Seonghoon Hwang

SeonghoonHwang's activity

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

upvoted 20 papers about 7 hours ago

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Paper • 2607.22529 • Published Jul 24 • 49

HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement

Paper • 2607.18217 • Published Jul 20 • 55

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published Jul 13 • 61

DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space

Paper • 2607.25675 • Published Jul 28 • 70

HumanCLAW: Can Vision-Language Models Act Through a Body?

Paper • 2607.27180 • Published Jul 29 • 77

AlayaWorld: Long-Horizon and Playable Video World Generation

Paper • 2607.06291 • Published Jul 7 • 89

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published Jul 16 • 105

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published Jul 16 • 122

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Paper • 2606.29538 • Published Jul 16 • 147

PhiZero: A World Model Built Around Physical Language

Paper • 2607.28624 • Published Jul 30 • 175

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 526

EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

Paper • 2608.06197 • Published Aug 6 • 48

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

Paper • 2608.03571 • Published Aug 6 • 48

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published Aug 17 • 52

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

Paper • 2608.20958 • Published Aug 21 • 60

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published Aug 24 • 80

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published Aug 6 • 65

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

Paper • 2608.19799 • Published Aug 20 • 68

SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation

Paper • 2608.18565 • Published Aug 19 • 77

AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling

Paper • 2608.02602 • Published Aug 3 • 85