Xiangjun Fan

Orcid: 0009-0009-6689-6560

According to our database1, Xiangjun Fan authored at least 26 papers between 2020 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Synthetic Sandbox for Training Machine Learning Engineering Agents.
CoRR, April, 2026

GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification.
CoRR, March, 2026

LLM-Driven Reasoning for Constraint-Aware Feature Selection in Industrial Systems.
CoRR, March, 2026

TARo: Token-level Adaptive Routing for LLM Test-time Alignment.
CoRR, March, 2026

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning.
CoRR, March, 2026

DREAM: Where Visual Understanding Meets Text-to-Image Generation.
CoRR, March, 2026

Reason to Contrast: A Cascaded Multimodal Retrieval Framework.
CoRR, February, 2026

Xray-Visual Models: Scaling Vision models on Industry Scale Data.
CoRR, February, 2026

Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System.
CoRR, February, 2026

Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation.
CoRR, February, 2026

EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization.
CoRR, February, 2026

Guiding Generative Recommender Systems with Structured Human Priors via Multi-head Decoding.
Proceedings of the ACM Web Conference 2026, 2026

RankID: A Unified Semantic ID Learned through Multi-Stage Semantic Alignment of Multimodal Features.
Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining, 2026

2025
Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding.
CoRR, October, 2025

Think Then Embed: Generative Context Improves Multimodal Embedding.
CoRR, October, 2025

Exploring System 1 and 2 communication for latent reasoning in LLMs.
CoRR, October, 2025

RecoWorld: Building Simulated Environments for Agentic Recommender Systems.
CoRR, September, 2025

GEM: Empowering LLM for both Embedding Generation and Language Understanding.
CoRR, June, 2025

S'MoRE: Structural Mixture of Residual Experts for LLM Fine-tuning.
CoRR, April, 2025

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment.
CoRR, January, 2025

Quantifying Generalization Complexity for Large Language Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Efficient Sequential Recommendation for Long Term User Interest Via Personalization.
Proceedings of the IEEE International Conference on Data Mining, 2025

CAFE: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning.
Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV 2025, 2025

2023
HallE-Switch: Rethinking and Controlling Object Existence Hallucinations in Large Vision Language Models for Detailed Caption.
CoRR, 2023

2021
Learning An End-to-End Structure for Retrieval in Large-Scale Recommendations.
Proceedings of the CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1, 2021

2020
Deep Retrieval: An End-to-End Learnable Structure Model for Large-Scale Recommendations.
CoRR, 2020


  Loading...