布

How to Generate Pure Oxygen and Hydrogen at Home

Researchers at Stanford University Introduce TrAct: A Novel Optimization Technique for Efficient and Accurate First-Layer Training in Vision Models

集智网最新科研新闻