Hongbo Peng

M1chaelPeng's activity

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

upvoted a paper 7 days ago

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published 9 days ago • 70

upvoted 2 papers 25 days ago

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models

Paper • 2510.08531 • Published Oct 9, 2025 • 14

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models

Paper • 2505.21500 • Published May 27, 2025 • 15

upvoted a paper 29 days ago

MentalThink: Shaping Thoughts in Mental SVG World

Paper • 2607.03530 • Published Jul 3 • 14

upvoted 2 papers about 1 month ago

Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning

Paper • 2607.01191 • Published Jul 1 • 19

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Paper • 2606.28322 • Published Jun 26 • 43

upvoted a paper 4 months ago

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

Paper • 2604.14144 • Published Apr 15 • 63

upvoted a paper 5 months ago

WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics

Paper • 2603.13391 • Published Mar 11 • 20

upvoted a collection 5 months ago

olmOCR

Collection

olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 12 items • Updated Dec 23, 2025 • 156

upvoted 2 papers 5 months ago

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

Paper • 2603.08652 • Published Mar 9 • 40

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Paper • 2603.03447 • Published Mar 3 • 37

upvoted a paper 6 months ago

GEBench: Benchmarking Image Generation Models as GUI Environments

Paper • 2602.09007 • Published Feb 9 • 39

upvoted a collection 6 months ago

PRIME

Collection

PRIME data & models • 4 items • Updated Feb 7 • 3

upvoted a paper 6 months ago

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

Paper • 2602.01851 • Published Feb 2 • 16

upvoted 2 papers 7 months ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published Jan 14 • 196

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

Paper • 2601.05593 • Published Jan 9 • 87

upvoted a paper 8 months ago

Step-GUI Technical Report

Paper • 2512.15431 • Published Dec 17, 2025 • 134

upvoted a paper 10 months ago

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards

Paper • 2509.24981 • Published Sep 29, 2025 • 29

upvoted a paper 11 months ago

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

Paper • 2508.20478 • Published Aug 28, 2025 • 18

upvoted a paper 12 months ago

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

Paper • 2508.10711 • Published Aug 14, 2025 • 146