Haoran Li
- Papers
- 17
Cite
Notes
Only stored in your browser.
Authored papers
17OmniForcing: Unleashing Real-time Joint Audio-Visual Generation
arXiv 2026
Do Reasoning Models Enhance Embedding Models?
arXiv 2026
CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs
arXiv 2026
ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
arXiv 2025
HoPE: Hybrid of Position Embedding for Length Generalization in Vision-Language Models
arXiv 2025
DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation
arXiv 2025
Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational History
arXiv 2025
RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models
arXiv 2024
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
arXiv 2024
ROOT: VLM based System for Indoor Scene Understanding and Beyond
arXiv 2024
Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry Network
arXiv 2024
Analytic Federated Learning
arXiv 2024
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
arXiv 2024
Persona Knowledge-Aligned Prompt Tuning Method for Online Debate
arXiv 2024
Multi-step Jailbreaking Privacy Attacks on ChatGPT
arXiv 2023
CgT-GAN: CLIP-guided Text GAN for Image Captioning
arXiv 2023
AnswerSumm: A Manually-Curated Dataset and Pipeline for Answer Summarization
NAACL 2022 7
Affiliations
Frequent co-authors
10from 17 papers