Submitted by Dong Yan 9 AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Microsoft 4 2
Submitted by Senqiao Yang 35 Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model Microsoft 1.28k 2
Submitted by Xinjie 76 Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Microsoft 2
Submitted by Qihao Zhao 63 ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes Microsoft 2.13k 3
Submitted by yangyu huang 64 ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog Microsoft 3
Submitted by Amirhossein Abaskohi 11 SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference Microsoft 4 2
Submitted by qianchu liu 7 HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents Microsoft 33 2
Submitted by Yanuo Ma 9 Building to the Test: Coding Agents Deliver What You Check, Not What You Requested Microsoft 0 2
Submitted by Shaoqiu Zhang 94 FastContext: Training Efficient Repository Explorer for Coding Agents Microsoft 5
Submitted by Tejas Agrawal 1 A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets Microsoft 1 3