arXiv AI
Aug 12
Hybrid Token Compression for Vision-Language Models
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.
A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization
The paper introduces a unified rate–distortion framework for discrete visual tokenization, encompassing vector, product, and scalar quantization. It shows that minimizing distortion, rather than maximizing codebook utilization, is the key objective for reconstruction fidelity and establishes fairness conditions for comparing quantizers. Under these conditions, the study confirms the distortion hierarchy VQ–PQ–SQ and demonstrates that modern VQ methods achieve the lowest distortion.
Related stories
arXiv Computer Vision
Aug 25
VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers
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%.
arXiv AI
Jun 2
Channel-wise Vector Quantization
arXiv:2605. 26089v2 Announce Type: replace-cross Abstract: We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens.
arXiv Computer Vision
Sep 4
Tree-Structured Vector Quantization For Efficient And Progressive Image Compression
Tree-VQ introduces a progressive tree‑structured vector quantization framework for learned image compression, organizing discrete codewords in a hierarchical binary tree where each latent token is represented by a routed root‑to‑leaf path. Every prefix of this path yields a valid quantized representation, enabling coarse reconstructions from shallow nodes and successive refinements from deeper nodes. The method incorporates a prefix‑compatible tree entropy model, rate‑aware refinement scheduling, and hierarchical prefix supervision to achieve efficient, low‑latency compression with superior perceptual quality and fewer parameters compared to existing approaches.
arXiv AI
Aug 6
Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms
arXiv:2608. 04074v1 Announce Type: cross Abstract: Long-context LLM decoding reads the key-value (KV) cache at every step.
arXiv Computer Vision
Aug 31
Visual Token Coding for Video Multimodal Large Language Models
The paper introduces Visual Token Coding (VTC), a token compression method for video multimodal large language models that mimics classical video coding by predicting I/P frames and measuring residuals to reduce token redundancy. VTC is extended with dynamic features—Dynamic Resolution Input, Dynamic Token Allocation, and Spatial Coverage Top‑K—forming VTC_Dy, which can be applied to existing MLLMs without additional tuning. Experiments on three MLLMs and multiple video benchmarks show that VTC_Dy retains over 100% of average performance with a 50% token budget and 97.8% with a 25% budget, while the code is publicly available.
Hugging Face Trending Papers
Jun 1
Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression
Most existing extreme compression methods fail to achieve an optimal rate-distortion-perception trade-off, as they typically prioritize perceptual fidelity and visual realism over pixel-level accuracy. Consequently, the resulting reconstructions often deviate noticeably from the originals.
arXiv Machine Learning
Jun 30
A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff
arXiv:2604. 14603v2 Announce Type: replace-cross Abstract: The fundamental limit of natural signal compression has traditionally been characterized by classical rate-distortion (RD) theory through the tradeoff between coding rate and reconstruction distortion, while the rate-distortion-perception (RDP) framework introduces a divergence-based measure of perceptual quality as a modeling principle, leaving its theoretical origin unclear.
Hugging Face Trending Papers
Jul 23
Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence
Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing, caching, and quantizing multimodal representations under latency, memory, and energy constraints. This paper reviews recent advances in efficient vision-language and multimodal large language models, covering visual token compression, video token management, KV-cache optimization, Mixture-of-Experts (MoE) routing, low-bit quantization, edge deployment, and hardware-aware benchmarking.
arXiv Machine Learning
Sep 1
RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search
arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,...
Hugging Face Trending Papers
Sep 2
Multi-scale Image Representation Compression
The paper introduces MIRC, an overfitted image codec that quantizes all components—including latents, synthesis network, and entropy models—within a single rate‑distortion objective, following the neural video representation codec NVRC. It adds a multi‑scale representation with cross‑stage parameter sharing to capture cross‑scale redundancy, achieving a 10.5% BD‑rate saving over VVC on the CLIC2020 professional validation set. MIRC also offers configurable decoding complexity ranging from 1.2 to 2.9 kMAC per pixel, allowing deployment to match specific resource budgets.
arXiv AI
Jun 17
MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs
arXiv:2606. 17118v1 Announce Type: cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE-MLLMs) offer remarkable performance but incur prohibitive GPU memory costs, making compression essential.