arxiv:2404.03214
Walid Bousselham
WalidBouss
AI & ML interests
Computer Vision, Multi-modal learning and Zero-shot adaptation.
Recent Activity
upvoted
a
paper
15 days ago
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
upvoted
a
paper
3 months ago
Self-Improvement in Multimodal Large Language Models: A Survey
Organizations
models
36
WalidBouss/LLaVA_instructions
Updated
WalidBouss/Qwen2.5-VL-3b-MOT-4000
4B
•
Updated
•
8
WalidBouss/logs_robust_bench
Updated
WalidBouss/qwen25vl-3b-open_thoughts_1M-moddedtokenizer-3000
4B
•
Updated
•
10
WalidBouss/Qwen2.5-vl-3b-Instruct-ModdedTokenizer
Image-Text-to-Text
•
4B
•
Updated
•
6
WalidBouss/logs_text_only
Updated
WalidBouss/qwen2_5_vl_3b_geo_grpo_r1_vision-text_only-1M-OT
4B
•
Updated
•
6
WalidBouss/qwen2_5_vl_3b_geo_grpo_r1_vision
4B
•
Updated
•
7
WalidBouss/qwen2_5_vl_3b_geo_grpo_step_60-scratch-RL
4B
•
Updated
•
10
WalidBouss/qwen2_5_vl_3b_geo_grpo_step_60
4B
•
Updated
•
6
datasets
7
WalidBouss/MMStar_subset-RL
Viewer
•
Updated
•
1.5k
•
110
WalidBouss/MMMU_Pro_subset-RL
Viewer
•
Updated
•
1.73k
•
20
WalidBouss/MathVision_subset-RL
Viewer
•
Updated
•
3.04k
•
15
WalidBouss/MathVision_subset
Viewer
•
Updated
•
68
•
18
WalidBouss/MMMU_Pro_subset
Viewer
•
Updated
•
200
•
14
WalidBouss/MMStar_subset
Viewer
•
Updated
•
100
•
12
WalidBouss/vqav2-toy-subset
Viewer
•
Updated
•
60
•
13