Han-Bit Kang

hbkang's activity

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

upvoted a collection 3 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 527 items • Updated about 7 hours ago • 109

upvoted a paper 3 days ago

Towards Foundation Decision Models: Drex

Paper • 2611.07854 • Published 5 days ago • 25

upvoted a paper 5 days ago

LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers

Paper • 2611.05304 • Published 6 days ago • 13

upvoted a paper 6 days ago

BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion

Paper • 2610.41574 • Published 11 days ago • 11

upvoted a paper 10 days ago

Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs

Paper • 2610.36671 • Published 14 days ago • 117

upvoted 3 papers 13 days ago

On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction

Paper • 2610.22543 • Published 15 days ago • 29

LociArt: A Unified Paradigm for Free-Style Local Video Stylization

Paper • 2610.36456 • Published 14 days ago • 37

MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting

Paper • 2610.35724 • Published 15 days ago • 19

upvoted a paper 16 days ago

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper • 2610.31329 • Published 19 days ago • 47

upvoted a paper 18 days ago

RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting

Paper • 2610.27712 • Published 21 days ago • 21

upvoted a paper 23 days ago

Copy-Paste Language Models

Paper • 2610.19247 • Published 28 days ago • 10

upvoted a paper 27 days ago

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published 28 days ago • 139

upvoted 4 papers 28 days ago

ARCS: Towards Precise Text-to-SQL via Structured Disambiguation

Paper • 2610.09396 • Published Oct 7 • 12

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Paper • 2609.39600 • Published Sep 30 • 34

Universal Textual Teaching for LLMs

Paper • 2610.12114 • Published Oct 8 • 16

PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence

Paper • 2609.37712 • Published Sep 29 • 28

upvoted 3 papers about 1 month ago

SearchJev: A Fast and Calibrated System-1 Model for Search Agents

Paper • 2610.05107 • Published Oct 4 • 31

Language Models that Play Chess and Explain Their Moves

Paper • 2610.03695 • Published Oct 2 • 19

Chinese-Jev: Bringing System One Model to Chinese-Language Tasks

Paper • 2609.36965 • Published Sep 29 • 10

upvoted a paper about 2 months ago

The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction

Paper • 2609.18063 • Published Sep 16 • 30