Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping
Paper • 2603.23998 • Published
Shuohuan Wang
wangshuohuan
AI & ML interests
None yet
Recent Activity
authored a paper about 1 hour ago
Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping authored a paper about 1 hour ago
Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models authored a paper about 1 hour ago
Blink: Dynamic Visual Token Resolution for Enhanced Multimodal UnderstandingOrganizations
authored 8
papers about 1 hour ago
Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models
Paper • 2603.06043 • Published
Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding
Paper • 2512.10548 • Published
V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Intervention
Paper • 2512.03542 • Published
Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
Paper • 2509.21892 • Published
BeamLoRA: Beam-Constraint Low-Rank Adaptation
Paper • 2502.13604 • Published
Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards
Paper • 2210.12050 • Published
Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models
Paper • 2010.03542 • Published
authored 12
papers 1 day ago
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Paper • 2107.02137 • Published
ERNIE-Doc: A Retrospective Long-Document Modeling Transformer
Paper • 2012.15688 • Published • 1
ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora
Paper • 2012.15674 • Published • 1
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Paper • 2112.12731 • Published • 1
On Training Data Influence of GPT Models
Paper • 2404.07840 • Published
Dual Modalities of Text: Visual and Textual Generative Pre-training
Paper • 2404.10710 • Published • 2
HFT: Half Fine-Tuning for Large Language Models
Paper • 2404.18466 • Published • 1
ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages
Paper • 2212.06742 • Published • 4
Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
Paper • 2410.01610 • Published • 1
Curiosity-Driven Reinforcement Learning from Human Feedback
Paper • 2501.11463 • Published
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
Paper • 2502.13842 • Published
Mixture of Hidden-Dimensions Transformer
Paper • 2412.05644 • Published • 2