PPaperPicks

Siheng Chen

41 papers at tracked venues · 36 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systems
  2. LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
  3. MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
  4. TeachMaster: Generative Teaching via Code
  5. Text2Mem: A Unified Memory Operation Language for Memory Operating System
  6. VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization
  7. AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios
  8. BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation
  9. Colmdriver: Llm-Based Negotiation Benefits Cooperative Autonomous Driving
  10. Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
  11. FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
  12. FedDQC: Data Quality Control in Federated Instruction-tuning of Large Language Models
  13. FedMABench: Benchmarking Mobile GUI Agents on Decentralized Heterogeneous User Data
  14. InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models
  15. Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels
  16. MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
  17. OOD-Barrier: Build a Middle-Barrier for Open-Set Single-Image Test Time Adaptation via Vision Language Models
  18. One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception
  19. Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models
  20. Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative Perception
  21. RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation
  22. Self-Evolving Multi-Agent Collaboration Networks for Software Development
  23. Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation
  24. Training-Free Message Passing for Learning on Hypergraphs
  25. Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving
  26. V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection
  27. V2XScenes: A Multiple Challenging Traffic Conditions Dataset for Large-Range Vehicle-Infrastructure Collaborative Perception
  28. An Extensible Framework for Open Heterogeneous Collaborative Perception
  29. Communication-Efficient Collaborative Perception via Information Filling with Codebook
  30. Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents
  31. Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
  32. FastMAC: Stochastic Spectral Sampling of Correspondence Graph
  33. FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
  34. KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server
  35. Language-Driven Interactive Traffic Trajectory Generation
  36. MADE: Malicious Agent Detection for Robust Multi-Agent Collaborative Perception
  37. On the Vulnerability of Safety Alignment in Open-Access LLMs
  38. OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning
  39. Robust Collaborative Perception without External Localization and Clock Devices
  40. Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
  41. Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals