PPaperPicks

Bin Wang

Xiaomi AI Lab, Beijing, China

22 papers at tracked venues · 13 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Function-to-Style Guidance of LLMs for Code Translation
  2. Global Eye: Breaking the "Fixed Thinking Pattern" during the Instruction Expansion Process
  3. HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation
  4. Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study
  5. ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation
  6. Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology
  7. TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization
  8. Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization
  9. ToolACE: Winning the Points of LLM Function Calling
  10. A Comprehensive Evaluation of Quantization Strategies for Large Language Models
  11. DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy
  12. Empathetic Response Generation with Relation-aware Commonsense Knowledge
  13. EmpathyEar: An Open-source Avatar Multimodal Empathetic Chatbot
  14. Mixture of Diverse Size Experts
  15. Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents
  16. MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding
  17. Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations
  18. Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information Extraction
  19. SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM
  20. Scaling up masked audio encoder learning for general audio classification
  21. SpeechEE: A Novel Benchmark for Speech Event Extraction
    ACM MM 2024 · Bin Wang
  22. ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback