Lune

Profiles2022-2026

Ruihua Song

Renmin University of China

13Papers
2Last author
25Unique co-authors
0First author
0Solo

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

Recent papers13

  1. JointAVBench: A Benchmark for Joint Audio-Visual Reasoning EvaluationAuthor 5 of 6ICLR 2026 · 16 citations
  2. Evaluating Text Creativity across Diverse Domains: a Dataset and Large Language Model EvaluatorAuthor 6 of 6ICLR 2026 · 11 citations
  3. DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative WritingAuthor 5 of 9ACL 2026 · 3 citations
  4. Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning ModelsAuthor 8 of 9ICML 2026 · 2 citations
  5. Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning ChainsAuthor 5 of 6NeurIPS 2025 · 103 citations
  6. EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed DynamicsAuthor 5 of 7AAAI 2025 · 2 citations
  7. Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work GenerationAuthor 2 of 4ACL Findings 2025 · 2 citations
  8. Think Then React: Towards Unconstrained Action-to-Reaction Motion GenerationAuthor 6 of 6ICLR 2025
  9. Persuading across Diverse Domains: a Dataset and Persuasion Large Language ModelAuthor 5 of 6ACL 2024 · 9 citations
  10. See or Guess: Counterfactually Regularized Image CaptioningAuthor 3 of 6ACM MM 2024 · 7 citations
  11. Joint Semantic and Strategy Matching for Persuasive DialogueAuthor 6 of 11EMNLP Findings 2023 · 3 citations
  12. A Multi-Modal Knowledge Graph for Classical Chinese PoetryAuthor 5 of 6EMNLP Findings 2022 · 8 citations
  13. Multi-Modal Experience Inspired AI CreationAuthor 3 of 6ACM MM 2022 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines