Kim Jiwan

JiwanKim's activity

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

upvoted 3 papers 8 days ago

Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models

Paper • 2512.01949 • Published 10 days ago • 8

Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization

Paper • 2511.22586 • Published 15 days ago • 6

Qwen3-VL Technical Report

Paper • 2511.21631 • Published 15 days ago • 120

upvoted 2 papers 14 days ago

Monet: Reasoning in Latent Visual Space Beyond Images and Language

Paper • 2511.21395 • Published 16 days ago • 15

NVIDIA Nemotron Parse 1.1

Paper • 2511.20478 • Published 17 days ago • 20

upvoted a paper 15 days ago

Soft Adaptive Policy Optimization

Paper • 2511.20347 • Published 17 days ago • 38

upvoted a paper 16 days ago

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Paper • 2511.19418 • Published 17 days ago • 27

upvoted 2 papers 18 days ago

SAM 3: Segment Anything with Concepts

Paper • 2511.16719 • Published 21 days ago • 109

SAM 3D: 3Dfy Anything in Images

Paper • 2511.16624 • Published 21 days ago • 106

upvoted a paper 22 days ago

OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models

Paper • 2511.14582 • Published 24 days ago • 17

upvoted 3 papers 23 days ago

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

Paper • 2511.09611 • Published 29 days ago • 68

P1: Mastering Physics Olympiads with Reinforcement Learning

Paper • 2511.13612 • Published 25 days ago • 132

Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data

Paper • 2511.12609 • Published 26 days ago • 102

upvoted a paper 24 days ago

Depth Anything 3: Recovering the Visual Space from Any Views

Paper • 2511.10647 • Published 28 days ago • 93

upvoted a paper 26 days ago

Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs

Paper • 2511.05933 • Published Nov 8 • 7

upvoted a paper 27 days ago

Music Flamingo: Scaling Music Understanding in Audio Language Models

Paper • 2511.10289 • Published 29 days ago • 10

upvoted a paper 28 days ago

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Paper • 2511.08892 • Published about 1 month ago • 195

upvoted a paper 29 days ago

The Path Not Taken: RLVR Provably Learns Off the Principals

Paper • 2511.08567 • Published about 1 month ago • 32

upvoted 2 papers about 1 month ago

Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at Scale

Paper • 2511.05705 • Published Nov 7 • 6

Robot Learning from a Physical World Model

Paper • 2511.07416 • Published Nov 10 • 30