zikun-li (Zikun Li)

upvoted a paper 5 days ago

Sample-Efficient Alignment for LLMs

Paper • 2411.01493 • Published 10 days ago • 10

upvoted a paper about 1 month ago

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

Paper • 2410.05076 • Published Oct 7 • 6

upvoted 11 papers about 2 months ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19 • 134

HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models

Paper • 2409.16191 • Published Sep 24 • 41

Towards a Unified View of Preference Learning for Large Language Models: A Survey

Paper • 2409.02795 • Published Sep 4 • 72

Self-Harmonized Chain of Thought

Paper • 2409.04057 • Published Sep 6 • 16

Agent Workflow Memory

Paper • 2409.07429 • Published Sep 11 • 27

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Paper • 2409.04109 • Published Sep 6 • 43

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Paper • 2409.08264 • Published Sep 12 • 43

DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?

Paper • 2409.07703 • Published Sep 12 • 66

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Paper • 2409.10516 • Published Sep 16 • 37

NVLM: Open Frontier-Class Multimodal LLMs

Paper • 2409.11402 • Published Sep 17 • 71

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published Sep 17 • 107

upvoted 7 papers 2 months ago

Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation

Paper • 2408.15239 • Published Aug 27 • 27

Zikun Li

AI & ML interests

Organizations

zikun-li's activity

Sample-Efficient Alignment for LLMs

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

Training Language Models to Self-Correct via Reinforcement Learning

HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models

Towards a Unified View of Preference Learning for Large Language Models: A Survey

Self-Harmonized Chain of Thought

Agent Workflow Memory

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

NVLM: Open Frontier-Class Multimodal LLMs

OmniGen: Unified Image Generation

Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation

Diffusion Models Are Real-Time Game Engines

Writing in the Margins: Better Inference Pattern for Long Context Retrieval

Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts

Efficient LLM Scheduling by Learning to Rank

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

CogVLM2: Visual Language Models for Image and Video Understanding