VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.
Lan- guage models are few-shot learners.Advances in neural in- formation processing systems, 33:1877–1901
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
PhysiGen reduces interpenetration in text-driven 3D human interaction generation by simplifying meshes to geometric primitives for fast collision detection and guiding optimization with collision regions.
Re²MoGen generates open-vocabulary motions via MCTS-enhanced LLM keyframe planning, pose-prior optimization with dynamic temporal matching fine-tuning, and physics-aware RL post-training, claiming SOTA performance.
Neuro-Oracle distills longitudinal MRI changes into trajectory vectors via a 3D Siamese encoder, retrieves similar cases, and generates LLM-based prognoses, achieving AUC 0.834-0.905 on a resection-type proxy task versus 0.793 for single-timepoint baseline.
LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.
Linear attention delivers significant computational savings in multimodal transformers and follows the same scaling laws as softmax attention on ViT models trained on LAION-400M with ImageNet-21K zero-shot validation.
citing papers explorer
-
VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.
-
PhysiGen: Integrating Collision-Aware Physical Constraints for High-Fidelity Human-Human Interaction Generation
PhysiGen reduces interpenetration in text-driven 3D human interaction generation by simplifying meshes to geometric primitives for fast collision detection and guiding optimization with collision regions.
-
Re$^2$MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement
Re²MoGen generates open-vocabulary motions via MCTS-enhanced LLM keyframe planning, pose-prior optimization with dynamic temporal matching fine-tuning, and physics-aware RL post-training, claiming SOTA performance.
-
Neuro-Oracle: A Trajectory-Aware Agentic RAG Framework for Interpretable Epilepsy Surgical Prognosis
Neuro-Oracle distills longitudinal MRI changes into trajectory vectors via a 3D Siamese encoder, retrieves similar cases, and generates LLM-based prognoses, achieving AUC 0.834-0.905 on a resection-type proxy task versus 0.793 for single-timepoint baseline.
-
LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.
-
On The Application of Linear Attention in Multimodal Transformers
Linear attention delivers significant computational savings in multimodal transformers and follows the same scaling laws as softmax attention on ViT models trained on LAION-400M with ImageNet-21K zero-shot validation.
- Next-Scale Autoregressive Models for Text-to-Motion Generation