Amirhossein Kazemnejad

kazemnejad's activity

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

upvoted a paper 3 months ago

Value Drifts: Tracing Value Alignment During LLM Post-Training

Paper • 2510.26707 • Published Oct 30, 2025 • 13

authored 2 papers 4 months ago

The Promise of RL for Autoregressive Image Editing

Paper • 2508.01119 • Published Aug 1, 2025 • 11

The Markovian Thinker

Paper • 2510.06557 • Published Oct 8, 2025 • 31

commented a paper 4 months ago

The Markovian Thinker

Paper • 2510.06557 • Published Oct 8, 2025 • 31 •

2

upvoted a paper 4 months ago

The Markovian Thinker

Paper • 2510.06557 • Published Oct 8, 2025 • 31

upvoted a collection 4 months ago

The Markovian Thinker

Collection

Reformulating the RL of reasoning LLMs through Markovian Thinking paradigm. • 7 items • Updated Oct 9, 2025 • 11

updated a collection 4 months ago

The Markovian Thinker

Collection

Reformulating the RL of reasoning LLMs through Markovian Thinking paradigm. • 7 items • Updated Oct 9, 2025 • 11

updated 4 models 4 months ago

McGill-NLP/longcot-8k-1.5b

2B • Updated Oct 9, 2025 • 2 • 1

McGill-NLP/delethink-24k-1.5b

2B • Updated Oct 9, 2025 • 111 • 5

McGill-NLP/delethink-96k-1.5b

2B • Updated Oct 9, 2025 • 2 • 3

McGill-NLP/longcot-24k-1.5b

2B • Updated Oct 9, 2025 • 10 • 2

published 2 models 4 months ago

McGill-NLP/delethink-96k-1.5b

2B • Updated Oct 9, 2025 • 2 • 3

McGill-NLP/delethink-24k-1.5b

2B • Updated Oct 9, 2025 • 111 • 5

updated a collection 4 months ago

The Markovian Thinker

Collection

Reformulating the RL of reasoning LLMs through Markovian Thinking paradigm. • 7 items • Updated Oct 9, 2025 • 11

updated a dataset 4 months ago

McGill-NLP/openmath-filtered

Viewer • Updated Oct 3, 2025 • 200k • 56 • 1

published a dataset 4 months ago

McGill-NLP/openmath-filtered

Viewer • Updated Oct 3, 2025 • 200k • 56 • 1

updated a collection 4 months ago

The Markovian Thinker

Collection

Reformulating the RL of reasoning LLMs through Markovian Thinking paradigm. • 7 items • Updated Oct 9, 2025 • 11

updated a model 4 months ago

McGill-NLP/delethink-96k-base-1.5b

2B • Updated Oct 3, 2025 • 3 • 1