arxiv:2504.16828
Muhammad Khalifa
mkhalifa
AI & ML interests
natural language genration, reinforcement learning
Recent Activity
submitted
a paper
2 days ago
Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
new activity
30 days ago
mkhalifa/flan-t5-large-gsm8k:Add model card for GRACE
new activity
30 days ago
mkhalifa/flan-t5-large-svamp:Add model card for GRACE
Organizations
models
21
mkhalifa/flan-t5-large-gsm8k
Text Generation
•
Updated
•
16
mkhalifa/flan-t5-large-svamp
Text Generation
•
Updated
•
21
mkhalifa/flan-t5-large-mathqa
Text Generation
•
Updated
•
4
mkhalifa/ThinkPRM-gptoss-20B
Updated
•
15
mkhalifa/r1_14b_discriminative_prm
Text Generation
•
15B
•
Updated
mkhalifa/r1_14b_longthought-1K
Text Generation
•
15B
•
Updated
•
1
mkhalifa/r1-1.5b-longthought-outcome-matching
Text Generation
•
2B
•
Updated
•
1
mkhalifa/r1-1.5b-longthought-1K
Text Generation
•
2B
•
Updated
•
1
mkhalifa/r1_14b_longthought-1K-outcome-only
Text Generation
•
15B
•
Updated
•
2
mkhalifa/r1-1.5b-longthought-v2
Text Generation
•
2B
•
Updated
•
14
datasets
18
mkhalifa/agent
Updated
mkhalifa/gpqa-diamond-physics
Viewer
•
Updated
•
86
•
1.74k
mkhalifa/short-to-long-5K
Viewer
•
Updated
•
5k
•
5
mkhalifa/CoGEX
Viewer
•
Updated
•
51.8k
•
23
mkhalifa/llama-3.1-8b-instruct-math-trajectories-64-sample-per-problem
Viewer
•
Updated
•
736k
•
7
mkhalifa/llama-3.1-8b-instruct-math-trajectories-48-sample-per-problem
Viewer
•
Updated
•
552k
•
5
mkhalifa/llama-3.1-8b-instruct-math-trajectories-32-sample-per-problem
Viewer
•
Updated
•
368k
•
11
mkhalifa/llama-3.1-8b-instruct-math-trajectories-16-sample-per-problem
Viewer
•
Updated
•
184k
•
6
mkhalifa/llama-3.1-8b-instruct-math-trajectories-8-sample-per-problem
Viewer
•
Updated
•
92k
•
11
mkhalifa/llama-3.1-70b-instruct-math-trajectories-8-sample-per-problem
Viewer
•
Updated
•
92k
•
12