Junnan Li
- Papers
- 17
Cite
Notes
Only stored in your browser.
Authored papers
17A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
arXiv 2025
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
arXiv 2025
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
arXiv 2025
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
arXiv 2025
Scalable Chain of Thoughts via Elastic Reasoning
arXiv 2025
GTA1: GUI Test-time Scaling Agent
arXiv 2025
Fractured Chain-of-Thought Reasoning
arXiv 2025
ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks
arXiv 2025
Aria-UI: Visual Grounding for GUI Instructions
arXiv 2024
VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation
CVPR 2025 1
Aria: An Open Multimodal Native Mixture-of-Experts Model
arXiv 2024
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
arXiv 2024
OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs
arXiv 2024
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
arXiv 2023
ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
CVPR 2024 1
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM
arXiv 2023
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
CVPR 2022 1
Affiliations
Frequent co-authors
10from 17 papers