Jiaheng Liu

CheeryLJH's activity

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

upvoted a paper 4 days ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published 5 days ago • 169

upvoted a paper 5 days ago

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

Paper • 2601.09688 • Published 5 days ago • 113

liked a dataset 5 days ago

MVU-Eval-Team/MVU-Eval-Data

Viewer • Updated Nov 12, 2025 • 1.82k • 979 • 1

upvoted 3 papers 8 days ago

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

Paper • 2601.06002 • Published 10 days ago • 48

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Paper • 2601.06021 • Published 10 days ago • 39

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Paper • 2601.05432 • Published 11 days ago • 159

upvoted 3 papers 15 days ago

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

Paper • 2601.00393 • Published 18 days ago • 122

Deep Delta Learning

Paper • 2601.00417 • Published 18 days ago • 31

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

Paper • 2512.24615 • Published 20 days ago • 114

upvoted a paper 18 days ago

Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space

Paper • 2512.24617 • Published 20 days ago • 58

upvoted 2 papers 21 days ago

InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search

Paper • 2512.18745 • Published 29 days ago • 11

MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

Paper • 2512.22047 • Published 24 days ago • 26

liked a dataset 23 days ago

NJU-LINK/T2AV-Compass

Viewer • Updated 25 days ago • 500 • 116 • 3

upvoted a paper 26 days ago

T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation

Paper • 2512.21094 • Published 26 days ago • 24

submitted a paper to Daily Papers 26 days ago

T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation

Paper • 2512.21094 • Published 26 days ago • 24

upvoted a paper 26 days ago

LongVideoAgent: Multi-Agent Reasoning with Long Videos

Paper • 2512.20618 • Published 27 days ago • 53

upvoted 3 papers 27 days ago

Step-DeepResearch Technical Report

Paper • 2512.20491 • Published 27 days ago • 82

SemanticGen: Video Generation in Semantic Space

Paper • 2512.20619 • Published 27 days ago • 91

UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models

Paper • 2512.17385 • Published Dec 19, 2025 • 18

upvoted a paper 28 days ago

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

Paper • 2512.19682 • Published 28 days ago • 15