Lune

Profiles2020-2026

Wulong Liu

Huawei Advanced Computing and Storage Lab

13Papers
1Last author
54Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers13

  1. TrimR: Verifier-based Training-Free Thinking Trimming for Efficient Test-Time ScalingAuthor 8 of 10ICLR 2026 · 14 citations
  2. AttentionPredictor: Temporal Patterns Matter for KV Cache CompressionAuthor 8 of 11NeurIPS 2025 · 8 citations
  3. KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM InferenceAuthor 7 of 9ICML 2025
  4. Distributional Reinforcement Learning with Regularized Wasserstein LossAuthor 3 of 5NeurIPS 2024 · 2 citations
  5. Conformalized Fairness via Quantile RegressionAuthor 4 of 6NeurIPS 2022 · 22 citations
  6. Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive LearningAuthor 7 of 7AAAI 2021 · 61 citations
  7. An Efficient Transfer Learning Framework for Multiagent Reinforcement LearningAuthor 8 of 12NeurIPS 2021 · 34 citations
  8. Adaptive Online Packing-guided Search for POMDPsAuthor 6 of 7NeurIPS 2021 · 28 citations
  9. Addressing Action Oscillations through Learning Policy InertiaAuthor 4 of 5AAAI 2021 · 27 citations
  10. Model-Based Reinforcement Learning via Imagination with Derived MemoryAuthor 4 of 10NeurIPS 2021 · 14 citations
  11. Foresee then Evaluate: Decomposing Value Estimation with Latent Future PredictionAuthor 8 of 9AAAI 2021 · 5 citations
  12. Neighborhood Cognition Consistent Multi-Agent Reinforcement LearningAuthor 2 of 8AAAI 2020 · 85 citations
  13. Multi-Agent Interactions Modeling with Correlated PoliciesAuthor 6 of 7ICLR 2020 · 22 citations
Dusk over the sea between two cliffs drawn in fine vertical lines