1
Graph Neural Networks are Heuristics
颠覆认知：GNN本质是高级启发式算法而非特征学习器，理论推导+实验验证给出新视角
arXiv:2601.13465v4 Announce Type: replace Abstract: Graph neural networks are usually treated as auxiliaries for combinatorial optimization: they imit…
2
Teacher Supervision over Representation Equivalence Classes
颠覆知识蒸馏常规认知：预训练表征只有等价类意义，匹配坐标是伪命题
arXiv:2607.03572v1 Announce Type: cross Abstract: Knowledge distillation is usually framed as a choice of what to match in the teacher - its logits, h…
3
ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs
无需训练，仅通过反转输入文本，就能显著提升解码器LLM的文本嵌入质量。
arXiv:2606.05858v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened new avenues for generating training-free t…
4
Noise-Aware Visual Representation Learning for Medical Visual Question Answering
医学视觉问答新突破：噪声感知学习提升视觉表示鲁棒性
arXiv:2606.05535v1 Announce Type: cross Abstract: Medical visual question answering (Med-VQA) has strong potential for clinical decision support by en…
5
CoralBay: A Self-Supervised CT Foundation Model
自监督学习新突破：CoralBay开创CT基础模型，无需标注数据即可高效训练医学影像AI
arXiv:2606.03888v1 Announce Type: new Abstract: Self-supervised learning has enabled large-scale pre-training on 2D natural images, producing general-…
6
CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs
基于码本的连续用户表示方法，让LLM实现高效个性化生成，无需微调模型参数。
arXiv:2602.00742v2 Announce Type: replace Abstract: User modeling characterizes individuals through their preferences and behavioral patterns to enabl…
7
View Space: Learning Representation across Arbitrary Graphs
针对任意图结构学习表示的通用框架，原创性高，已被ICML 2026接收。
arXiv:2512.11561v2 Announce Type: replace Abstract: Generalizing pretrained models to unseen datasets without retraining is a central challenge toward…
8
Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning
KDD 2026接收，提出用最小充分表示学习为LLM高效合成领域数据，降低人工成本。
arXiv:2605.30039v1 Announce Type: new Abstract: Large Language Models have demonstrated remarkable progress in general-purpose capabilities and can ac…
9
Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings
超越思维链？新研究提出"重写"范式，将生成式多模态嵌入统一为通用接口，重塑AI推理与表示方式。
arXiv:2604.22280v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal mult…
10
Training-Free Vector Quantization via Gaussian VAEs
提出一种无需训练的向量量化新方法，利用高斯VAE实现高效表示学习，为量化领域开辟新路径。
arXiv:2512.06609v3 Announce Type: replace Abstract: Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images…
11
Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings
食品成分嵌入空间的几何结构揭秘，用AI分析食材间隐藏关系，带你从数学视角重新理解烹饪。
arXiv:2605.22391v1 Announce Type: cross Abstract: We present Epicure, a family of three sibling skip-gram ingredient embeddings retrained from scratch…
12
Hypergraph as Language
跳出传统图思维，用超图语言表达复杂关系，LLM建模迎来新范式。
arXiv:2605.21858v1 Announce Type: new Abstract: Large language models (LLMs) have recently shown strong potential in modeling relational structures. H…
13
Graph Embedding in the Graph Fractional Fourier Transform Domain
在图的分数傅里叶变换域中嵌入，突破传统谱嵌入的表达瓶颈，捕获更全面的图结构特征
arXiv:2508.02383v2 Announce Type: replace Abstract: Spectral graph embedding plays a critical role in graph representation learning by generating low-…
14
Structure-Aware Masking for Protein Representation Learning
突破性结构感知掩码方法，提升蛋白质表征学习效能，为AI制药与蛋白质设计提供新思路
arXiv:2605.16581v1 Announce Type: new Abstract: Masked language modeling (MLM) is the standard objective for training protein language models, typical…
15
Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning
用掩码自编码器做脑功能连接自监督表示学习，如何高效分词？双线性分词方案给出新思路
arXiv:2605.14048v1 Announce Type: new Abstract: Masked autoencoders (MAEs) have recently shown promise for self-supervised representation learning of …
16
Improved Baselines with Representation Autoencoders
用预训练视觉编码器替代传统 VAE，系统性设计选择研究揭示三大简化改进思路。
arXiv:2605.18324v1 Announce Type: cross Abstract: Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this p…
17
PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
提出PaAno方法，用补丁表示学习实现高效时间序列异常检测，兼顾性能与计算资源
arXiv:2602.01359v2 Announce Type: replace-cross Abstract: Although recent studies on time-series anomaly detection have increasingly adopted ever-larg…
18
AudioMosaic: Contrastive Masked Audio Representation Learning
新方法AudioMosaic融合对比学习与掩码表示，攻克音频自监督的对比方法难题。
arXiv:2605.14231v1 Announce Type: cross Abstract: Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale …