Shuo Yang
6 papers · Latest:
LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries
LLM agents empower users to integrate and govern their personal data across platforms, moving beyond fragmented, platform-centric personalization.
Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
Bian Que is an LLM agent framework that automates online system operations by intelligently orchestrating data and knowledge, reducing human effort and improving efficiency.
OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
OCR-Memory enables LLM agents to retain long-term experience by encoding historical trajectories visually, overcoming text-context limits and reducing hallucination.
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
DR-Venus is a 4B deep research agent trained on only 10K open data, outperforming larger models for edge-scale deployment.
Well Begun is Half Done: Training-Free and Model-Agnostic Semantically Guaranteed User Representation Initialization for Multimodal Recommendation
This paper introduces SG-URInit, a training-free and model-agnostic method to initialize semantically rich user representations for multimodal recommendation systems.
GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding
GenomeQA is a new benchmark evaluating general LLMs on raw genome sequence understanding, revealing their ability to use local signals but struggle with complex inference.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.