Xinnan Dai

5 papers · 2023–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

ICLR (3) ACL (1) ICML (1)

Top co-authors

Caihua Shan (2) Jiliang Tang (2) Dongsheng Li (2) Jun Pang (1) Michael J. Morais (1) Shenglai Zeng (1) Monica Xiao Cheng (1) Dante Everaert (1) Rohit Patki (1) Tianqi Zheng (1)

Research topics

Artificial Intelligence (5) Core AI (5) Deep Learning (2) Machine Learning (2) Core Methods (2) Mathematics & Optimization (1) Architectures (1) Learning Types (1) Models (1) Optimization (1)

Keywords

large language model (2) benchmark evaluation (1) graph structure (1) gaussian priors (1) adaptive regularization (1) monte carlo tree search (1) pre-trained model (1) model explanation (1) temporal graph (1) spatial transcriptomics (1) user personalization (1) context compression (1) autonomous discovery (1) attention pattern (1) graph neural network (1) cell embedding (1) graph pattern understanding (1) fidelity-sparsity curve (1) deterministic edges (1) edge recovery (1)

Papers

Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs ACL 2026 Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms ICML 2025 How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension ICLR 2025 CellPLM: Pre-training of Cell Language Model Beyond Single Cells ICLR 2024 Explaining Temporal Graph Models through an Explorer-Navigator Framework ICLR 2023