Siqiao Xue
10 papers · 2022–2025 · 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (34) 🐣 Hot Topic Early Bird 💎 Century Club · Bronze
🗃️
Keyword Collector
(52)
Venues
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(8)
Core AI
(7)
Deep Learning
(6)
Learning Types · Machine Learning
(4)
Optimization & Theory
(4)
Architectures
(3)
Learning Types · Deep Learning
(3)
Data Science & Analytics
(2)
Core Methods
(2)
Learning Paradigms
(2)
Methods
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Bayesian & Probabilistic
(1)
Keywords
large language model
(4)
event sequence
(4)
temporal point process
(3)
prompt learning
(2)
continual learning
(2)
graph neural network
(2)
time series
(2)
transfer learning
(1)
message passing
(1)
domain generalization
(1)
instruction tuning
(1)
autoregressive model
(1)
bellman equation
(1)
time series forecasting
(1)
few-shot learning
(1)
probabilistic model
(1)
continuous time
(1)
knowledge transfer
(1)
energy function
(1)
model-based reinforcement learning
(1)
Papers
Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
ICLR 2025
CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending
ACL 2024
EasyTPP: Towards Open Benchmarking Temporal Point Processes
ICLR 2024
GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting
AAAI 2024
LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs
AAAI 2024
Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes
AAAI 2023
Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning
NeurIPS 2023
Prompt-augmented Temporal Point Process for Streaming Event Sequence
NeurIPS 2023
Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompts
EMNLP 2023
HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences
NeurIPS 2022