PPaperPicks

Sheng Wang

19 papers at tracked venues · 12 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts
  2. Mitigating Context Interference for Reliable and Efficient Search Agents
  3. Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models
  4. Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation
  5. Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration
  6. Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension
  7. How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models
  8. MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
  9. MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards
    ICLR 2025 · Sheng Wang
  10. ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom
  11. QSpec: Speculative Decoding with Complementary Quantization Schemes
  12. Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control
  13. Towards Deeper GCNs: Alleviating Over-Smoothing via Iterative Training and Fine-Tuning
  14. TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
    NeurIPS 2025 · Sheng Wang
  15. UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
  16. Cross-Domain Contrastive Learning for Time Series Clustering
  17. LoRA Meets Dropout under a Unified Framework
    ACL 2024 · Sheng Wang
  18. PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA
    ACL 2024 · Sheng Wang
  19. Retrieved Sequence Augmentation for Protein Representation Learning