Huang's INTelligence lab

HINT-lab's activity

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

ChengsongHuang 

authored a paper 11 days ago

Self-Rewarding Vision-Language Model via Reasoning Decomposition

Paper • 2508.19652 • Published 12 days ago • 80

ChengsongHuang 

published 3 datasets 14 days ago

HINT-lab/one_model_iter2_solver_tuned

Viewer • Updated 20 days ago • 4.59k • 8

HINT-lab/one_model_iter3_solver_tuned

Viewer • Updated 20 days ago • 4.64k • 10

HINT-lab/one_model_iter1_solver_tuned

Viewer • Updated 20 days ago • 4.15k • 8

ChengsongHuang 

updated 3 datasets 20 days ago

HINT-lab/one_model_iter3_solver_tuned

Viewer • Updated 20 days ago • 4.64k • 10

HINT-lab/one_model_iter2_solver_tuned

Viewer • Updated 20 days ago • 4.59k • 8

HINT-lab/one_model_iter1_solver_tuned

Viewer • Updated 20 days ago • 4.15k • 8

ChengsongHuang 

updated a dataset 28 days ago

HINT-lab/qwen0_6_solver_v1

Viewer • Updated 28 days ago • 2.42k • 21

ChengsongHuang 

published a dataset 28 days ago

HINT-lab/qwen3_1_7_solver_v1

Viewer • Updated about 1 month ago • 9.69k • 20

ChengsongHuang 

updated a dataset about 1 month ago

HINT-lab/qwen3_1_7_solver_v1

Viewer • Updated about 1 month ago • 9.69k • 20

ChengsongHuang 

authored a paper about 1 month ago

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Paper • 2508.05004 • Published Aug 7 • 124

ChengsongHuang 

published a dataset about 1 month ago

HINT-lab/qwen0_6_solver_v1

Viewer • Updated 28 days ago • 2.42k • 21

ChengsongHuang 

authored a paper 3 months ago

POSS: Position Specialist Generates Better Draft for Speculative Decoding

Paper • 2506.03566 • Published Jun 4 • 6

shrango 

authored a paper 3 months ago

POSS: Position Specialist Generates Better Draft for Speculative Decoding

Paper • 2506.03566 • Published Jun 4 • 6

ChengsongHuang 

authored a paper 5 months ago

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

Paper • 2504.00043 • Published Mar 30 • 10

JixuanLeng 

authored a paper 5 months ago

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

Paper • 2504.00043 • Published Mar 30 • 10

ChengsongHuang 

authored 4 papers 6 months ago

On Grounded Planning for Embodied Tasks with Language Models

Paper • 2209.00465 • Published Aug 29, 2022 • 1

Optimizing Language Model's Reasoning Abilities with Weak Supervision

Paper • 2405.04086 • Published May 7, 2024 • 2

Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning

Paper • 2410.10074 • Published Oct 14, 2024 • 1

Efficient Test-Time Scaling via Self-Calibration

Paper • 2503.00031 • Published Feb 25 • 15