arXiv subjects

Huanrui Yang

Publications and source records attributed to Huanrui Yang.

At least 19 recordsLinked to original sources

arXiv2026

From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning

The rapid expansion of multimodal models has surfaced formidable bottlenecks in computation, memory, and deployment, catalyzing the rise of Efficient Multimodal Learning (EML) as a pivotal research frontier. Despite intensive progress, a cohesive understanding of what, how, and where efficiency is manifested across the learning stack remains fragmented. This survey systematizes the EML landscape by introducing the first structured, model-to-system taxonomy. We distill insights from over 300 seminal works into three hierarchical levels--model, algorithm, and system--addressing architectural parsimony, execution refinement, and hardware-aware orchestration, respectively. Moving beyond a purely categorical review, we offer a methodological synthesis of the vertical synergies between these layers, elucidating how cross-layer co-design contributes to the fundamental "Efficiency-Utility-Privacy" trade-off. Through an integrative case study of Multimodal Large Language Models (MLLMs), we trace the field's evolutionary trajectory from initial structural adjustments to modern full-stack resource orchestration. Furthermore, we provide a holistic discussion and application-specific optimization blueprints for diverse domains and posit a paradigm shift toward self-regulating intelligence, where efficiency is an intrinsic, emergent property of the model's fundamental design rather than a post-hoc constraint. Finally, we present open challenges and future directions that will define the trajectory of EML research. This survey establishes a structured framework for multimodal systems that are not only high-performing and generalizable but natively efficient and ready for ubiquitous deployment. A continuously updated version is available at https://github.com/pwang322/Efficient-Multimodal-Learning-Survey.

cs.MM↗

arXiv2026

CST: Collaborative Selective Transmission for Communication-Efficient Multimodal Edge Inference

Collaborative multimodal inference improves edge perception by combining observations from distributed sensing devices, but transmitting high-dimensional helper representations incurs substantial communication overhead and can lead to high end-to-end latency. Existing communication-efficient methods reduce payloads through compression, semantic coding, or feature selection, yet typically optimize compactness or task relevance without explicitly accounting for information already represented at the main device. Consequently, task-relevant but redundant helper features may still consume bandwidth. We present Collaborative Selective Transmission (CST), a main-directed query--response framework that retrieves only helper information complementary to the current main representation. Inspired by Partial Information Decomposition and the Multiview Redundancy Assumption, CST learns sample-adaptive, helper-specific sparse retrieval supports while discouraging retrieval of semantics already covered by the main device or duplicated across helpers. During inference, the main device transmits only support indices, and each helper returns the corresponding latent values, avoiding dense helper-feature exchange. Across three real-world multimodal sensing benchmarks, CST transmits no more than 14.18% of helper feature values while achieving best or near-best task performance among the evaluated methods. Experiments on a five-node NVIDIA Jetson Orin Nano testbed across 5--100 Mbps demonstrate up to a $4.27\times$ speedup over Transmit-All in end-to-end inference, confirming practical end-to-end latency reductions.

cs.LG↗

arXiv2026

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers

Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic complexity of cross-view global attention quickly becomes the dominant computational bottleneck. While recent efforts attempt to improve efficiency through compressed or sparse attention, they fail to fully exploit the inherent sparsity and dynamic behavior of global attention. In this work, we present a comprehensive analysis of global attention across multiple F3R transformers and reveal that attention patterns are highly heterogeneous, dynamic, and extremely sparse across layers and attention heads. Motivated by these findings, we propose SAF3R, a training-free dynamic sparse attention framework tailored to F3R transformers. SAF3R integrates tailored sparse attention mechanisms with offline head profiling and an efficient online adaptation strategy to match input-dependent attention behaviors. Extensive experiments demonstrate that SAF3R achieves high sparsity ratios while preserving camera pose estimation and 3D reconstruction quality, translating into substantial end-to-end speedup on F3R transformers compared to existing methods. Code is available at https://github.com/jndeng/SAF3R

cs.CV↗

arXiv2026

GeoCache: Training-Free Acceleration of Multi-View Texture Diffusion via Geometric Delta Transport

Geometry-conditioned multi-view diffusion enables high-quality 3D texture generation, but its repeated per-view denoiser evaluations introduce substantial computational cost. Existing training-free accelerators primarily exploit temporal redundancy by reusing computation across denoising steps. In multi-view texturing, however, skipping a step also removes the cross-view interaction that continually aligns different observations of the same surface, leading to rapidly degraded consistency and fidelity. Our analysis identifies a complementary source of redundancy: although intermediate features remain view-specific, geometrically corresponding surface points exhibit transferable evolution in their predicted clean signals. Based on this observation, we introduce \gc{}, a training-free plugin that evaluates a rotating subset of anchor views and transports their geometry-aligned per-step $\xz$ updates to the remaining views. Periodic full-view computation controls accumulated error, while sampler-consistent reconstruction preserves the denoising trajectory. \gc{} requires neither retraining nor architectural modification and uses the position maps already available in geometry-conditioned texturing pipelines. Across Hunyuan3D-2.1, SyncMVD, and MVPainter, \gc{} achieves a stronger speed--fidelity trade-off than temporal caches and step reduction at operating points above $2\times$. On Hunyuan3D-2.1, it delivers a $2.21\times$ denoiser-loop speedup with an MV-LPIPS of 0.0293 and an MV-PSNR of 33.60 dB, providing the best fidelity among all tested methods above $2\times$. The same transferred configuration reaches the highest speedup and lowest FLOPs on SyncMVD, while \gc{} achieves the lowest FLOPs and best fidelity among the accelerated methods on MVPainter. These results establish cross-view geometry as an effective acceleration axis for multi-view texture diffusion.

cs.CV↗

arXiv2026

TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models

Static quantization assigns one weight precision to every denoising step. To preserve quality, that precision must accommodate the most quantization-sensitive step, even though many other steps can tolerate fewer bits. The resulting model may satisfy its memory budget, but it repeatedly pays worst-case arithmetic throughout the denoising trajectory. We introduce Temporal-Adaptive Bit Sparsification Quantization (TASQ) to separate these two costs. TASQ stores one shared maximum-precision weight buffer and learns a Temporal-Spatial LSB Mask that selects a lower effective precision for each layer and denoising stage by truncating least-significant bits. Storage therefore remains fixed by the worst case, while BitOPs decrease at less sensitive stages without per-stage weight copies or runtime search. A Temporal-Precision Engine maps the learned schedule to bit-serial execution, where cycles scale with effective precision and switching precision has no measured cycle overhead. On PixArt-Sigma, SANA-1.6B, and SDXL-Turbo, TASQ achieves quality comparable to static quantization with less computation. Together with the Temporal-Precision Engine, it reduces execution cycles by 25 to 50 percent over static quantization and by 6.1 to 7.5x over a naive static 8-bit bit-serial execution. Code is available at https://github.com/seokho-han/tasq.

cs.CV↗

arXiv2026

LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection

Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.g., 2, 3-bit), resulting in a ``deployment gap" where Large Language Models cannot be optimally fitted to specific memory budgets. To bridge this gap, we introduce LiftQuant, a novel framework that enables continuous bit-width control for true Pareto-optimal deployment. The core innovation is a ``lift-then-project" mechanism which approximates low-dimensional weight vectors by projecting a simple 1-bit lattice from a higher-dimensional ``lifted" space. Crucially, the effective bit-width is determined simply by the ratio of the lifted dimension to the original dimension, which allows the bit-width to be tuned quasi-continuous as the dimension is a flexible structural parameter. This projection generates a structured yet non-uniform codebook, capturing the expressive power of Vector Quantization (VQ). While beneficial over VQ, LiftQuant's decoding path relies solely on linear transformations and 1-bit uniform quantizers, retaining hardware-friendly nature. This flexibility is transformative: LiftQuant enables a 70B LLM to be compressed to 2.4 bits to precisely fit a 24GB GPU, where its performance significantly surpasses state-of-the-art 2-bit models fitted on the same device. Our code and ckpt is available at https://github.com/Heliulu/LiftQuant.

cs.LG↗

arXiv2026

MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM

Dynamic runtime latency and memory constraints necessitate flexible large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based on available computational resources. Recent work on such any-precision quantization either relies on hardware-inefficient vector quantization or induces additional scaling factors when switching between bit-widths. Meanwhile, existing post-training quantization (PTQ) methods calibrated for a fixed low precision show poor generalizability under runtime precision change. In this work, we attribute the source of poor generalization across bit-widths to a precision-dependent \textit{outlier migration} phenomenon where the distribution of PTQ-sensitive tokens changes across precisions. Motivated by this observation, we propose \texttt{MoBiQuant}, a novel any-precision Mixture-of-Bits quantization framework that adjusts weight precision for flexible LLM inference based on token sensitivity. Specifically, we propose a many-in-one recursive residual quantization that can iteratively reconstruct higher-precision weights at runtime and mitigates \textit{outlier migration} with a token-aware router to dynamically select the optimal inference precision of each token.Extensive experiments show that \texttt{MoBiQuant} matches or surpasses frontier single-precision PTQ while exhibiting strong elasticity, achieving significant memory savings and throughput gains of up to $1.34\times$ over state-of-the-art any-precision methods.

cs.LG↗

arXiv2026

GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs

Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert-wise bit-widths based on their importance, approaching the accuracy-memory Pareto frontier and enabling extreme low-bit quantization. However, existing methods rely on layer-wise importance estimation and overlook router shifts induced by quantization, resulting in suboptimal allocation and routing. In this work, we propose Global Expert-level Mixed-precision Quantization (GEMQ) to overcome these limitations via (1) a global linear-programming formulation that captures model-wide expert importance based on quantization error analysis, and (2) efficient router fine-tuning to adapt routing to quantized experts. These components are integrated into a progressive quantization framework that iteratively refines importance estimation and allocation. Experiments demonstrate that GEMQ significantly reduces memory and accelerates inference with minimal accuracy degradation. Source code is available at https://github.com/jndeng/GEMQ .

cs.LG↗

arXiv2026

MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation

Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams while retaining past competence, yet texture-biased backbones risk error accumulation and catastrophic forgetting. Drawing inspiration from the process of decoupling shape and texture in the human visual system, we introduce MoASE, a plug-in mixture-of-experts that disentangles domain-agnostic structure from domain-specific texture using Activation Sparsity Experts with Spatial Differentiable Dropout, forming complementary high- and low-activation pathways, while high- and low-rank bottlenecks diversify representations. The Activation Sparsity Gate produces input-adaptive SDD thresholds for precise token selection, and the Domain-Aware Router assigns per-sample expert weights using texture-sensitive cues. To curb confirmation bias on unlabeled streams and stabilize supervision, we then introduce Domain-Adaptive On-Policy Distillation to constitute MoASE++, with an EMA-anchored on-policy reverse KL distillation and an augmentation policy conditioned on entropy and confidence that aligns predictions across the same views and improves the robustness-plasticity balance. Extensive experiments on classification (CIFAR-10/100-C, ImageNet-C) and semantic segmentation (Cityscapes->ACDC) demonstrate consistent state-of-the-art performance, offering a principled, controllable approach to continual adaptation in dynamic visual environments.

cs.CV↗

arXiv2026

From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation

Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with simpler sequential modules is appealing, yet naive substitution is often lossy, especially at larger scales. This paper revisits attention replacement through the lens of sparsity. Based on the observation of diverse sparsity patterns across transformer layers, we posit that pretrained transformers decompose the complex token dependency across tokens into various sequence-to-sequence mappings of diverse complexities, where some layer functionalities can be approximated and replaced with much simpler sequential modules without loss. We evaluate this premise using a plug-and-play layer-wise distillation framework to approximate and replace attention functionalities in pretrained vision transformer models. Controlled group-wise replacements under a fixed training budget reveal a clear pattern: substituting layers with sparser attention incurs substantially smaller accuracy drops than replacing denser ones. We further impose explicit attention sparsity on the pretrained ViT via AViT-style token retention and perform sparsity-guided distillation for sequential replacing models, where we see increasing teacher sparsity consistently reduces the student-teacher gap. The proposed method achieves efficient attention replacement for reduced parameter size and latency through the guidance of attention sparsity.

cs.LG↗

arXiv2026

FAR: Function-preserving Attention Replacement for IMC-friendly Inference

While transformers dominate modern vision and language models, their attention mechanism remains poorly suited for in-memory computing (IMC) devices due to intensive activation-to-activation multiplications and non-local memory access, leading to substantial latency and bandwidth overhead on ReRAM-based accelerators. To address this mismatch, we propose FAR, a Function-preserving Attention Replacement framework that substitutes all attention in pretrained DeiTs with sequential modules inherently compatible with IMC dataflows. Specifically, FAR replaces self-attention with a multi-head bidirectional LSTM architecture via block-wise distillation to retain functional equivalence while enabling linear-time computation and localized weight reuse. We further incorporate structured pruning on FAR models, enabling flexible adaptation to resource-constrained IMC arrays while maintaining functional fidelity. Evaluations on the DeiT family demonstrate that FAR maintains comparable accuracy to the original attention-based models on ImageNet and multiple downstream tasks with reduced parameters and latency. Further analysis shows that FAR preserves the semantic token relationships learned by attention while improving computational efficiency, highlighting its potential for energy-efficient transformer inference on IMC-based edge accelerators.

cs.CV↗

arXiv2026

Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction

Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test time. While practitioners commonly believe a higher task success rate necessitates the use of a larger and stronger LLM model, multi-step interaction with a large LLM incurs prohibitive inference cost. To address this problem, we explore the use of low-precision quantized LLMs in the long-horizon decision-making process. Based on the observation of diverse sensitivities among interaction steps, we propose Dynamic Mixed-Precision Routing (DMR), a framework that adaptively selects between high-precision and low-precision LLMs at each decision step. The router is trained via a two-stage pipeline, consisting of KL-divergence-based supervised learning that identifies precision-sensitive steps, followed by Group-Relative Policy Optimization (GRPO) to further improve task success rates. Experiments on ALFWorld and WebShop demonstrate that our approach achieves a strong accuracy-cost trade-off over single-precision baselines.

cs.AI↗

arXiv2026

PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers

Visual Geometry Transformer (VGGT) is a strong feed-forward model for multiple 3D tasks, but its Alternating-Attention (AA) stack scales quadratically in the total token count, making long clips expensive. Existing token-reduction accelerators operate inside AA, leaving the patch grid that enters AA uncompressed. We introduce PaceVGGT, a pre-AA token pruning framework that prunes DINO patch tokens before the first AA block of a frozen VGGT. PaceVGGT trains a lightweight Token Scorer that estimates per-token importance from DINO features. The scorer is first distilled against an AA-internal attention target from the unpruned backbone, then refined under downstream camera, depth, and point-map losses. A per-frame keep budget fixes the backbone-visible sequence length, while an importance-adaptive merge/prune assignment preserves residual content from high-saliency frames under a fixed total merge budget. A Feature-guided Restoration module reconstructs the dense spatial grid required by the prediction heads. On ScanNet-50 and 7-Scenes, PaceVGGT remains on the reconstruction quality--latency frontier while reducing inference latency. On ScanNet-50, it reduces latency by $5.1\times$ over unmodified VGGT at $N=300$ and $1.47\times$ over LiteVGGT at $N=1000$. These results identify pre-AA pruning as a viable acceleration route for frozen VGGT-style geometry transformers.

cs.CV↗

arXiv2026

MSSSeg: Learning Multi-Scale Structural Complexity for Self-Supervised Segmentation

Self-supervised semantic segmentation methods often suffer from structural errors, including merging distinct objects or fragmenting coherent regions, because they rely primarily on low-level appearance cues such as color and texture. These cues lack structural discriminability: they carry no information about the structural organization of a region, making it difficult to distinguish boundaries between similar-looking objects or maintain coherence within internally varying regions. Recent approaches attempt to address this by incorporating depth priors, yet remain limited by not explicitly modeling structural complexity that persists even when appearance cues are ambiguous. To bridge this gap, we present MSSSeg, a framework that explicitly learns multi-scale structural complexity from both semantic and depth domains, via three coupled components: (1) a Differentiable Box-Counting (DBC) module that captures and aligns multi-scale structural complexity features with semantic features; (2) a Learnable Structural Augmentation (StructAug) that corrupts pixel-intensity patterns, forcing the network to rely on structural complexity features from DBC; and (3) a Persistent Homology Loss (PHLoss) that directly supervises the structural complexity of predicted segmentations. Extensive experiments demonstrate that MSSSeg achieves new state-of-the-art performance on COCO-Stuff-27, Cityscapes, and Potsdam without excessive computational overhead, validating that explicit structural complexity learning is crucial for self-supervised segmentation.

cs.CV↗

arXiv2026

PhysDepth: Plug-and-Play Physical Refinement for Monocular Depth Estimation in Challenging Environments

State-of-the-art monocular depth estimation (MDE) models often struggle in challenging environments, primarily because they overlook robust physical information. To demonstrate this, we first conduct an empirical study by computing the covariance between a model's prediction error and atmospheric attenuation. We find that the error of existing SOTAs increases with atmospheric attenuation. Based on this finding, we propose PhysDepth, a plug-and-play framework that solves this fragility by infusing physical priors into modern SOTA backbones. PhysDepth incorporates two key components: a Physical Prior Module (PPM) that leverages Rayleigh Scattering theory to extract robust features from the high-SNR red channel, and a physics-derived Red Channel Attenuation Loss (RCA) that enforces model to learn the Beer-Lambert law. Extensive evaluations demonstrate that PhysDepth achieves SOTA accuracy in challenging conditions.

cs.CV↗

arXiv2025

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference

The Key-Value (KV) cache reading latency increases significantly with context lengths, hindering the efficiency of long-context LLM inference. To address this, previous works propose retaining a small fraction of KV cache based on token importance. For example, KV eviction uses static heuristics to retain tokens, while KV retrieval dynamically selects query-relevant tokens for more adaptive cache management. However, we observe that important tokens are often sparsely distributed across the long context. This sparsity makes existing page-level KV retrieval inaccurate, as each page may include irrelevant tokens and miss critical ones. In this work, we propose Fier, a \underline{Fi}ne-Grained and \underline{E}fficient KV cache \underline{R}etrieval method. Fier uses 1-bit quantized keys to estimate the importance of each token, resulting in efficient and precise retrieval. Experiments show that Fier matches full KV performance using only 11\% of the cache budget across various long-context tasks, reducing decoding latency by 1.2$\times$ to 1.5$\times$.Code is available at https://github.com/SimWangArizona/FIER

cs.DB↗

arXiv2025

SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models

Vision-Language-Action (VLA) models exhibit unprecedented capabilities for embodied intelligence. However, their extensive computational and memory costs hinder their practical deployment. Existing VLA compression and acceleration approaches conduct quantization or token pruning in an ad-hoc manner but fail to enable both for a holistic efficiency improvement due to an observed incompatibility. This work introduces SQAP-VLA, the first structured, training-free VLA inference acceleration framework that simultaneously enables state-of-the-art quantization and token pruning. We overcome the incompatibility by co-designing the quantization and token pruning pipeline, where we propose new quantization-aware token pruning criteria that work on an aggressively quantized model while improving the quantizer design to enhance pruning effectiveness. When applied to standard VLA models, SQAP-VLA yields significant gains in computational efficiency and inference speed while successfully preserving core model performance, achieving a $\times$1.93 speedup and up to a 4.5\% average success rate enhancement compared to the original model.

cs.CV↗

arXiv2025

BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models

Rotations have become essential to state-of-the-art quantization pipelines for large language models (LLMs) by effectively smoothing outliers in weights and activations. However, further optimizing the rotation parameters offers only limited performance gains and introduces significant training overhead: due to rotation parameter sharing, full-model must be loaded simultaneously to enable backpropagation, resulting in substantial memory consumption and limited practical utility. In this work, we identify two fundamental limitations of current rotational quantization methods: (i) rotation fails to align channel means, resulting in wider quantization bounds and increased rounding errors; and (ii) rotation makes the activation distribution more Gaussian-like, increasing energy loss caused by clipping errors. To address these issues, we introduce \textbf{BASE-Q}, a simple yet powerful approach that combines bias correction and asymmetric scaling to effectively reduce rounding and clipping errors. Furthermore, BASE-Q enables blockwise optimization, eliminating the need for memory-intensive full-model backpropagation. Extensive experiments on various LLMs and benchmarks demonstrate the effectiveness of BASE-Q, narrowing the accuracy gap to full-precision models by 50.5\%, 42.9\%, and 29.2\% compared to QuaRot, SpinQuant, and OSTQuant, respectively. The code will be released soon.

cs.LG↗