Tencent

Verified

AI & ML interests

None defined yet.

Recent Activity

Mosaic90 new activity about 23 hours ago

tencent/DiffSpot:DiffSpot: can your VLM spot a single CSS-level change between two screenshots?

YCZhou submitted a paper 1 day ago

World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning

paulinsider updated a dataset 2 days ago

tencent/VulnGym

View all activity

Papers

World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

View all Papers

in tencent/DiffSpot about 23 hours ago

DiffSpot: can your VLM spot a single CSS-level change between two screenshots?

#2 opened about 23 hours ago by

submitted a paper to Daily Papers 1 day ago

World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning

Paper • 2606.03603 • Published 2 days ago • 26

updated a dataset 2 days ago

tencent/VulnGym

Viewer • Updated 2 days ago • 592 • 486 • 5

published a model 3 days ago

tencent/Universal_Audio_Tokenizer

Updated 3 days ago • 5

updated a model 3 days ago

tencent/Universal_Audio_Tokenizer

Updated 3 days ago • 5

hhoh

updated a model 3 days ago

tencent/HY-MT1.5-7B

Translation • 8B • Updated 3 days ago • 2.91k • 161

published a dataset 6 days ago

tencent/PlanningBench

Viewer • Updated 7 days ago • 467 • 345 • 7

published a dataset 6 days ago

tencent/DiffSpot

Viewer • Updated 6 days ago • 4.4k • 436 • 4

updated a dataset 6 days ago

tencent/DiffSpot

Viewer • Updated 6 days ago • 4.4k • 436 • 4

updated a dataset 7 days ago

tencent/PlanningBench

Viewer • Updated 7 days ago • 467 • 345 • 7

submitted a paper to Daily Papers 7 days ago

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

Paper • 2605.28398 • Published 8 days ago • 15

in tencent/Hy-MT2-1.8B-2Bit-GGUF 8 days ago

tencent / Hy-MT2-1.8B-2Bit-GGUF

#5 opened 10 days ago by

updated a model 8 days ago

tencent/Hy-MT1.5-1.8B-1.25bit

Translation • 2B • Updated 8 days ago • 348 • 31

submitted a paper to Daily Papers 8 days ago

Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement

Paper • 2605.26952 • Published 9 days ago • 16

hhoh

in tencent/Hy-MT2-1.8B 8 days ago

You open-sourced my ass - 你“开源”我的屁吧！

#1 opened 9 days ago by

hhoh

in tencent/Hy-MT2-7B-GGUF 8 days ago

Formatting degradation and token corruption when handling structured tags (SRT translation use-case)

#3 opened 13 days ago by

hhoh

in tencent/Hy-MT2-30B-A3B 8 days ago

请问论文中参评的外部模型使用的prompt是怎么样的？

#5 opened 10 days ago by

Purpose of this model?

#4 opened 11 days ago by

Open Source My Ass! -- The "Open Source" Label is a Marketing Trap, Not a Promise of Freedom

#3 opened 13 days ago by

submitted a paper to Daily Papers 8 days ago

EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

Paper • 2605.23271 • Published 13 days ago • 79