Han-Bit Kang

hbkang's activity

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

upvoted a paper 1 minute ago

Scaling Embeddings Outperforms Scaling Experts in Language Models

Paper • 2601.21204 • Published 3 days ago • 90

upvoted a paper about 21 hours ago

One-step Latent-free Image Generation with Pixel Mean Flows

Paper • 2601.22158 • Published 2 days ago • 6

upvoted 7 papers 2 days ago

LongCat-Video Technical Report

Paper • 2510.22200 • Published Oct 25, 2025 • 32

LongCat-Flash-Omni Technical Report

Paper • 2511.00279 • Published Oct 31, 2025 • 25

LongCat-Image Technical Report

Paper • 2512.07584 • Published Dec 8, 2025 • 20

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Paper • 2601.10355 • Published 17 days ago • 39

LongCat-Flash-Thinking-2601 Technical Report

Paper • 2601.16725 • Published 9 days ago • 169

DeepSeek-OCR 2: Visual Causal Flow

Paper • 2601.20552 • Published 4 days ago • 43

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published 4 days ago • 27

upvoted 5 papers 3 days ago

OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

Paper • 2505.08617 • Published May 13, 2025 • 42

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published 4 days ago • 19

Towards Pixel-Level VLM Perception via Simple Points Prediction

Paper • 2601.19228 • Published 5 days ago • 15

Self-Distillation Enables Continual Learning

Paper • 2601.19897 • Published 4 days ago • 21

A Pragmatic VLA Foundation Model

Paper • 2601.18692 • Published 6 days ago • 44

upvoted 2 papers 4 days ago

Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction

Paper • 2601.17668 • Published 7 days ago • 4

Self-Refining Video Sampling

Paper • 2601.18577 • Published 6 days ago • 23

upvoted 3 papers 5 days ago

Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

Paper • 2601.17027 • Published 15 days ago • 40

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

Paper • 2506.16035 • Published Jun 19, 2025 • 89

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch

Paper • 2601.13606 • Published 12 days ago • 10

upvoted a paper 6 days ago

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

Paper • 2601.15165 • Published 11 days ago • 68