UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 293
Jiang
Dongwei
AI & ML interests
None yet
Recent Activity
upvoted a paper 12 months ago
The Alignment Waltz: Jointly Training Agents to Collaborate for Safety upvoted a paper about 1 year ago
IA2: Alignment with ICL Activations Improves Supervised Fine-TuningOrganizations
upvoted a paper 6 days ago
upvoted a paper 12 months ago
upvoted a paper about 1 year ago
upvoted 2
articles about 1 year ago
Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf
• • 799 Article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
NormalUhr
• • 135 upvoted a paper about 1 year ago
authored a
paper about 1 year ago
liked a
dataset about 1 year ago
Add link to Github repository
1
#2 opened over 1 year ago
by 
nielsr
upvoted a paper over 1 year ago
commented a
paper over 1 year ago
updated a
dataset over 1 year ago
published a
dataset over 1 year ago
upvoted a paper over 1 year ago
liked a
model over 1 year ago
updated a
model over 1 year ago
published a
model over 1 year ago
Wandb log not found
1
#1 opened over 1 year ago
by 
Yuu1998
updated 2
models over 1 year ago