Trending Research
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
stepfun-ai/step-audio
?
?
17 Feb 2025
Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following.
Craw4LLM: Efficient Web Crawling for LLM Pretraining
Web crawl is a main source of large language models' (LLMs) pretraining data, but the majority of crawled web pages are discarded in pretraining due to low data quality.
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
We introduce SWE-Lancer, a benchmark of over 1, 400 freelance software engineering tasks from Upwork, valued at \$1 million USD total in real-world payouts.
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
stepfun-ai/step-video-t2v
?
?
14 Feb 2025
We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length.
OmniParser for Pure Vision Based GUI Agent
microsoft/omniparser
?
?
1 Aug 2024
The recent success of large vision language models shows great potential in driving the agent system operating on user interfaces.
Ranked #10 on
Natural Language Visual Grounding
on ScreenSpot
MoBA: Mixture of Block Attention for Long-Context LLMs
moonshotai/moba
?
?
18 Feb 2025
Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI).
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world industrial applications.
OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia
aslp-lab/osum
?
?
23 Jan 2025
Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable comprehensive speech-based interactions.
Data Formulator 2: Iteratively Creating Rich Visualizations with AI
To create rich visualizations, data analysts often need to iterate back and forth among data processing and chart specification to achieve their goals.
Magma: A Foundation Model for Multimodal AI Agents
We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds.
