PPaperPicks

Xunliang Cai

63 papers at tracked venues · 48 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×35EMNLP ×13AAAI ×6NeurIPS ×4ICLR ×2NAACL ×2ACM MM ×1

Frequent coauthors

Xuemiao Zhang
DBLP profile ↗ORCID search ↗
×4
Xiaoyun Zhang
DBLP profile ↗ORCID search ↗
×2
Peng Ding
DBLP profile ↗ORCID search ↗
×2
Yejie Wang
DBLP profile ↗ORCID search ↗
×2
Zhuocheng Gong
DBLP profile ↗ORCID search ↗
×2
Wentao Shi
DBLP profile ↗ORCID search ↗
×1
Junlin Liu
DBLP profile ↗ORCID search ↗
×1
Yingxuan Yang
DBLP profile ↗ORCID search ↗
×1
Shiyu Liu
DBLP profile ↗ORCID search ↗
×1
Lingyue Fu
DBLP profile ↗ORCID search ↗
×1
Xin Guo
DBLP profile ↗ORCID search ↗
×1
Jiaming Zhou
DBLP profile ↗ORCID search ↗
×1

Papers

  1. AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation
    ACL 2026 ·
    Wentao Shi
    DBLP profile ↗ORCID search ↗
  2. AMO-Bench: Large Language Models Still Struggle in High School Math Competitions
    ACL 2026 ·
    Junlin Liu
    DBLP profile ↗ORCID search ↗
  3. Attribution-Based Analysis and Optimization of Modular Agentic Workflows
    ACL 2026 ·
    Yingxuan Yang
    DBLP profile ↗ORCID search ↗
  4. BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search
    ACL 2026 ·
    Shiyu Liu
    DBLP profile ↗ORCID search ↗
  5. CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks
    ACL 2026 ·
    Lingyue Fu
    DBLP profile ↗ORCID search ↗
  6. Counteracting the Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
    ACL 2026 ·
    Xin Guo
    DBLP profile ↗ORCID search ↗
  7. DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding
    ACL 2026 ·
    Jiaming Zhou
    DBLP profile ↗ORCID search ↗
  8. Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents
    ACL 2026 ·
    Haojin Yang
    DBLP profile ↗ORCID search ↗
  9. How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
    ACL 2026 ·
    Yangyi Fang
    DBLP profile ↗ORCID search ↗
  10. LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
    ACL 2026 ·
    Yuchun Fan
    DBLP profile ↗ORCID search ↗
  11. Large-Scale Diverse Synthesis for Mid-Training
    ACL 2026 ·
    Xuemiao Zhang
    DBLP profile ↗ORCID search ↗
  12. LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
    ACL 2026 ·
    Xuemiao Zhang
    DBLP profile ↗ORCID search ↗
  13. MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
    ACL 2026 ·
    Xiaoliang Fu
    DBLP profile ↗ORCID search ↗
  14. MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
    ACL 2026 ·
    Junhao Ruan
    DBLP profile ↗ORCID search ↗
  15. Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
    ACL 2026 ·
    Yuxuan Hu
    DBLP profile ↗ORCID search ↗
  16. PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
    ACL 2026 ·
    Ai Jian
    DBLP profile ↗ORCID search ↗
  17. Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
    AAAI 2026 ·
    Deyang Kong
    DBLP profile ↗ORCID search ↗
  18. Scaling and Transferability of Annealing Strategies in Large Language Model Training
    AAAI 2026 ·
    Siqi Wang
    DBLP profile ↗ORCID search ↗
  19. Turning Failures into Value: Negative Experience Replay for RLVR via Confidence Gating and Boundary Failure Sampling
    ACL 2026 ·
    Jialiang Guo
    DBLP profile ↗ORCID search ↗
  20. Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text
    ACL 2026 ·
    Zhihao Xu
    DBLP profile ↗ORCID search ↗
  21. VANE: Guiding High-Value Exploration in RLVR via Outcome-Process Novelty Shaping
    ACL 2026 ·
    Xu He
    DBLP profile ↗ORCID search ↗
  22. WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling
    ACL 2026 ·
    Jiacheng Li
    DBLP profile ↗ORCID search ↗
  23. A Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
    EMNLP 2025 ·
    Xiaoyun Zhang
    DBLP profile ↗ORCID search ↗
  24. AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
    ACL 2025 ·
    Qi Liu
    DBLP profile ↗ORCID search ↗
  25. AgentRefine: Enhancing Agent Generalization through Refinement Tuning
    ICLR 2025 ·
    Dayuan Fu
    DBLP profile ↗ORCID search ↗
  26. Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning
    ACL 2025 ·
    Yongquan He
    DBLP profile ↗ORCID search ↗
  27. Dynamic Fisher-weighted Model Merging via Bayesian Optimization
    NAACL 2025 ·
    Sanwoo Lee
    DBLP profile ↗ORCID search ↗
  28. Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
    ICLR 2025 ·
    Ruichen Shao
    DBLP profile ↗ORCID search ↗
  29. Enhancing LLMs via High-Knowledge Data Selection
    AAAI 2025 ·
    Feiyu Duan
    DBLP profile ↗ORCID search ↗
  30. FIRE: Flexible Integration of Data Quality Ratings for Effective Pretraining
    EMNLP 2025 ·
    Liangyu Xu
    DBLP profile ↗ORCID search ↗
  31. FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
    ACL 2025 ·
    Xuemiao Zhang
    DBLP profile ↗ORCID search ↗
  32. Instance-level Randomization: Toward More Stable LLM Evaluations
    EMNLP 2025 ·
    Yiyang Li
    DBLP profile ↗ORCID search ↗
  33. Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
    NeurIPS 2025 ·
    Zhe Kong
    DBLP profile ↗ORCID search ↗
  34. Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration
    ACL 2025 ·
    Shao Zhang
    DBLP profile ↗ORCID search ↗
  35. Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuning
    EMNLP 2025 ·
    Jizhi Zhang
    DBLP profile ↗ORCID search ↗
  36. LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning
    ACL 2025 ·
    Jin Jiang
    DBLP profile ↗ORCID search ↗
  37. MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models
    EMNLP 2025 ·
    Siyu Yan
    DBLP profile ↗ORCID search ↗
  38. Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
    NAACL 2025 ·
    Yiwen Ding
    DBLP profile ↗ORCID search ↗
  39. Multi-Programming Language Sandbox for LLMs
    ACL 2025 ·
    Shihan Dou
    DBLP profile ↗ORCID search ↗
  40. NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
    NeurIPS 2025 ·
    Lanrui Wang
    DBLP profile ↗ORCID search ↗
  41. Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
    ACL 2025 ·
    Xuemiao Zhang
    DBLP profile ↗ORCID search ↗
  42. PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
    NeurIPS 2025 ·
    Ao Wang
    DBLP profile ↗ORCID search ↗
  43. Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning
    EMNLP 2025 ·
    Jianing Wang
    DBLP profile ↗ORCID search ↗
  44. ReMamba: Equip Mamba with Effective Long-Sequence Modeling
    EMNLP 2025 ·
    Danlong Yuan
    DBLP profile ↗ORCID search ↗
  45. Revisit Self-Debugging with Self-Generated Tests for Code Generation
    ACL 2025 ·
    Xiancai Chen
    DBLP profile ↗ORCID search ↗
  46. Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies
    ACL 2025 ·
    Zhengyu Chen
    DBLP profile ↗ORCID search ↗
  47. S3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners
    AAAI 2025 ·
    Yuchen Yan
    DBLP profile ↗ORCID search ↗
  48. SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
    AAAI 2025 ·
    Muxi Diao
    DBLP profile ↗ORCID search ↗
  49. SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity
    EMNLP 2025 ·
    Xiangyu Xi
    DBLP profile ↗ORCID search ↗
  50. The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights
    ACL 2025 ·
    Yufang Liu
    DBLP profile ↗ORCID search ↗
  51. Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
    EMNLP 2025 ·
    Hexiang Tan
    DBLP profile ↗ORCID search ↗
  52. When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
    EMNLP 2025 ·
    Xiaoyun Zhang
    DBLP profile ↗ORCID search ↗
  53. Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement
    ACL 2025 ·
    Peng Ding
    DBLP profile ↗ORCID search ↗
  54. DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning
    ACL 2024 ·
    Yejie Wang
    DBLP profile ↗ORCID search ↗
  55. Graph-Structured Speculative Decoding
    ACL 2024 ·
    Zhuocheng Gong
    DBLP profile ↗ORCID search ↗
  56. Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
    ACM MM 2024 ·
    Peng Ding
    DBLP profile ↗ORCID search ↗
  57. How Do Your Code LLMs perform? Empowering Code Instruction Tuning with Really Good Data
    EMNLP 2024 ·
    Yejie Wang
    DBLP profile ↗ORCID search ↗
  58. Learning or Self-aligning? Rethinking Instruction Fine-tuning
    ACL 2024 ·
    Mengjie Ren
    DBLP profile ↗ORCID search ↗
  59. Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation
    EMNLP 2024 ·
    Ruotong Pan
    DBLP profile ↗ORCID search ↗
  60. Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
    NeurIPS 2024 ·
    Bei Li
    DBLP profile ↗ORCID search ↗
  61. Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal
    EMNLP 2024 ·
    Zhicong Lu
    DBLP profile ↗ORCID search ↗
  62. Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism
    ACL 2024 ·
    Jiahao Liu
    DBLP profile ↗ORCID search ↗
  63. What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation
    AAAI 2024 ·
    Zhuocheng Gong
    DBLP profile ↗ORCID search ↗