ProQuant: Progressive Quantization-aware Training for Edge MLLMs
cs.CV, cs.CL
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/yufeixue-ai/ProQuant
Terminology
Sources
- Qwen3-VL Technical Report
- LLaVA-OneVision: Easy Visual Task Transfer
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
- PACE: Progressive Angular-to-Norm Contrastive Embedding
- DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
- MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
- LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
- QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
- SpinQuant: LLM quantization with learned rotations
- TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
- Temporal Feature Matters: A Framework for Diffusion Model Quantization
- LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit
- Scaling Law for Quantization-Aware Training
- LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
- BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation
- QVGen: Pushing the Limit of Quantized Video Generative Models
- SPEED-Q: Staged Processing with Enhanced Distillation towards Efficient Low-bit On-device VLM Quantization
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs