Fitting Vision Adapters at Frontier Scales
cs.CV, cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/MoonshotAI/Kimi-K3
Sources
- Flamingo: a Visual Language Model for Few-Shot Learning
- NVLM: Open Frontier-Class Multimodal LLMs
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- The Platonic Representation Hypothesis
- Grounding Language Models to Images for Multimodal Inputs and Outputs
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
- Latent Implicit Visual Reasoning
- Latent Space Translation via Semantic Alignment
- Linearly Mapping from Image to Text Space
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- Relative representations enable zero-shot latent space communication
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- eP-ALM: Efficient Perceptual Augmentation of Language Models
- Multimodal Few-Shot Learning with Frozen Language Models
- Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
- Efficient Streaming Language Models with Attention Sinks
- MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
- MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
- MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models