语义解析论文趋势 2023–2026

主要结论

• 语义解析论文从 2023 年的 58 篇增长到 2026 年的 79 篇，三年间扩大到约 1.4 倍。
• CVPR 是发语义解析论文最多的会议，2023–2026 年共 117 篇，占四个会议总量的 51%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 20 篇。
• 在「神经符号」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的数学推理是 10 倍，语义解析是 1.4 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026ASQ: Agent-guided Semantic-aware Quantization for Large Language Models
• ICML 2026CURE: Consistency-under-Unified Semantic Regularization for Generalized Category Discovery
• ICLR 2026vCache: Verified Semantic Prompt Caching
• CVPR 2026AdaSFormer Adaptive Serialized Transformers for Monocular Semantic Scene Completion from
• NeurIPS 2025A Semantic Parsing Framework for End-to-End Time Normalization
• ICML 2025HashAttention: Semantic Sparsity for Faster Inference
• ICLR 2025Discrete Latent Plans via Semantic Skill Abstractions
• CVPR 2025DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID
• NeurIPS 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
• ICML 2024Language Models as Semantic Indexers
• ICLR 2024A Semantic Invariant Robust Watermark for Large Language Models
• CVPR 2024EFormer: Enhanced Transformer towards Semantic-Contour Features of Foreground for Portraits Matting
• NeurIPS 2023BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing
• ICML 2023Marginalization is not Marginal: No Bad VAE Local Minima when Learning Optimal Sparse Representations
• ICLR 2023Compositional Law Parsing with Latent Random Functions
• CVPR 2023GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning
• NeurIPS 2026Bandits via Additive Quantized Representations
• ICML 2026Learning Sparse Visual Representations via Spatial-Semantic Factorization
• ICLR 2026Cache-to-Cache: Direct Semantic Communication Between Large Language Models
• CVPR 2026GeoSURGE Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings

全部语义解析论文

共 230 篇，第 2 / 5 页

51. ICML 2026WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views
52. NeurIPS 2026ASQ: Agent-guided Semantic-aware Quantization for Large Language Models
53. NeurIPS 2026Bandits via Additive Quantized Representations
54. NeurIPS 2026Beyond Pixel-wise Supervision: Local Structure Regularization for Semantic Segmentation
55. NeurIPS 2026ChartArena: A Unified Benchmark with Atomic-Primitive Reasoning for Chart Parsing
56. NeurIPS 2026CI4A: Semantic Component Interfaces for Agents Empowering Web Automation
57. NeurIPS 2026DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
58. NeurIPS 2026Dense Cross-Tokenizer Distillation via Semantic Optimal Local Alignment
59. NeurIPS 2026Do Semantic Distance Tests Actually Predict Creativity in Large Language Models?
60. NeurIPS 2026DSSA: Dynamic Sparse Semantic Anchoring for Purifying Protective Perturbations against Diffusion Models
61. NeurIPS 2026Emergent Semantic Role Understanding in Language Models
62. NeurIPS 2026Evidential Semantic Uncertainty Decomposition for Large Language Models
63. NeurIPS 2026Face Deepfake-aware Recovery via Semantic-driven Facial Representation-based Watermarking
64. NeurIPS 2026Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
65. NeurIPS 2026Hide to Guide: Learning via Semantic Masking
66. NeurIPS 2026Learning a Unified Cross-Model Semantic Dictionary via Gated Bottleneck Sparse Autoencoders
67. NeurIPS 2026Learning Sparse Semantic-Cortical Atoms for Multisubject Naturalistic fMRI Encoding
68. NeurIPS 2026MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
69. NeurIPS 2026Off-Policy Evaluation of Large Language Models via Learned Semantic Bottleneck Embeddings
70. NeurIPS 2026Position: Semantic Uncertainty Measures Disagreement, Not Reliability
71. NeurIPS 2026S-EDL: Eliciting Self-Evidence from Sequence Likelihoods for Semantic Calibration of LLMs
72. NeurIPS 2026SCG-HF: Semantic Consistency Grouping for Hierarchical Fusion in Video Emotion Recognition
73. NeurIPS 2026Semantic Freedom Bottleneck for Domain-Generalized Multimodal Face Anti-Spoofing
74. NeurIPS 2026Semantic Search over 9 Million Mathematical Theorems
75. NeurIPS 2026SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data
76. NeurIPS 2026The Locality Cost of Semantic Patch Self-Distillation
77. NeurIPS 2026Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume
78. NeurIPS 2026UNICOM: Unified Multimodal Modeling via Compressed Continuous Semantic Representations
79. NeurIPS 2026ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
80. CVPR 20253D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations
81. CVPR 2025Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
82. CVPR 2025Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
83. CVPR 2025Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior
84. CVPR 2025DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
85. CVPR 2025DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID
86. CVPR 2025FluxSpace: Disentangled Semantic Editing in Rectified Flow Models
87. CVPR 2025Layered Image Vectorization via Semantic Simplification
88. CVPR 2025Learning Visual Composition through Improved Semantic Guidance
89. CVPR 2025MaSS13K: A Matting-level Semantic Segmentation Benchmark
90. CVPR 2025Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction
91. CVPR 2025SEC-Prompt:SEmantic Complementary Prompting for Few-Shot Class-Incremental Learning
92. CVPR 2025SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations
93. CVPR 2025SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion
94. CVPR 2025SINR: Sparsity Driven Compressed Implicit Neural Representations
95. CVPR 2025SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
96. CVPR 2025The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generationf
97. CVPR 2025Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion
98. CVPR 2025TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features
99. ICLR 2025Discrete Latent Plans via Semantic Skill Abstractions
100. ICLR 2025Improving Unsupervised Constituency Parsing via Maximizing Semantic Information

常见问题

2023–2026 年四大会议一共有多少篇语义解析论文？

共 230 篇，按年份分别是 2023 年 58 篇、2024 年 53 篇、2025 年 40 篇、2026 年 79 篇。

NeurIPS 2026 有多少篇语义解析论文？

NeurIPS 2026 有 28 篇语义解析论文，上一届是 12 篇。

ICLR 2026 有多少篇语义解析论文？

ICLR 2026 有 9 篇语义解析论文，上一届是 5 篇。

ICML 2026 有多少篇语义解析论文？

ICML 2026 有 12 篇语义解析论文，上一届是 4 篇。

CVPR 2026 有多少篇语义解析论文？

CVPR 2026 有 30 篇语义解析论文，上一届是 19 篇。

哪个会议的语义解析论文最多？

CVPR，2023–2026 年共 117 篇。