Xiang Hu
12 papers · 2020–2026 · 5 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 ↓+4 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (26) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🧬 Topic Evolution
🗃️
Keyword Collector
(66)
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Natural Language Processing
(10)
Deep Learning
(8)
Generation
(7)
Machine Learning
(6)
Architectures
(6)
Artificial Intelligence
(4)
Core AI
(4)
Understanding
(4)
Learning Types · Deep Learning
(3)
Applications
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Resources & Methods
(2)
Interdisciplinary
(1)
Reinforcement Learning
(1)
Keywords
large language model
(3)
grammar induction
(2)
cky parsing
(2)
bidirectional language model
(2)
language modeling
(2)
self-supervised learning
(2)
syntactic language model
(2)
unsupervised parsing
(2)
constituency parsing
(1)
intent detection
(1)
natural language inference
(1)
autoregressive transformer
(1)
inference efficiency
(1)
recursive neural network
(1)
deep learning
(1)
context length
(1)
sequence-to-sequence generation
(1)
text representation
(1)
mixture of expert
(1)
language model
(1)
Papers
Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models
ACL 2026
A Systematic Study of Compositional Syntactic Transformer Language Models
ACL 2025
Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
ICML 2025
NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language Models
ACL 2025
Tree-Structured Non-Autoregressive Decoding for Sequence-to-Sequence Text Generation
EMNLP 2025
Unsupervised Morphological Tree Tokenizer
ACL 2025
Augmenting Transformers with Recursively Composed Multi-grained Representations
ICLR 2024
Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale
ACL 2024
A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification
ICLR 2023
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation
EMNLP 2022
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling
ACL 2021
Interactive Question Clarification in Dialogue via Reinforcement Learning
COLING 2020