Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
PopGen: Generating Semantically Diverse Populations for Zero-Shot CoordinationGoogle DeepMind · arXiv (Cornell University)Oct 11MoTA: Cross-Modal Motion Transfer for Animating 3D Head Avatars via 2D Motion TokensMicrosoft · ACM Transactions on Multimedia Computing Communications and ApplicationsOct 11OncoReg: Medical Image Registration for Oncological ChallengesAlibaba · The Journal of Machine Learning for Biomedical ImagingOct 11CompLit: Scientific Literature Search Benchmarks Must Cover Implicit, Cumulative, and Unmet NeedsLG AI Research · arXiv (Cornell University)Oct 10SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill CompositionAlibaba · arXiv (Cornell University)Oct 10Harmony Harness: Multi-Objective Self-Evolution of Agent HarnessesAlphabet, Google DeepMind · arXiv (Cornell University)Oct 10Last Secure Code Benchmark: Is the Code You Vibe Secure?Alibaba · arXiv (Cornell University)Oct 10Self-Evolving Visual Agent via Margin RewardMicrosoft · arXiv (Cornell University)Oct 10What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training StrategiesAlibaba · arXiv (Cornell University)Oct 10Random Fourier Features in Near-Linear TimeMicrosoft · arXiv (Cornell University)Oct 10Executable but Unfaithful: Mock Object, Stub, and Assertion Generation by LLMs and Coding AgentsMistral AI · arXiv (Cornell University)Oct 10Towards Merging-conditional Backdoor Unalignment against Large Language ModelsAlibaba · arXiv (Cornell University)Oct 10Harness^2: Recursive Agent Harnessing for an Open WorldAlphabet · arXiv (Cornell University)1 citationOct 9Disentangling Task-Relevant Latent Dynamics for Reward ModelingGoogle DeepMind · arXiv (Cornell University)Oct 9Unconstrained CTI-REALM with Open-WeightsMistral AI · arXiv (Cornell University)Oct 9OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native ToolsSenseTime · arXiv (Cornell University)Oct 9AutoEnvScaling: Automating the Data Flywheel with Terminal AgentsMicrosoft · arXiv (Cornell University)Oct 9Multimodal Co-Generation With Continuous Bitstream DiffusionNVIDIA · arXiv (Cornell University)Oct 9Simple Linear Corrections for Compression in Late InteractionMicrosoft · arXiv (Cornell University)Oct 9Agentic Data Engineering for LLMs: System Design and a Controlled Empirical StudyAlibaba · arXiv (Cornell University)Oct 9ASSET: Adaptive Speech Segmentation via Reinforcement LearningNVIDIA · arXiv (Cornell University)Oct 9GeoFix: Geometry Fixing for 4D Consistent GenerationAlphabet · arXiv (Cornell University)Oct 9Scaling Agentic Data for Long-Horizon Terminal IntelligenceAlibaba · arXiv (Cornell University)Oct 9Why DiT Models Underperform as Representation Learners without Long Skip ConnectionsAlibaba · arXiv (Cornell University)Oct 9Branching On-Policy DistillationSenseTime · arXiv (Cornell University)Oct 9