PPaperPicks

Jieping Ye

63 papers at tracked venues · 52 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Bridging the Language Gap: Uncovering and Aligning Shared Circuits for Multi-Hop Reasoning in Multilingual LLMs
  2. Enhancing Spatial Reasoning Through Visual and Textual Thinking
  3. FGD-Align: Pluralistic Alignment for Large Language Models via Fuzzy Group Decision-Making
  4. Flora: Effortless Context Construction to Arbitrary Length and Scale
  5. On the Step Length Confounding in LLM Reasoning Data Selection
  6. CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery
  7. Concise and Organized Perception Facilitates Reasoning in Large Language Models
  8. Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
  9. Controlling Thinking Speed in Reasoning Models
  10. Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models
  11. EchoShot: Multi-Shot Portrait Video Generation
  12. Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
  13. From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
  14. GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching
  15. Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions
  16. HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
  17. IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding
  18. Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach
  19. Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings
  20. Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models
  21. Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
  22. Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
  23. NeuronMerge: Merging Models via Functional Neuron Groups
  24. PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration
  25. PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Model
  26. ROPO: Robust Preference Optimization for Large Language Models
  27. ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
  28. Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
  29. SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
  30. SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning
  31. Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs
  32. Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs
  33. Structure-aware Domain Knowledge Injection for Large Language Models
  34. The 14th International Workshop on Urban Computing
  35. TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
  36. Tracing and Dissecting How LLMs Recall Factual Knowledge for Real World Questions
  37. Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models
  38. A3S: A General Active Clustering Method with Pairwise Constraints
  39. AddressCLIP: Empowering Vision-Language Models for City-Wide Image Address Localization
  40. Boosting Vanilla Lightweight Vision Transformers via Re-parameterization
  41. Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
  42. Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
  43. Discrete Latent Perspective Learning for Segmentation and Detection
  44. Efficient Denoising Diffusion via Probabilistic Masking
  45. Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning
  46. Enhancing LLM's Cognition via Structurization
  47. Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
  48. From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
  49. Graph-constrained diffusion for End-to-End Path Planning
  50. INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
  51. Instance-adaptive Zero-shot Chain-of-Thought Prompting
  52. Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding
  53. Interpreting and Improving Large Language Models in Arithmetic Calculation
  54. LLaFS: When Large Language Models Meet Few-Shot Segmentation
  55. Learning Neural Volumetric Pose Features for Camera Localization
  56. Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
  57. Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
  58. Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
  59. RoScenes: A Large-Scale Multi-view 3D Dataset for Roadside Perception
  60. SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graph
  61. The 13th International Workshop on Urban Computing
  62. The 4th KDD Workshop on Deep Learning for Spatiotemporal Data, Applications, and Systems (DeepSpatial'24)
  63. URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering