-
Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles
Paper • 2505.23590 • Published • 25 -
How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning
Paper • 2505.24273 • Published • 4 -
Accelerating Diffusion LLMs via Adaptive Parallel Decoding
Paper • 2506.00413 • Published • 7 -
DINGO: Constrained Inference for Diffusion LLMs
Paper • 2505.23061 • Published • 30
Spyros Gidaris
sgidaris
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 days ago
DIP: Unsupervised Dense In-Context Post-training of Visual
Representations
commented on
a paper
2 days ago
DIP: Unsupervised Dense In-Context Post-training of Visual
Representations
upvoted
a
paper
9 days ago
JAFAR: Jack up Any Feature at Any Resolution
Organizations
None yet
Collections
1
-
Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles
Paper • 2505.23590 • Published • 25 -
How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning
Paper • 2505.24273 • Published • 4 -
Accelerating Diffusion LLMs via Adaptive Parallel Decoding
Paper • 2506.00413 • Published • 7 -
DINGO: Constrained Inference for Diffusion LLMs
Paper • 2505.23061 • Published • 30
models
0
None public yet
datasets
0
None public yet