arxiv:2607.25294
🤝 Open to Collab
Lai Wei
WaltonFuture
AI & ML interests
(Multimodal) LLM, Machine Learning
Recent Activity
authored a paper 2 days ago
CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition authored a paper 2 days ago
EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement
Learning FrameworkOrganizations
models 7
WaltonFuture/Diabetica-Qwen3-4B
4B • Updated • 3 • 2
WaltonFuture/Qwen2.5VL-3b-RLCS
Image-Text-to-Text • 4B • Updated • 5
WaltonFuture/Qwen2.5-VL-7B-MM-UPT-MMR1
Image-Text-to-Text • 8B • Updated • 17 • 3
WaltonFuture/Qwen2.5VL-7b-RLCS
Image-Text-to-Text • 8B • Updated • 65
WaltonFuture/Diabetica-o1
8B • Updated • 11
WaltonFuture/Diabetica-7B
Text Generation • 8B • Updated • 104 • • 10
WaltonFuture/Diabetica-1.5B
2B • Updated • 17 • 1
datasets 39
WaltonFuture/agentic-sft-new
Viewer • Updated • 781k • 1.58k • 6
WaltonFuture/areal-cc
Updated • 12
WaltonFuture/metamathqa-qwen3_4b-sampled
Viewer • Updated • 243k • 32
WaltonFuture/geoqa-combine-syn
Viewer • Updated • 24.1k • 21
WaltonFuture/MMR1-combine-syn
Viewer • Updated • 17.3k • 18
WaltonFuture/DAPO-17K
Viewer • Updated • 17.4k • 33
WaltonFuture/MM-Reasoning-Combine
Viewer • Updated • 15.9k • 22 • 1
WaltonFuture/Multimodal-RL-Data
Viewer • Updated • 31.8k • 119 • 8
WaltonFuture/Multimodal-Cold-Start
Viewer • Updated • 51.5k • 101 • 11
WaltonFuture/VQA-MultiTask
Viewer • Updated • 258k • 150 • 1