PPaperPicks

Junchi Yan

125 papers at tracked venues · 119 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
  2. ST-TPP: Learning Semi-Transductive Temporal Point Processes with Gromov-Wasserstein Barycentric Regularization
  3. Towards Real-Time Neutral Atom Array Assembly via Unsupervised Hologram Generation and Path Optimization
  4. BTBS-LNS: Binarized-Tightening, Branch and Search on Learning LNS Policies for MIP
  5. Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation
  6. BiQAP: Neural Bi-level Optimization-based Framework for Solving Quadratic Assignment Problems
  7. Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization
  8. Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks
  9. COExpander: Adaptive Solution Expansion for Combinatorial Optimization
  10. CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning
  11. CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation Learning
  12. DSBRouter: End-to-end Global Routing via Diffusion Schr\"{o}dinger Bridge
  13. DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving
  14. Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
  15. FlatFusion: Delving Into Details of Sparse Transformer-Based Camera-LiDAR Fusion for Autonomous Driving
  16. Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape
  17. FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers
  18. Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization
  19. Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning
  20. GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-Based Transformer
  21. GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training
  22. HEAP: Hyper Extended A-PDHG Operator for Constrained High-dim PDEs
  23. HShare: Fast LLM Decoding by Hierarchical Key-Value Sharing
  24. Int2Planner: An Intention-based Multi-modal Motion Planner for Integrated Prediction and Planning
  25. LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
  26. Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision
  27. Learning Structured Universe Graph with Outlier OOD Detection for Partial Matching
  28. ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs
  29. MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study
  30. NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
  31. On Designing General and Expressive Quantum Graph Neural Networks with Applications to MILP Instance Representation
  32. On the Role of Label Noise in the Feature Learning Process
  33. Optimal Control Operator Perspective and a Neural Adaptive Spectral Method
  34. Optimal Flow Transport and its Entropic Regularization: a GPU-friendly Matrix Iterative Algorithm for Flow Balance Satisfaction
  35. Optimize Battery Control: A Multi-Objective Evolutionary Ensemble Reinforcement Learning Approach
  36. Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and Modalities
  37. PhysPDE: Rethinking PDE Discovery and a Physical Hypothesis Selection Benchmark
  38. Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning
  39. Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances
  40. QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning Baseline
  41. QuEST: Low-Bit Diffusion Model Quantization via Efficient Selective Finetuning
  42. QuaDiM: A Conditional Diffusion Model For Quantum State Property Estimation
  43. QuanONet: Quantum Neural Operator with Application to Differential Equation
  44. Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
  45. Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives
  46. Regularizing Energy among Training Samples for Out-of-Distribution Generalization
  47. Reinvent the Operation not the Architecture: Quantum-inspired High-order Product for Compatible and Improved LLMs Training
  48. Repurposing AlphaFold3-like Protein Folding Models for Antibody Sequence and Structure Co-design
  49. Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance
  50. Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach
  51. Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction
  52. RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments
  53. SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEs
  54. SelKD: Selective Knowledge Distillation via Optimal Transport Perspective
  55. Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training
  56. StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
  57. Tensor Network: from the Perspective of AI4Science and Science4AI
    IJCAI 2025 · Junchi Yan
  58. The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
  59. Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters
  60. Towards More Diverse and Challenging Pre-Training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views
  61. Train on Pins and Test on Obstacles for Rectilinear Steiner Minimum Tree
  62. Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving
  63. UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP
  64. UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection
  65. Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search
  66. VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
  67. ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation
  68. Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
  69. Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime
  70. Boosting Order-Preserving and Transferability for Neural Architecture Search: A Joint Architecture Refined Search and Fine-Tuning Approach
  71. Boundary Matters: A Bi-Level Active Finetuning Method
  72. CalibRBEV: Multi-Camera Calibration via Reversed Bird's-eye-view Representations for Autonomous Driving
  73. Certified Robustness on Visual Graph Matching via Searching Optimal Smoothing Range
  74. Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning
  75. Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation
  76. CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
  77. Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
  78. Double-Bounded Optimal Transport for Advanced Clustering and Classification
  79. Dynamic Reactive Spiking Graph Neural Network
  80. EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model
  81. Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization
  82. FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
  83. GeoMix: Towards Geometry-Aware Data Augmentation
  84. Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
  85. Graph Out-of-Distribution Detection Goes Neighborhood Shaping
  86. Graph Out-of-Distribution Generalization via Causal Intervention
  87. Grounding and Enhancing Grid-based Models for Neural Fields
  88. How Graph Neural Networks Learn: Lessons from Training Dynamics
  89. InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes
  90. L2P-MIP: Learning to Presolve for Mixed Integer Programming
  91. LLMCO4MR: LLMs-Aided Neural Combinatorial Optimization for Ancient Manuscript Restoration from Fragments with Case Studies on Dunhuang
  92. LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
  93. Learning Divergence Fields for Shift-Robust Graph Representations
  94. Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation
  95. Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation
  96. M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering
  97. MILP-FBGen: LP/MILP Instance Generation with Feasibility/Boundedness
  98. MixSATGEN: Learning Graph Mixing for SAT Instance Generation
  99. MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation
  100. Node2ket: Efficient High-Dimensional Network Embedding in Quantum Hilbert Space
  101. Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
  102. OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport
  103. On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm
  104. PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
  105. PhiloGPT: A Philology-Oriented Large Language Model for Ancient Chinese Manuscripts with Dunhuang as Case Study
  106. Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-End Oriented Object Detection with Single Point Supervision
  107. PointOBB: Learning Oriented Object Detection via Single Point Supervision
  108. PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling
  109. QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
  110. ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization
  111. ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation
  112. Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptions
  113. Rethinking Parity Check Enhanced Symmetry-Preserving Ansatz
  114. Rethinking the symmetry-preserving circuits for constrained variational quantum algorithms
  115. SSL4Q: Semi-Supervised Learning of Quantum Data with Application to Quantum State Classification
  116. Theoretically Achieving Continuous Representation of Oriented Bounding Boxes
  117. Think2Drive: Efficient Reinforcement Learning by Thinking with Latent World Model for Autonomous Driving (in CARLA-V2)
  118. Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation
  119. Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach
  120. Towards LLM4QPE: Unsupervised Pretraining of Quantum Property Estimation and A Benchmark
  121. Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
  122. UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis
  123. Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance
  124. ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization
  125. What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information