-
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
Paper • 2601.21821 • Published • 60 -
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Paper • 2601.22975 • Published • 109 -
Reinforced Attention Learning
Paper • 2602.04884 • Published • 28 -
LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts
Paper • 2510.19363 • Published • 62
Chunjiang Ge
ChunjiangGe
AI & ML interests
None yet
Recent Activity
commented on
a paper
about 2 hours ago
SLA2: Sparse-Linear Attention with Learnable Routing and QAT updated
a collection
10 days ago
RL updated
a collection
10 days ago
MLLM Organizations
-
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 25 -
Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
Paper • 2601.17367 • Published • 34 -
Small-scale proxies for large-scale Transformer training instabilities
Paper • 2309.14322 • Published • 22 -
Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
Paper • 2602.00747 • Published • 9
-
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
Paper • 2601.21821 • Published • 60 -
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Paper • 2601.22975 • Published • 109 -
Reinforced Attention Learning
Paper • 2602.04884 • Published • 28 -
LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts
Paper • 2510.19363 • Published • 62
-
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 25 -
Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
Paper • 2601.17367 • Published • 34 -
Small-scale proxies for large-scale Transformer training instabilities
Paper • 2309.14322 • Published • 22 -
Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
Paper • 2602.00747 • Published • 9
models 0
None public yet
datasets 0
None public yet