taesiri PRO

taesiri's activity

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

upvoted 2 papers about 12 hours ago

Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes

Paper • 2506.00227 • Published 6 days ago • 9

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

Paper • 2506.03355 • Published 2 days ago • 6

upvoted 2 papers about 13 hours ago

Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation

Paper • 2506.04225 • Published 1 day ago • 19

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

Paper • 2506.04207 • Published 1 day ago • 41

upvoted a paper about 22 hours ago

SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation

Paper • 2506.03139 • Published 2 days ago • 13

upvoted 4 papers about 24 hours ago

LayerFlow: A Unified Model for Layer-aware Video Generation

Paper • 2506.04228 • Published 1 day ago • 13

RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions

Paper • 2506.03448 • Published 2 days ago • 4

Image Editing As Programs with Diffusion Models

Paper • 2506.04158 • Published 1 day ago • 16

MiMo-VL Technical Report

Paper • 2506.03569 • Published 2 days ago • 58

upvoted 2 papers 1 day ago

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Paper • 2505.24864 • Published 6 days ago • 112

Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning

Paper • 2505.24726 • Published 6 days ago • 162

upvoted an article 2 days ago

view article

Article

Holo1: New family of GUI automation VLMs powering GUI agent Surfer-H

By and 1 other •

3 days ago

• 59

upvoted a paper 2 days ago

FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation

Paper • 2506.01144 • Published 4 days ago • 14

upvoted 2 collections 2 days ago

SynthRL

Collection

Models & Datasets of SynthRL • 10 items • Updated 2 days ago • 4

ReasonFLux-Coder

Collection

Coding LLMs excel at both writing code and generating unit tests. • 9 items • Updated 11 days ago • 6

upvoted 5 papers 2 days ago

DINGO: Constrained Inference for Diffusion LLMs

Paper • 2505.23061 • Published 8 days ago • 26

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Paper • 2506.03143 • Published 2 days ago • 34

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

Paper • 2506.02096 • Published 3 days ago • 49

VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments

Paper • 2506.02387 • Published 3 days ago • 55

MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs

Paper • 2506.01674 • Published 4 days ago • 23