PPaperPicks

Zhenheng Tang

19 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. CloneMem: Benchmarking Long-Term Memory for AI Clones
  2. GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
  3. Probing the Plasticity and Correlation of LLM Value Systems: LLM Value Rankings are Not Stable
    ACL 2026 · Zhenheng Tang
  4. SNI-GNN: SmartNIC-Assisted Full-Graph GNN Training with In-Network Embedding Prediction
  5. BurstGPT: A Real-World Workload Dataset to Optimize LLM Serving Systems
  6. Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
  7. ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
  8. Hot-pluggable Federated Learning: Bridging General and Personalized FL via Dynamic Selection
  9. MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs
  10. One-shot Federated Learning Methods: A Practical Guide
  11. ParZC: Parametric Zero-Cost Proxies for Efficient NAS
  12. STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
  13. Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
  14. FedImpro: Measuring and Improving Client Update in Federated Learning
    ICLR 2024 · Zhenheng Tang
  15. FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
    NeurIPS 2024 · Zhenheng Tang
  16. LPZero: Language Model Zero-cost Proxy Search from Zero
  17. Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models
  18. Should We Really Edit Language Models? On the Evaluation of Edited Language Models
  19. VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting