In a Training Loop 🔄

2 19 16

weiliu

thinkwee

https://thinkwee.top/about/

AI & ML interests

LLM reasoning, agents

Recent Activity

liked a Space about 12 hours ago

thinkwee/BibGuard

updated a Space 3 days ago

thinkwee/BibGuard

published a Space 5 days ago

thinkwee/BibGuard

View all activity

Organizations

None yet

liked a Space about 12 hours ago

BibGuard

🛡

Check and improve your academic bibliography and LaTeX documents

updated a Space 3 days ago

BibGuard

🛡

Check and improve your academic bibliography and LaTeX documents

published a Space 5 days ago

BibGuard

🛡

Check and improve your academic bibliography and LaTeX documents

upvoted a paper 7 days ago

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Paper • 2601.11061 • Published 11 days ago • 7

upvoted a paper 15 days ago

An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift

Paper • 2601.05882 • Published 18 days ago • 20

upvoted a paper 26 days ago

Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

Paper • 2512.24618 • Published 27 days ago • 141

upvoted a paper 2 months ago

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

Paper • 2511.20102 • Published Nov 25, 2025 • 27

upvoted 2 papers 3 months ago

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

Paper • 2510.11052 • Published Oct 13, 2025 • 52

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

Paper • 2509.23379 • Published Sep 27, 2025 • 15

upvoted 2 papers 4 months ago

Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance

Paper • 2510.03528 • Published Oct 3, 2025 • 19

When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment

Paper • 2509.00544 • Published Aug 30, 2025 • 11

upvoted 3 papers 5 months ago

IntrEx: A Dataset for Modeling Engagement in Educational Conversations

Paper • 2509.06652 • Published Sep 8, 2025 • 26

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

Paper • 2508.19827 • Published Aug 27, 2025 • 33

Agentic Reinforced Policy Optimization

Paper • 2507.19849 • Published Jul 26, 2025 • 158

updated 2 collections 5 months ago

NOVER1

Collection

NOVER-series models for general reasoning • 3 items • Updated Aug 21, 2025 • 2

NOVEReason

Collection

General Reasoning datasets for training the NOVER model • 4 items • Updated Aug 21, 2025 • 2

liked a Space 5 months ago

NOVER

🧠

Reasoning on ANYTHING

updated a Space 5 months ago

NOVER

🧠

Reasoning on ANYTHING

published a Space 5 months ago

NOVER

🧠

Reasoning on ANYTHING

liked a model 5 months ago

thinkwee/NOVER1-Qwen2.5-7B

Question Answering • 8B • Updated Aug 20, 2025 • 4 • 2

weiliu

AI & ML interests

Recent Activity

Organizations

thinkwee's activity

BibGuard

BibGuard

BibGuard

NOVER

NOVER

NOVER