minghao

Liam-Liu's activity

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

upvoted 2 papers about 1 month ago

Reasoning with Sampling: Your Base Model is Smarter Than You Think

Paper • 2510.14901 • Published Oct 16 • 47

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems

Paper • 2510.11652 • Published Oct 13 • 28

authored 10 papers about 2 months ago

OAgents: An Empirical Study of Building Effective Agents

Paper • 2506.15741 • Published Jun 17 • 35

IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?

Paper • 2509.24709 • Published Sep 29 • 6

VideoScore2: Think before You Score in Generative Video Evaluation

Paper • 2509.22799 • Published Sep 26 • 25

Towards Personalized Deep Research: Benchmarks and Evaluations

Paper • 2509.25106 • Published Sep 29 • 29

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing

Paper • 2509.26346 • Published Sep 30 • 18

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

Paper • 2510.10689 • Published Oct 12 • 46

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems

Paper • 2510.11652 • Published Oct 13 • 28

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

Paper • 2510.14616 • Published Oct 16 • 11

COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes

Paper • 2510.14763 • Published Oct 16 • 13

A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning

Paper • 2510.12838 • Published Oct 13 • 24

upvoted 2 papers about 2 months ago

COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes

Paper • 2510.14763 • Published Oct 16 • 13

SimKO: Simple Pass@K Policy Optimization

Paper • 2510.14807 • Published Oct 16 • 10

upvoted 2 papers 2 months ago

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing

Paper • 2509.26346 • Published Sep 30 • 18

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published Sep 29 • 140

authored a paper 3 months ago

Reverse-Engineered Reasoning for Open-Ended Generation

Paper • 2509.06160 • Published Sep 7 • 149

upvoted 3 papers 3 months ago

Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

Paper • 2509.04292 • Published Sep 4 • 57

Reverse-Engineered Reasoning for Open-Ended Generation

Paper • 2509.06160 • Published Sep 7 • 149

O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing

Paper • 2509.01596 • Published Sep 1 • 3