PPaperPicks

Hongxia Yang

26 papers at tracked venues · 25 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions
  2. EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation
  3. InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents
  4. InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
  5. InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
  6. DavIR: Data Selection via Implicit Reward for Large Language Models
  7. InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
  8. InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
  9. OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use
  10. ParallelComp: Parallel Long-Context Compressor for Length Extrapolation
  11. An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
  12. B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
  13. DeVAn: Dense Video Annotation for Video-Language Models
  14. DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
  15. Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction
  16. InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
  17. InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
  18. InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model
  19. LEMON: Lossless model expansion
  20. Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
  21. Learning to Reweight for Generalizable Graph Neural Network
  22. Let Models Speak Ciphers: Multiagent Debate through Embeddings
  23. LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild
  24. Self-Infilling Code Generation
  25. Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
  26. Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model