Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
After the Attacker Leaves: Benchmarking Carryover Attacks on LLM AgentsSenseTime · arXiv (Cornell University)Oct 20CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?SenseTime · arXiv (Cornell University)Oct 18Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch AgentsSenseTime · arXiv (Cornell University)Oct 12OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native ToolsSenseTime · arXiv (Cornell University)Oct 9Branching On-Policy DistillationSenseTime · arXiv (Cornell University)Oct 9TARP: Text-Augmented Re-centered Projection for few-shot CLIP adaptationSenseTime · Computer Vision and Image UnderstandingOct 9RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement LearningSenseTime · arXiv (Cornell University)Oct 7Self-correction Optimization for Interleaved Multimodal GenerationSenseTime · arXiv (Cornell University)Oct 7XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary DecisionsSenseTime · arXiv (Cornell University)Oct 3Towards Vision‐Language Geo‐Foundation Models: A SurveySenseTime · The Photogrammetric Record3 citationsSep 28What Visual Generators Need from Teachers: Rethinking Representation AlignmentSenseTime · arXiv (Cornell University)Sep 28Evolving Support Priorities in Empathetic Reinforcement LearningSenseTime · arXiv (Cornell University)Sep 28Rethinking Visual Token Compression for Video Large Language Models: A Simple Yet Strong BaselineSenseTime · arXiv (Cornell University)Sep 28Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video UnderstandingSenseTime · arXiv (Cornell University)Sep 6CrossViewDiff: A cross-view diffusion model for satellite-to-street view synthesisSenseTime · Pattern RecognitionSep 3StructureBench: A Unified Benchmark Suite for Multi-Scenario Structured Generation Tasks with On-Device ModelsSenseTime · International Joint Conference on Artificial IntelligenceSep 1When History Is Multimodal: Rethinking Context Management for Long-Horizon AgentsSenseTime · arXiv (Cornell University)Aug 30Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal AgentsSenseTime · arXiv (Cornell University)Aug 26TransPhy: Visual In-Context Learning for Physically Grounded Image EditingSenseTime · arXiv (Cornell University)Aug 25StateTrace: An Object-Centric Framework for Hidden-State Spatiotemporal Reasoning in Long VideosSenseTime · arXiv (Cornell University)Aug 19OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use TrajectoriesSenseTime · arXiv (Cornell University)Aug 9GraphVerse: A Comprehensive Visual Graph Reasoning Benchmark for Multimodal Large Language ModelsSenseTime · arXiv (Cornell University)Aug 7One 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 1Fishing for Answers: Exploring One-Shot vs. Iterative Retrieval Strategies for Retrieval Augmented GenerationSenseTime · IEEE International Conference on Automation Science and Engineering (CASE)Aug 1Parallel Hyper-Prior and Dual-Domain Autoregressive Transformer for Lossless JPEG Recompression of Pathology ImagesSenseTime · IEEE Transactions on Medical ImagingJul 22