arXiv:2609.16656v1 Announce Type: new Abstract: State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to attention-based architectures and have been extended to vision...
arXiv:2607. 06600v1 Announce Type: cross Abstract: Line segment detection is a key building block in visual SLAM, 3D reconstruction, and industrial inspection.
arXiv:2512. 08240v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs.
arXiv:2509. 10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost.
VQ-Transplant is a framework that allows new vector‑quantization (VQ) modules to be inserted into frozen, pre‑trained visual tokenizers without retraining the entire model. By preserving all encoder‑decoder parameters and adding a lightweight decoder adaptation trained for only five epochs on ImageNet‑1k, the method mitigates decoder‑quantization mismatch. Experiments show that VQ-Transplant achieves near state‑of‑the‑art reconstruction fidelity for industry‑level models such as VAR while cutting training costs by 95%.
SCULPT is a training-time method that enhances the readiness of edge vision models for low-bit post‑training quantization (PTQ). It introduces a topology‑aware activation regularizer to reduce skewness and kurtosis, and a stable percentile‑based clipping mechanism that learns deployment‑ready activation bounds during ordinary FP32 fine‑tuning. The resulting clipping bounds can be directly exported into standard PTQ workflows for INT8 or lower‑bit settings such as W4A8.
PACE introduces a training‑free Condense‑and‑Extract framework that speeds up Vision‑Language Model inference by first adaptively downsampling visual inputs before encoding and then selectively retaining essential tokens during decoding. The Adaptive Pixel Compressor (APC) reduces encoder workload while preserving global context, and the Dynamic Dual‑Attention Extractor (DDAE) keeps task‑critical details by fusing visual and language signals. Applied to Qwen2.5‑VL‑7B, PACE maintains 93.8% of performance using only 10% of visual tokens, achieving a 3.1× speedup in time to first token.
Squeeze10-LLM is a staged mixed‑precision post‑training quantization framework that reduces 16‑bit LLM weights to an average of 1.6 bits per weight by assigning 80% of weights to 1 bit and 20% to 4 bits. It introduces Post‑Binarization Activation Robustness (PBAR), a weight significance metric that considers activation impact, and Full Information Activation Supervision (FIAS), a strategy that preserves activation information to limit error propagation. Experiments on LLaMA and LLaMA2 demonstrate that Squeeze10‑LLM achieves state‑of‑the‑art performance for sub‑2‑bit weight‑only quantization, raising average accuracy from 43% to 56% on six zero‑shot classification tasks.
arXiv:2608.21952v1 Announce Type: new Abstract: Recent advances in sequence modeling have highlighted Mamba as a state space architecture offering efficient long-range dependency modeling and providi...
arXiv:2603. 00198v2 Announce Type: replace-cross Abstract: Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning.
arXiv:2606. 01503v1 Announce Type: cross Abstract: Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective.
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.