Zikun Li

zikun-li's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper 7 days ago

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

Paper • 2410.05076 • Published 9 days ago • 6

upvoted 2 papers 20 days ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published 27 days ago • 131

HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models

Paper • 2409.16191 • Published 22 days ago • 41

upvoted 9 papers 28 days ago

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 • 42

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

Paper • 2409.08264 • Published Sep 12 • 42

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 about 1 month ago • 34

NVLM: Open Frontier-Class Multimodal LLMs

Paper • 2409.11402 • Published 29 days ago • 69

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published 29 days ago • 82

upvoted 8 papers about 2 months ago

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

Paper • 2408.15239 • Published Aug 27 • 27

Diffusion Models Are Real-Time Game Engines

Paper • 2408.14837 • Published Aug 27 • 121

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

Paper • 2408.14906 • Published Aug 27 • 138

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

Paper • 2408.15664 • Published Aug 28 • 11

Efficient LLM Scheduling by Learning to Rank

Paper • 2408.15792 • Published Aug 28 • 19

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

Paper • 2408.15998 • Published Aug 28 • 83

CogVLM2: Visual Language Models for Image and Video Understanding

Paper • 2408.16500 • Published Aug 29 • 56

Law of Vision Representation in MLLMs

Paper • 2408.16357 • Published Aug 29 • 92

upvoted 16 papers 2 months ago

Layerwise Recurrent Router for Mixture-of-Experts

Paper • 2408.06793 • Published Aug 13 • 30

Imagen 3

Paper • 2408.07009 • Published Aug 13 • 60

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Paper • 2408.06072 • Published Aug 12 • 35

ControlNeXt: Powerful and Efficient Control for Image and Video Generation

Paper • 2408.06070 • Published Aug 12 • 52

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Paper • 2408.05147 • Published Aug 9 • 37

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Paper • 2408.05211 • Published Aug 9 • 46

Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models

Paper • 2408.04594 • Published Aug 8 • 14

Transformer Explainer: Interactive Learning of Text-Generative Models

Paper • 2408.04619 • Published Aug 8 • 154

MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization

Paper • 2408.02555 • Published Aug 5 • 28

Language Model Can Listen While Speaking

Paper • 2408.02622 • Published Aug 5 • 37

RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation

Paper • 2408.02545 • Published Aug 5 • 32

MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Paper • 2408.01800 • Published Aug 3 • 74

Gemma 2: Improving Open Language Models at a Practical Size

Paper • 2408.00118 • Published Jul 31 • 73

SAM 2: Segment Anything in Images and Videos

Paper • 2408.00714 • Published Aug 1 • 105

MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts

Paper • 2407.21770 • Published Jul 31 • 22

The Llama 3 Herd of Models

Paper • 2407.21783 • Published Jul 31 • 103

upvoted 24 papers 3 months ago

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning

Paper • 2407.18248 • Published Jul 25 • 30

Mixture of Nested Experts: Adaptive Processing of Visual Tokens

Paper • 2407.19985 • Published Jul 29 • 34

Diffusion Feedback Helps CLIP See Better

Paper • 2407.20171 • Published Jul 29 • 34

FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention

Paper • 2407.19918 • Published Jul 29 • 47

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

Paper • 2407.18121 • Published Jul 25 • 15

Understanding Reference Policies in Direct Preference Optimization

Paper • 2407.13709 • Published Jul 18 • 16

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

Paper • 2407.14057 • Published Jul 19 • 43

EVLM: An Efficient Vision-Language Model for Visual Understanding

Paper • 2407.14177 • Published Jul 19 • 42

BOND: Aligning LLMs with Best-of-N Distillation

Paper • 2407.14622 • Published Jul 19 • 17

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence

Paper • 2407.16655 • Published Jul 23 • 27

VILA^2: VILA Augmented VILA

Paper • 2407.17453 • Published Jul 24 • 38

E5-V: Universal Embeddings with Multimodal Large Language Models

Paper • 2407.12580 • Published Jul 17 • 38

Scaling Diffusion Transformers to 16 Billion Parameters

Paper • 2407.11633 • Published Jul 16 • 25

Qwen2-Audio Technical Report

Paper • 2407.10759 • Published Jul 15 • 54

Qwen2 Technical Report

Paper • 2407.10671 • Published Jul 15 • 154

Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning

Paper • 2406.02265 • Published Jun 4 • 6

MUSCLE: A Model Update Strategy for Compatible LLM Evolution

Paper • 2407.09435 • Published Jul 12 • 20

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Paper • 2407.09025 • Published Jul 12 • 127

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

Paper • 2407.01392 • Published Jul 1 • 39

Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams

Paper • 2406.08085 • Published Jun 12 • 13

Unveiling Encoder-Free Vision-Language Models

Paper • 2406.11832 • Published Jun 17 • 49

Compositional Video Generation as Flow Equalization

Paper • 2407.06182 • Published Jun 10 • 12

Associative Recurrent Memory Transformer

Paper • 2407.04841 • Published Jul 5 • 31

ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation

Paper • 2407.06135 • Published Jul 8 • 20