-
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 • 8 -
DINGO: Constrained Inference for Diffusion LLMs
Paper • 2505.23061 • Published • 31
Spyros Gidaris
sgidaris
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
Latent Denoising Makes Good Visual Tokenizers
updated
a collection
about 2 months ago
TO READ
authored
a paper
about 2 months ago
Franca: Nested Matryoshka Clustering for Scalable Visual Representation
Learning
Organizations
None yet
-
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 • 8 -
DINGO: Constrained Inference for Diffusion LLMs
Paper • 2505.23061 • Published • 31
models
0
None public yet
datasets
0
None public yet