Semantic Scholar
Semantic Scholar uses groundbreaking AI and engineering to understand the semantics of scientific literature to help Scholars discover relevant resear
Helping Scholars Discover New Insights Semantic Scholar provides free, AI-driven search and discovery tools, and open resources for the global research community. We index over 200 million academic papers sourced from publisher partnerships, data providers, and web crawls. We are a Research and Product Development team within Ai2 building a better way to search and discover scientific knowledge. With Semantic Scholar, researchers can understand a paper at a glance. Our system extracts meaning and identifies connections from within papers, then surfaces these insights to help Scholars discover and understand research. Our Values reflect who we are, why we are building Semantic Scholar, and guide us through hard decisions. We are motivated to use AI in novel ways for a dramatic impact. Tackling our problems with AI not only helps our community, it also improves the quality of our AI research by grounding it in real-world application. Scientific knowledge should be available to everyone. We recognize that the status quo disproportionately benefits certain groups of scholars over others. As a non-profit, we evaluate the impact of our choices and pursue directions that help balance the scales. Collaboration makes us stronger. We make a conscious effort to collaborate with our teammates, and by doing so, we will both improve the quality of our work and distribute the burden of support. We are small, but mighty. We stand behind our convictions when we believe they are the right direction, even if that is a more difficult path. We question what has been done historically, never satisfied with the status quo. We aim to gain knowledge sooner by starting conversations early and by prototyping our ideas quickly. When we realize a path we have chosen is not working, we are willing to recognize it openly and do the work to learn from it. We aim to establish a higher standard for applying AI in a trustworthy and transparent way. By educating and building trust in our AI-driven solutions, we will foster a community who are invested in our success and patient with our mistakes. We provide a free, reliable source of scholarly data for developers to build projects that accelerate scientific progress. Reach millions of scholars by integrating your academic content into Semantic Scholar's knowledge graph Join our Beta Program to provide feedback and help scholars around the globe Download logos, illustrations, and brand guidelines
Papers with Code
Your daily dose of AI research from AK
Get trending papers in your email inbox once a day! Get trending papers in your email inbox! VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity. VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity. A multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio. A multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio. A large language model adapted for time-series forecasting achieves near-optimal zero-shot performance on diverse datasets across different time scales and granularities. A large language model adapted for time-series forecasting achieves near-optimal zero-shot performance on diverse datasets across different time scales and granularities. VOID is a video object removal framework that uses vision-language models and video diffusion models to generate physically plausible scenes by leveraging causal reasoning and counterfactual reasoning. VOID is a video object removal framework that uses vision-language models and video diffusion models to generate physically plausible scenes by leveraging causal reasoning and counterfactual reasoning. LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times. LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times. DeepScientist autonomously conducts scientific discovery through Bayesian Optimization, surpassing human state-of-the-art methods on multiple AI tasks. DeepScientist autonomously conducts scientific discovery through Bayesian Optimization, surpassing human state-of-the-art methods on multiple AI tasks. The AI Scientist-v2 autonomously proposes hypotheses, performs experiments, analyzes data, and writes peer-reviewed scientific papers, marking the first fully AI-generated paper accepted by a conference. The AI Scientist-v2 autonomously proposes hypotheses, performs experiments, analyzes data, and writes peer-reviewed scientific papers, marking the first fully AI-generated paper accepted by a conference. A large-scale dynamic dataset derived from AAA games is introduced to improve generative inverse and forward rendering, featuring high-resolution synchronized RGB and G-buffer data alongside a novel VLM-based evaluation method that correlates well with human judgment. A large-scale dynamic dataset derived from AAA games is i
Semantic Scholar
Papers with Code
Semantic Scholar
Papers with Code
Only in Semantic Scholar (10)
Semantic Scholar
Papers with Code
Semantic Scholar
Papers with Code
