Searcharxiv⌕ Search

arXiv subjects

Huanrui Yang

Publications and source records attributed to Huanrui Yang.

At least 19 recordsLinked to original sources
arXiv2026

Scaling Up Analog CIM: A Simulation Framework for Topology-Aware Mapping

Analog compute-in-memory (CIM) enables energy-efficient AI inference by performing in-situ matrix multiplication. The growing demand for deploying larger models motivates chiplet integration to expand CIM capacity. However, simulation abstractions based on local operator costs and aggregate communication metrics obscure the impact of weight-mapping topology when CIM system scales up. We develop a phase analysis that quantifies how strongly mapping topology affects system performance across hardware configurations and how mapping optimization translates into latency gains. To evaluate and exploit this design space, we present Isobar, a simulation platform integrating CIM decompositions, heterogeneous execution, and resource modeling. Validated against silicon measurements and cycle-accurate simulation, Isobar provides reliable cost estimates that enable effective mapping search across model and hardware configurations. For Gemma-7B prefill, Isobar-guided mapping reduces communication time by 23.3% and end-to-end latency by 18.6% relative to the strongest baseline. Isobar's system-level modeling show that analog CIM retains energy-efficiency potential relative to GPU when scaled to thousands of dies, and identify topology-aware mapping as a key design dimension for efficient execution.

cs.AR↗
arXiv2026

Anchor: Augmented Cross-Layer Recurrent State for Long-Context Retrieval in Test-Time Training

Parameter-efficient linearization turns a pretrained autoregressive Transformer into an efficient model by hybridizing sliding-window attention (SWA) with a constant-size recurrent memory. But does every layer's recurrent state contribute to long-context retrieval? Investigating an SWA and Test-Time Training (TTT) hybrid, we find that retrieval is sparse across depth, concentrated in a few anchor layers, and that the remaining states hold similar information expressed through layer-specific transformations. We exploit both observations in Anchor: TTT memory placed only at the anchor layers, and a cross-layer recurrent state written once and read by many layers, each through its own learned read map that realizes a layer-specific stretch and rotation, along with demonstrated generalization to other hybrid attentions. On Llama-3.1-8B and Mistral-7B, Anchor delivers 2.3-3.1x higher recall and 6.7-8.9 points higher MMLU accuracy than LoLCATs with a 10x smaller recurrent state, retains 91-95% of the teacher's MMLU accuracy, and cuts end-to-end latency by up to 4.3x relative to softmax attention.

cs.LG↗
arXiv2026

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

Large language models (LLMs) achieve strong performance in long-horizon agentic tasks through multi-step interaction and reasoning at test time. However, repeatedly invoking these models incurs substantial inference cost over an episode. Post-training quantization (PTQ) reduces this cost, but using a fixed low precision throughout an episode can sharply lower task success. We observe that interaction steps differ sharply in their sensitivity to quantization: given the same context, decoding a step at low precision turns a success into a failure at only about 1% of the steps, which we call critical steps. Based on this observation, we propose Dynamic Mixed-Precision Routing (DMR), a framework that adaptively selects between high-precision and low-precision versions of the same LLM at each decision step. Leveraging an entire-space factorization to jointly predict a step's divergence and its effect on the outcome, DMR learns to recognize these critical steps by training only a lightweight router on the model's hidden state. By reusing a shared high-precision KV cache and the hidden states, DMR avoids redundant context prefill and a separate text encoder, enabling precision switching with less than 1 ms of overhead per step and adding less than 0.11% to step latency for routing. This mixed-precision design also enables nested quantization, reducing the memory footprint by 39% on average compared with FP16. Across three long-horizon agentic benchmarks with nested quantization, DMR achieves an average 2.44x decode speedup over FP16 at comparable task success rates, without fine-tuning the underlying model. On ALFWorld with GPTQ, DMR achieves a 1.71x decode speedup with 86.9% success, compared with 87.2% for FP16.

cs.AI↗
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 outlier migration phenomenon where the distribution of PTQ-sensitive tokens changes across precisions. Motivated by this observation, we propose 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 outlier migration with a token-aware router to dynamically select the optimal inference precision of each token.Extensive experiments show that 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. Our code is available at https://github.com/SimWangArizona/MoBiQuant.

cs.LG↗
arXiv2026

Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction

Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post-training compression, like quantization, in practical deployment, it has been observed that the unlearning effect can be substantially weakened, with the forgetting behavior degrading more severely than that of model utility. This paper proposes a quantization-robust unlearning framework that makes forgetting robust to quantization while maintaining overall model utility. We analyze this gap through the lens of loss landscape. Specifically, our analysis reveals a curvature-based criteria that pinpoints sensitive weights in the unlearned model that leads to both non-robust forgetting and reduced utility. We therefore propose sensitivity-guided noisy regularization, which is applied on the sensitive parameters to steer the model convergence towards a smoother minima of uniformly low forget and retain losses. Balancing unlearning and utility, we further propose forget-critical optimization, which updates only forget-critical layers, preserving most of the network to retain useful knowledge. Extensive experiments on the MUSE and TOFU benchmarks across multiple LLM unlearning algorithms show that our approach achieves substantially more quantization-resilient forgetting while maintaining utility. Code is available at https://github.com/jialuw0830/QRUnlearn.

cs.LG↗
arXiv2026

TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery

Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for aggressive model pruning without performance drop, empirical results show existing methods proposed for question answering tasks severely degrade task performance when applied to agentic models. We trace this failure to two decisions: what to prune and how to recover. For pruning, one-shot importance estimates fail to track how the pruned model adapts. For recovery, offline distillation covers only teacher prefixes, while full-trajectory on-policy distillation causes student errors to compound across turns. In this work, we propose Trajectory-Anchored Pruning (TAP), the first structural pruning framework for reinforcement learning (RL)-trained agents. TAP couples structural pruning with efficient on-policy recovery, anchoring interactions to teacher trajectories while allowing the student to generate each reasoning-action response. A frozen dense teacher supervises the student's response prefixes, addressing within-response training-inference mismatch while preventing student-induced deviations from propagating across training turns. Instead of one-shot pruning, TAP re-scores channels using gradients of the recovery objective on the recovered student, connecting iterative channel selection to the evolving policy. With 60% of FFN channels removed, TAP retains 99.2% and 88.0% of the dense 7B agents' task success rates on ALFWorld and WebShop, respectively, while reducing GPU time per successful task by approximately 22% and 17%. These results demonstrate effective structural compression of long-horizon agents under a limited recovery budget.

cs.LG↗
arXiv2026

PrePARE: Pre-AA Token Pruning for Frozen Multi-View Geometry Transformers

Multi-view geometry transformers are feed-forward 3D foundation models that jointly predict depth maps, point maps, and camera poses for N images in a single forward pass. Most of them build on an alternating-attention (AA) stack whose cross-view attention runs over the patch tokens of all N views in every block, so its cost grows quadratically in N: on 300-frame ScanNetv2 clips, VGGT peaks at 72.3 GiB, and MapAnything does not fit on a 93 GiB card. Existing methods reduce tokens or attention inside the AA stack, so the full patch grid still enters it, and the pre-AA interface, where the encoder hands its tokens to the first AA block, has been overlooked. We propose PrePARE, which prunes patch tokens once at the pre-AA interface and restores the dense grid once after the last AA block. Every block of the frozen AA stack then runs on the reduced tokens, while the prediction heads receive the full grid. A Token Scorer, supervised by how the unpruned AA stack uses each token, and a Feature-guided Restoration module are the only trained parts. The Token Routing module is rule-based. On ScanNetv2 at N = 300, PrePARE reduces the peak memory of VGGT by 80%, from 72.3 to 14.4 GiB, below every in-AA method we ran, and runs 5.4 times faster, while its per-scene Chamfer distance is lower than the unpruned model's on 34 of 50 scenes (sign test p = 0.015). On pi^3 and Depth Anything 3 it saves 15% and 20% of peak memory, where the in-AA methods save at most 9%, and at 1000 frames it is the only method we ran that fits Depth Anything 3 and MapAnything on one GPU.

cs.CV↗
arXiv2026

Learning Perturbation Robust Policies for LLM Agents with Stable Optimization

Reinforcement learning (RL) has become an effective post-training paradigm for long-horizon large language model (LLM) agents. However, we find that the resulting policies can be sensitive to various policy perturbations, such as hidden-state noise, pruning, and quantization. In this work, we study how to improve perturbation robustness during policy optimization. We first introduce the notion of a perturbation robust policy and analyze conditions under which perturbed policy updates preserve stable monotonic improvement. Based on this analysis, we introduce Stable Perturbation-Robust Policy Optimization (SPrPO), which applies adaptive and sensitivity-aware perturbations during RL training. We evaluate SPrPO on ALFWorld and WebShop and conduct systematic experiments across multiple perturbation types and scales, showing improved perturbation robustness while maintaining stable policy optimization.

cs.LG↗
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

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↗