FAST: Efficient Action Tokenization for Vision-Language-Action Models
Paper
•
2501.09747
•
Published
•
23
ML Optimization Papers
-
-
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 85 -
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
Paper • 2501.06842 • Published • 16 -
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Paper • 2501.03895 • Published • 52 -
LTX-Video: Realtime Video Latent Diffusion
Paper • 2501.00103 • Published • 44 -
Efficiently Serving LLM Reasoning Programs with Certaindex
Paper • 2412.20993 • Published • 36 -
Token-Budget-Aware LLM Reasoning
Paper • 2412.18547 • Published • 46 -
TRecViT: A Recurrent Video Transformer
Paper • 2412.14294 • Published • 13 -
iFormer: Integrating ConvNet and Transformer for Mobile Application
Paper • 2501.15369 • Published • 12 -
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
Paper • 2501.12370 • Published • 11 -
Return of the Encoder: Maximizing Parameter Efficiency for SLMs
Paper • 2501.16273 • Published • 5 -
Cost-Optimal Grouped-Query Attention for Long-Context LLMs
Paper • 2503.09579 • Published • 5 -
Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
Paper • 2503.00540 • Published • 1 -
MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding
Paper • 2502.03183 • Published • 1 -
OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models
Paper • 2503.08686 • Published • 19 -
QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension
Paper • 2503.08689 • Published • 4 -
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
Paper • 2503.07677 • Published • 80 -
LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
Paper • 2503.08619 • Published • 20