An AI4AI Framework for Visual Token Pruning
cs.LG, cs.CV
Submitted: 2026-08-07
Updated: 2026-09-06
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen Technical Report
- Qwen2.5-VL Technical Report
- SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
- Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination
- When and Why Momentum Accelerates SGD:An Empirical Study
- Recognition Of Surface Defects On Steel Sheet Using Transfer Learning
- ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval
- The Essence of Balance for Self-Improving Agents in Vision-and-Language Navigation
- Instruction-as-State: Environment-Guided and State-Conditioned Semantic Understanding for Embodied Navigation
- GraphIR: Architecture-Level Search States for LLM-Guided Neural Architecture Evolution
- LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- LLaMA: Open and Efficient Foundation Language Models
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks