Jinsong Li

Jinsong-Li's activity

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

upvoted a paper 8 days ago

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Paper • 2512.16969 • Published 11 days ago • 106

authored 3 papers 5 months ago

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

Paper • 2502.08590 • Published Feb 12 • 42

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Paper • 2506.04997 • Published Jun 5

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

Paper • 2506.19848 • Published Jun 24 • 26

upvoted a paper 5 months ago

SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

Paper • 2508.04700 • Published Aug 6 • 52

authored a paper 5 months ago

Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

Paper • 2508.00819 • Published Aug 1 • 62

commented a paper 5 months ago

LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

Paper • 2508.00477 • Published Aug 1 • 9 •

2

upvoted 2 papers 5 months ago

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

Paper • 2508.02193 • Published Aug 4 • 133

Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

Paper • 2508.00819 • Published Aug 1 • 62

upvoted a paper 6 months ago

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

Paper • 2506.19848 • Published Jun 24 • 26

upvoted a paper 7 months ago

Video World Models with Long-term Spatial Memory

Paper • 2506.05284 • Published Jun 5 • 55

liked 2 datasets 9 months ago

SincereX/ChartBench

Viewer • Updated Oct 14, 2024 • 277k • 184 • 10

HuggingFaceM4/ChartQA

Viewer • Updated Mar 5, 2024 • 32.7k • 7.78k • 58

upvoted a paper 10 months ago

SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation

Paper • 2502.13128 • Published Feb 18 • 41

upvoted a paper 11 months ago

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

Paper • 2502.08590 • Published Feb 12 • 42

upvoted 2 papers 12 months ago

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning

Paper • 2501.03226 • Published Jan 6 • 43

Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

Paper • 2501.03218 • Published Jan 6 • 35

upvoted 2 papers about 1 year ago

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Paper • 2410.16268 • Published Oct 21, 2024 • 69

Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate

Paper • 2410.07167 • Published Oct 9, 2024 • 39

upvoted a paper over 1 year ago

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

Paper • 2407.03320 • Published Jul 3, 2024 • 94