PPaperPicks

Shikun Zhang

41 papers at tracked venues · 33 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×13AAAI ×6NeurIPS ×6EMNLP ×4CVPR ×3IJCAI ×3ICLR ×2ICML ×2ACM MM ×1NAACL ×1

Frequent coauthors

Xiaoling Zhou
DBLP profile ↗ORCID search ↗
×7
Bo Li
DBLP profile ↗ORCID search ↗
×6
Zhuohao Yu
DBLP profile ↗ORCID search ↗
×5
Chaoya Jiang
DBLP profile ↗ORCID search ↗
×5
Yutao Mou
DBLP profile ↗ORCID search ↗
×4
Yidong Wang
DBLP profile ↗ORCID search ↗
×2
Mingjie Zhang
DBLP profile ↗ORCID search ↗
×1
Xiang Zhang
DBLP profile ↗ORCID search ↗
×1
Deyang Kong
DBLP profile ↗ORCID search ↗
×1
Ang Lv
DBLP profile ↗ORCID search ↗
×1
Xiangyu Xi
DBLP profile ↗ORCID search ↗
×1
Zile Qiao
DBLP profile ↗ORCID search ↗
×1

Papers

  1. ASKD: Reinforcement Learning-Style Knowledge Distillation with Quality-Adaptive Skewness
    AAAI 2026 ·
    Mingjie Zhang
    DBLP profile ↗ORCID search ↗
  2. Data Selection for Multi-turn Dialogue Instruction Tuning
    ACL 2026 ·
    Bo Li
    DBLP profile ↗ORCID search ↗
  3. Instruction Data Selection via Answer Divergence
    ACL 2026 ·
    Bo Li
    DBLP profile ↗ORCID search ↗
  4. Joint Optimization of Training Data and Policy in RLHF
    ACL 2026 ·
    Zhuohao Yu
    DBLP profile ↗ORCID search ↗
  5. L2-LoRA: Improving Low-Rank Adaptation with Layer-Specific Regularization
    AAAI 2026 ·
    Xiang Zhang
    DBLP profile ↗ORCID search ↗
  6. LeLoRA: Learnable Low-Rank Adaptation of Large Language Models
    ACL 2026 ·
    Xiaoling Zhou
    DBLP profile ↗ORCID search ↗
  7. Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG
    AAAI 2026 ·
    Bo Li
    DBLP profile ↗ORCID search ↗
  8. Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
    AAAI 2026 ·
    Deyang Kong
    DBLP profile ↗ORCID search ↗
  9. Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning
    ACL 2026 ·
    Bo Li
    DBLP profile ↗ORCID search ↗
  10. Thinking Twice Makes Large Language Models Safer and More Helpful
    ACL 2026 ·
    Yutao Mou
    DBLP profile ↗ORCID search ↗
  11. ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
    ACL 2026 ·
    Yutao Mou
    DBLP profile ↗ORCID search ↗
  12. All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
    CVPR 2025 ·
    Xiaoling Zhou
    DBLP profile ↗ORCID search ↗
  13. Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization
    NeurIPS 2025 ·
    Xiaoling Zhou
    DBLP profile ↗ORCID search ↗
  14. Can You Really Trust Code Copilot? Evaluating Large Language Models from a Code Security Perspective
    ACL 2025 ·
    Yutao Mou
    DBLP profile ↗ORCID search ↗
  15. GETMusic: Generating Music Tracks with a Unified Representation and Diffusion Framework
    IJCAI 2025 ·
    Ang Lv
    DBLP profile ↗ORCID search ↗
  16. HaDeMiF: Hallucination Detection and Mitigation in Large Language Models
    ICLR 2025 ·
    Xiaoling Zhou
    DBLP profile ↗ORCID search ↗
  17. MPL: Multiple Programming Languages with Large Language Models for Information Extraction
    ACL 2025 ·
    Bo Li
    DBLP profile ↗ORCID search ↗
  18. Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
    ICML 2025 ·
    Zhuohao Yu
    DBLP profile ↗ORCID search ↗
  19. Robustness to Spurious Correlations via Dynamic Knowledge Transfer
    IJCAI 2025 ·
    Xiaoling Zhou
    DBLP profile ↗ORCID search ↗
  20. SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
    NeurIPS 2025 ·
    Zhuohao Yu
    DBLP profile ↗ORCID search ↗
  21. SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity
    EMNLP 2025 ·
    Xiangyu Xi
    DBLP profile ↗ORCID search ↗
  22. Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling
    NAACL 2025 ·
    Zile Qiao
    DBLP profile ↗ORCID search ↗
  23. SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
    CVPR 2025 ·
    Hongrui Jia
    DBLP profile ↗ORCID search ↗
  24. VLM-R³: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
    NeurIPS 2025 ·
    Chaoya Jiang
    DBLP profile ↗ORCID search ↗
  25. AutoSurvey: Large Language Models Can Automatically Write Surveys
    NeurIPS 2024 ·
    Yidong Wang
    DBLP profile ↗ORCID search ↗
  26. Boosting Model Resilience via Implicit Adversarial Data Augmentation
    IJCAI 2024 ·
    Xiaoling Zhou
    DBLP profile ↗ORCID search ↗
  27. Enhancing In-Context Learning via Implicit Demonstration Augmentation
    ACL 2024 ·
    Xiaoling Zhou
    DBLP profile ↗ORCID search ↗
  28. FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models
    EMNLP 2024 ·
    Zhuohao Yu
    DBLP profile ↗ORCID search ↗
  29. Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models
    ACM MM 2024 ·
    Chaoya Jiang
    DBLP profile ↗ORCID search ↗
  30. Hallucination Augmented Contrastive Learning for Multimodal Large Language Model
    CVPR 2024 ·
    Chaoya Jiang
    DBLP profile ↗ORCID search ↗
  31. KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models
    ACL 2024 ·
    Zhuohao Yu
    DBLP profile ↗ORCID search ↗
  32. Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks
    AAAI 2024 ·
    Bo Li
    DBLP profile ↗ORCID search ↗
  33. MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
    NeurIPS 2024 ·
    Chaoya Jiang
    DBLP profile ↗ORCID search ↗
  34. NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
    ICML 2024 ·
    Zeqian Ju
    DBLP profile ↗ORCID search ↗
  35. PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness
    EMNLP 2024 ·
    Wenjin Yao
    DBLP profile ↗ORCID search ↗
  36. PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
    ICLR 2024 ·
    Yidong Wang
    DBLP profile ↗ORCID search ↗
  37. RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
    EMNLP 2024 ·
    Xuanwang Zhang
    DBLP profile ↗ORCID search ↗
  38. Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction
    ACL 2024 ·
    Dingyao Yu
    DBLP profile ↗ORCID search ↗
  39. SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
    NeurIPS 2024 ·
    Yutao Mou
    DBLP profile ↗ORCID search ↗
  40. TiMix: Text-Aware Image Mixing for Effective Vision-Language Pre-training
    AAAI 2024 ·
    Chaoya Jiang
    DBLP profile ↗ORCID search ↗
  41. What Makes a Good Order of Examples in In-Context Learning
    ACL 2024 ·
    Qi Guo
    DBLP profile ↗ORCID search ↗