Han-Bit Kang

hbkang's activity

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

upvoted 2 papers about 4 hours ago

Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

Paper • 2601.17027 • Published 10 days ago • 19

Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding

Paper • 2506.16035 • Published Jun 19, 2025 • 89

upvoted a paper about 8 hours ago

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch

Paper • 2601.13606 • Published 7 days ago • 6

upvoted a paper 1 day ago

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Paper • 2601.15165 • Published 6 days ago • 64

upvoted 2 papers 4 days ago

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published 9 days ago • 177

GutenOCR: A Grounded Vision-Language Front-End for Documents

Paper • 2601.14490 • Published 6 days ago • 32

upvoted a paper 5 days ago

Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings

Paper • 2512.12167 • Published Dec 13, 2025 • 2

upvoted a paper 6 days ago

Toward Efficient Agents: Memory, Tool learning, and Planning

Paper • 2601.14192 • Published 7 days ago • 49

upvoted a paper 8 days ago

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published 14 days ago • 145

upvoted a paper 11 days ago

Solar Open Technical Report

Paper • 2601.07022 • Published 16 days ago • 63

upvoted a paper 12 days ago

End-to-End Video Character Replacement without Structural Guidance

Paper • 2601.08587 • Published 14 days ago • 8

upvoted a paper 13 days ago

GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting

Paper • 2403.08551 • Published Mar 13, 2024 • 11

upvoted a paper 14 days ago

FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing

Paper • 2601.01720 • Published 22 days ago • 6

upvoted 3 papers 15 days ago

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

Paper • 2601.04720 • Published 19 days ago • 50

AgentOCR: Reimagining Agent History via Optical Self-Compression

Paper • 2601.04786 • Published 19 days ago • 28

Self-Supervised Prompt Optimization

Paper • 2502.06855 • Published Feb 7, 2025 • 15

upvoted 3 papers 18 days ago

Language Modelling with Pixels

Paper • 2207.06991 • Published Jul 14, 2022 • 2

Multilingual Pretraining for Pixel Language Models

Paper • 2505.21265 • Published May 27, 2025 • 1

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation

Paper • 2601.03955 • Published 20 days ago • 3

upvoted a paper 19 days ago

Synthetic continued pretraining

Paper • 2409.07431 • Published Sep 11, 2024 • 5