superb_xixianghe

user48271's activity

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

liked a model 4 days ago

xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic

Text Generation • 9B • Updated about 9 hours ago • 18.9k • 4.77k

updated a dataset 14 days ago

user48271/Stembind

Viewer • Updated 14 days ago • 6.89k • 1.78k • 1

liked a model 2 months ago

openbmb/MiniCPM5-2B

Text Generation • 3B • Updated 4 days ago • 1.04M • 1.85k

upvoted a paper 2 months ago

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published Sep 3 • 82

authored 7 papers 2 months ago

Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs

Paper • 2609.02548 • Published Sep 2 • 1

TACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data Selection

Paper • 2507.03673 • Published Jul 4, 2025

ENC-Bench: A Benchmark for Evaluating Multimodal Large Language Models in Electronic Navigational Chart Understanding

Paper • 2603.22763 • Published Mar 24

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation

Paper • 2605.21125 • Published May 30

Efficient Hallucination Detection: Adaptive Bayesian Estimation of Semantic Entropy with Guided Semantic Exploration

Paper • 2603.22812 • Published Mar 24

MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias

Paper • 2606.17953 • Published Jun 16

StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning

Paper • 2606.00148 • Published May 29

upvoted a paper 2 months ago

Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs

Paper • 2609.02548 • Published Sep 2 • 1

New activity in LiquidAI/LFM2.5-2.6B 3 months ago

self-recognization not right

2

#3 opened 3 months ago by

user48271

liked a model 5 months ago

yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF

Text Generation • 12B • Updated Jun 19 • 92k • 1.77k

New activity in WeiboAI/VibeThinker-3B 5 months ago

这模型几乎通过了我所有的本地推理测试，很强，唯一做不出来的问题我贴在下面

❤️ 1

6

#5 opened 5 months ago by

pypry

怎么自我认知还是deepseek？而且好像没有做快慢思考，无法自适应控制思考长度

3

#12 opened 5 months ago by

user48271

New activity in openbmb/MiniCPM5-1B-GGUF 5 months ago

After deploying it in LM Studio, the output is just endless repetition.

👍 5

5

#5 opened 5 months ago by

user48271

liked a dataset 5 months ago

openbmb/UltraData-SFT-2605

Viewer • Updated May 28 • 12.2M • 18.6k • 418

liked a Space 6 months ago

Running

20

ArXiv Daily Papers

📚

20

Browse the day’s top arXiv papers

liked a dataset 6 months ago

user48271/Stembind

Viewer • Updated 14 days ago • 6.89k • 1.78k • 1