Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Microcosmos: Reimagining Artificial Life for the GPU EraSakana AI · Conference on Artificial Life (ALIFE)Aug 1Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream NetworksSakana AI · Conference on Artificial Life (ALIFE)Aug 1One Image is All You Need: Agentic One-Shot Image Generation via Text-Based World Models for Long-Tail Spatial PerceptionSenseTime · IEEE International Conference on Automation Science and Engineering (CASE)Aug 1Supporting the Adoption of Privacy-Enhancing Technologies Through Requirements EngineeringAlphabet · IEEE International Requirements Engineering Conference (RE)Aug 1Learning Developmental Scaffoldings to Guide Self-OrganisationSakana AI · Conference on Artificial Life (ALIFE)Aug 1Fishing for Answers: Exploring One-Shot vs. Iterative Retrieval Strategies for Retrieval Augmented GenerationSenseTime · IEEE International Conference on Automation Science and Engineering (CASE)Aug 1End-to-end multimodal pathology foundation model with clinical dialogueMicrosoft · Nature Medicine3 citationsJul 31KPIs 2024 challenge: Advancing glomerular segmentation from patch- to slide-levelNVIDIA · Medical Image Analysis1 citationJul 31Tool Calling Behind the Curtain: Secure Function Execution for Agentic LLMs Inside Confidential VMsMeta · International Journal of Computer Information Systems and Industrial Management ApplicationsJul 31Learning to Coordinate Symbolic Tools: LLM Agents for Verified Sum-of-Squares CertificatesOpenAI · arXiv (Cornell University)Jul 31RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement LearningMicrosoft · arXiv (Cornell University)Jul 31AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?Microsoft · arXiv (Cornell University)Jul 31Themis: Software-Defined Hardware PrefetchingAlphabet · arXiv (Cornell University)Jul 31The Kikuchi Hierarchy is Sharp for $k$XORMicrosoft · arXiv (Cornell University)Jul 31HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question AnsweringiFlytek · arXiv (Cornell University)Jul 31Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation FrameworkMicrosoft · arXiv (Cornell University)Jul 31MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping AgentsAlibaba · arXiv (Cornell University)Jul 31Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and RememberMininglamp Technology · arXiv (Cornell University)Jul 31Navigation reliability assessment on occupancy grid networks for AMR navigation using a dynamic programming binary-addition-tree algorithmNVIDIA · Reliability Engineering & System Safety1 citationJul 30Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production ScaleMicrosoft · arXiv (Cornell University)Jul 30LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language ModelsAlibaba · arXiv (Cornell University)Jul 30ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale RecommendationMeta · arXiv (Cornell University)Jul 30On the Computational Complexity of (Extended) Threshold Dimension and (Semi-)Ladder IndexAlphabet · arXiv (Cornell University)Jul 30Towards 4D Gesture Reconstruction Through Leaky Acoustic WavesAlphabet · GetMobile Mobile Computing and CommunicationsJul 30Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics ForecastingNVIDIA · arXiv (Cornell University)Jul 30