arXiv subjects

Ting Jiang

Publications and source records attributed to Ting Jiang.

At least 19 recordsLinked to original sources

arXiv2026

Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs

Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision tasks by significantly expanding receptive fields, yet their quadratic parameter growth critically impedes storage-efficient edge deployment. While existing efficient architectures adopt parameter-efficient depthwise separable convolution backbones that leverage techniques like low-rank approximation and weight sharing to compress depthwise convolutions, we identify a critical oversight: pointwise convolutions dominate parameter volume (>87% in models like RepLKNet-31B) and constitute the primary deployment bottleneck on resource-constrained edge devices. This results in prohibitive storage costs and severe memory-loading constraints on resource-limited devices (e.g., smartphones with 4-12 GB Random Access Memory (RAM)). To overcome this, we propose Channel Group-Shared (CGS) low-rank approximation, a novel Singular Value Decomposition (SVD)-based parameter-sharing strategy. CGS constructs a structured low-rank paradigm isomorphic to SVD decomposition, comprising shared (high-parameter-cost) down/up-projection matrices across channel groups within a layer and channel-group-specific (low-parameter-cost) scalable diagonal matrices. This group-sharing design achieves significant parameter reduction. Extensive experiments demonstrate that large-kernel CNNs (RepLKNet, ConvNeXt, SLaK) enhanced with CGS strike an empirically favorable balance between competitive performance and substantially reduced storage costs. Crucially, by alleviating storage constraints, reducing memory bandwidth pressure during loading, and minimizing model loading latency, CGS enables the feasible deployment of pre-trained large-kernel CNN models on edge devices, thereby bridging the gap between high-performance vision models and practical edge deployment.

cs.LG↗

arXiv2026

LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM Compression

SVD-based low-rank compression has become a fast-growing direction for reducing the memory and computational cost of large language models (LLMs). However, meaningful comparison across existing studies remains difficult as prior evaluations use varied benchmarks, inconsistent ratios, and diverse setups, often failing to isolate low-rank effects from auxiliary techniques. As a result, it remains unclear whether reported gains reflect method-level improvements or differences in evaluation protocol. This lack of comparability highlights the need for a unified, reproducible evaluation platform. To address this problem, we present LowRankArena, a standardized evaluation platform for SVD-based LLM compression. LowRankArena unifies task versions, uniform-precision compression budgets, comparison regimes, and inference measurements, and provides a reproducible pipeline with over 3 TiB released compressed checkpoints. Using LowRankArena, our aligned audit of five representative SVD methods reveals that prior findings are highly conditional under standardized protocols: clear leaders and performance tiers shift across backbones and keep ratios, multiple-choice accuracy can hide large perplexity degradation, and nominal low-rank savings yield workload-dependent and often limited end-to-end speedups. Our code is available at: https://github.com/Zishan-Shao/lowrankarena.git.

cs.CL↗

arXiv2026

DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions

Large language models (LLMs) handle many tasks with one set of parameters, but under KV-cached inference it is unclear what task-general structure, if any, is used at decode time rather than during prefill. We propose DecodeShare, a protocol that identifies a low-dimensional subspace consistently shared across tasks in decode-time hidden states, and then tests its causal role by removing that subspace only during decoding. In our experiments, disturbing the discovered shared subspace degrades decision performance far more than disturbing either a prefill-derived or random subspace under the same intervention budget. We further show this decode-shared subspace has practical consequences for activation steering: common steering directions can overlap the task-general decode channel. Projecting out this shared subspace directly separates the functional roles of the two components, while evaluating steering vectors at decode-time yields more reliable signal for downstream deployment than prefill-based proxies. Despite its compactness, the shared subspace can serve as a high-leverage causal channel at decode time. Code is available at: https://github.com/Zishan-Shao/decodeshare.git.

cs.AI↗

arXiv2026

ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor

Denoising generative models deliver high-fidelity generation but remain bottlenecked by inference latency due to the many iterative denoiser calls required during sampling. Training-free acceleration methods reduce latency by either sparsifying the model architecture or shortening the sampling trajectory. Current training-free acceleration methods are more complex than necessary: higher-order predictors amplify error under aggressive speedups, and architectural modifications hinder deployment. Beyond 2x acceleration, step skipping creates structural scarcity -- at most one fresh evaluation per local window -- leaving the computed output and its backward difference as the only causally grounded information. Based on this, we propose ZEUS, an acceleration method that predicts reduced denoiser evaluations using a second-order predictor, and stabilizes aggressive consecutive skipping with an interleaved scheme that avoids back-to-back extrapolations. ZEUS adds essentially zero overhead, no feature caches, and no architectural modifications, and it is compatible with different backbones, prediction objectives, and solver choices. Across image and video generation, ZEUS consistently improves the speed-fidelity performance over recent training-free baselines, achieving up to 3.2x end-to-end speedup while maintaining perceptual quality. Our code is available at: https://github.com/Ting-Justin-Jiang/ZEUS.

cs.LG↗

arXiv2026

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and DeepSeek Sparse Attention (DSA) is a representative production-grade solution: a lightweight lightning indexer selects the top-k most relevant tokens per query, reducing core attention from $O(L^2)$ to $O(Lk)$. However, the indexer itself retains $O(L^2)$ complexity and must run independently at every layer, despite the fact that the resulting top-k selections are highly similar across consecutive layers. We present IndexCache, which exploits this cross-layer redundancy by partitioning layers into a small set of Full layers that run their own indexers and a majority of Shared layers that simply reuse the nearest Full layer's top-k indices. We propose two complementary approaches to determine and optimize this configuration. Training-free IndexCache applies a greedy search algorithm that selects which layers to retain indexers by directly minimizing language modeling loss on a calibration set, requiring no weight updates. Training-aware IndexCache introduces a multi-layer distillation loss that trains each retained indexer against the averaged attention distributions of all layers it serves, enabling even simple interleaved patterns to match full-indexer accuracy. Experimental results on a 30B DSA model show that IndexCache can remove 75% of indexer computations with negligible quality degradation, achieving up to 1.82$\times$ prefill speedup and 1.48$\times$ decode speedup compared to standard DSA. These positive results are further confirmed by our preliminary experiments on the production-scale GLM-5 model (Figure 1).

cs.CL↗

arXiv2026

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Think about how human handles complex reading tasks: marking key points, inferring their relationships, and structuring information to guide understanding and responses. Likewise, can a large language model benefit from text structure to enhance text-processing performance? To explore it, in this work, we first introduce Structure of Thought (SoT), a prompting technique that explicitly guides models to construct intermediate text structures, consistently boosting performance across eight tasks and three model families. Building upon this insight, we present T2S-Bench, the first benchmark designed to evaluate and improve text-to-structure capabilities of models. T2S-Bench includes 1.8K samples across 6 scientific domains and 32 structural types, rigorously constructed to ensure accuracy, fairness, and quality. Evaluation on 45 mainstream models reveals substantial improvement potential: the average accuracy on the multi-hop reasoning task is only 52.1%, and even the most advanced model achieves 58.1% node accuracy in end-to-end extraction. Furthermore, on Qwen2.5-7B-Instruct, SoT alone yields an average +5.7% improvement across eight diverse text-processing tasks, and fine-tuning on T2S-Bench further increases this gain to +8.6%. These results highlight the value of explicit text structuring and the complementary contributions of SoT and T2S-Bench. Dataset and eval code have been released at https://t2s-bench.github.io/T2S-Bench-Page/.

cs.CL↗

arXiv2026

GLM-5: from Vibe Coding to Agentic Engineering

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

cs.LG↗

arXiv2025

Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models

We present a novel enhanced cyclic coordinate descent (ECCD) framework for solving generalized linear models with elastic net constraints that reduces training time in comparison to existing state-of-the-art methods. We redesign the CD method by performing a Taylor expansion around the current iterate to avoid nonlinear operations arising in the gradient computation. By introducing this approximation, we are able to unroll the vector recurrences occurring in the CD method and reformulate the resulting computations into more efficient batched computations. We show empirically that the recurrence can be unrolled by a tunable integer parameter, $s$, such that $s > 1$ yields performance improvements without affecting convergence, whereas $s = 1$ yields the original CD method. A key advantage of ECCD is that it avoids the convergence delay and numerical instability exhibited by block coordinate descent. Finally, we implement our proposed method in C++ using Eigen to accelerate linear algebra computations. Comparison of our method against existing state-of-the-art solvers shows consistent performance improvements of $3\times$ in average for regularization path variant on diverse benchmark datasets. Our implementation is available at https://github.com/Yixiao-Wang-Stats/ECCD.

stat.ML↗

arXiv2025

Robust and Hyper-Efficient Multi-dimensional Optical Fiber Semantic Communication

The growing demands of artificial intelligence and immersive media require communication beyond bit-level accuracy to meaning awareness. Conventional optical systems that focused on syntactic precision suffer significant inefficiencies. Here, we introduce a multi-dimensional semantic communication framework that bridges this gap by directly mapping high-level semantic features onto the orthogonal physical dimensions of light, frequency, polarization, and intensity, within a multimode fiber. This synergistic co-design of semantic logic and the photonic channel achieve an unprecedented equivalent spectral efficiency approaching 1000 bit/s/Hz. Moreover, it demonstrates profound resilience, maintaining high-fidelity reconstruction even when the physical-layer symbol error rate exceeds 36%, a condition under which conventional communication systems fail completely. Crucially, this deeply integrated co-design of semantic encoding and physical-layer modulation enables full semantic demodulation with only single-ended intensity detection, therefore significantly reducing system complexity and cost. This work establishes a validated pathway toward hyper-efficient, error-resilient optical networks for the next generation of data-intensive computing.

physics.optics↗

arXiv2025

FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models

Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal accuracy loss. Previous SVD-based approaches have focused primarily on reducing the memory footprint of model weights, largely overlooking the additional activation memory overhead incurred during inference when applying truncated factors via standard dense CUDA kernels. Our experiments demonstrate that this activation overhead, scaling with sequence length and hidden dimension, prevents current SVD compression techniques from achieving any reduction in peak inference memory, thereby limiting their viability for real-world, on-device deployments. We introduce FlashSVD, a novel, end-to-end rank-aware streaming inference framework specifically designed for SVD-compressed large language models. FlashSVD can be seamlessly integrated with any model that employs SVD-based methods for parameter reduction. By fusing low-rank projection kernels directly into both the self-attention and feed-forward network (FFN) pipelines, FlashSVD avoid materializing full-size activation buffers. Instead, small tiles of the truncated factors are loaded into on-chip SRAM, multiplied and reduced on the fly, and immediately evicted, preserving high GPU occupancy and adding no extra latency. On standard encoder benchmarks (e.g., BERT-Base), FlashSVD cuts peak activation memory by up to 70.2% and intermediate transient memory by 75%, all while incur no accuracy loss with upstreaming compression methods, offering a practical path toward memory-constrained deployment of low-rank LLMs.

cs.LG↗

arXiv2025

SADA: Stability-guided Adaptive Diffusion Acceleration

Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce per-step computation cost, while effectively reducing sampling time, demonstrate low faithfulness compared to the original baseline. We hypothesize that this fidelity gap arises because (a) different prompts correspond to varying denoising trajectory, and (b) such methods do not consider the underlying ODE formulation and its numerical solution. In this paper, we propose Stability-guided Adaptive Diffusion Acceleration (SADA), a novel paradigm that unifies step-wise and token-wise sparsity decisions via a single stability criterion to accelerate sampling of ODE-based generative models (Diffusion and Flow-matching). For (a), SADA adaptively allocates sparsity based on the sampling trajectory. For (b), SADA introduces principled approximation schemes that leverage the precise gradient information from the numerical ODE solver. Comprehensive evaluations on SD-2, SDXL, and Flux using both EDM and DPM++ solvers reveal consistent $\ge 1.8\times$ speedups with minimal fidelity degradation (LPIPS $\leq 0.10$ and FID $\leq 4.5$) compared to unmodified baselines, significantly outperforming prior methods. Moreover, SADA adapts seamlessly to other pipelines and modalities: It accelerates ControlNet without any modifications and speeds up MusicLDM by $1.8\times$ with $\sim 0.01$ spectrogram LPIPS.

cs.LG↗

arXiv2024

A Multi-Scale Spatial-Temporal Network for Wireless Video Transmission

Deep joint source-channel coding (DeepJSCC) has shown promise in wireless transmission of text, speech, and images within the realm of semantic communication. However, wireless video transmission presents greater challenges due to the difficulty of extracting and compactly representing both spatial and temporal features, as well as its significant bandwidth and computational resource requirements. In response, we propose a novel video DeepJSCC (VDJSCC) approach to enable end-to-end video transmission over a wireless channel. Our approach involves the design of a multi-scale vision Transformer encoder and decoder to effectively capture spatial-temporal representations over long-term frames. Additionally, we propose a dynamic token selection module to mask less semantically important tokens from spatial or temporal dimensions, allowing for content-adaptive variable-length video coding by adjusting the token keep ratio. Experimental results demonstrate the effectiveness of our VDJSCC approach compared to digital schemes that use separate source and channel codes, as well as other DeepJSCC schemes, in terms of reconstruction quality and bandwidth reduction.

eess.IV↗

arXiv2024

Optical Semantic Communication through Multimode Fiber: From Symbol Transmission to Sentiment Analysis

We propose and validate a novel optical semantic transmission scheme using multimode fiber (MMF). By leveraging the frequency sensitivity of intermodal dispersion in MMFs, we achieve high-dimensional semantic encoding and decoding in the frequency domain. Our system maps symbols to 128 distinct frequencies spaced at 600 kHz intervals, demonstrating a seven-fold increase in capacity compared to conventional communication encoding. We further enhance spectral efficiency by implementing 4-level pulse amplitude modulation (PAM-4), achieving 9.12 bits/s/Hz without decoding errors. Additionally, we explore the application of this system for sentiment analysis using the IMDb movie review dataset. By encoding semantically similar symbols to adjacent frequencies, the system's noise tolerance is effectively improved, facilitating accurate sentiment analysis. This work highlights the potential of MMF-based semantic communication to enhance both capacity and robustness in optical communication systems, offering promising applications in bandwidth-constrained and noisy environments.

eess.SP↗

arXiv2024

Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation

Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years. However, they often suffer from heavy computational burden and slow inference due to the complex calculation of multi-head self-attention (MSA), seriously hindering their practical application and deployment. In this work, we present an efficient SR model to mitigate the dilemma between model efficiency and SR performance, which is dubbed Entropy Attention and Receptive Field Augmentation network (EARFA), and composed of a novel entropy attention (EA) and a shifting large kernel attention (SLKA). From the perspective of information theory, EA increases the entropy of intermediate features conditioned on a Gaussian distribution, providing more informative input for subsequent reasoning. On the other hand, SLKA extends the receptive field of SR models with the assistance of channel shifting, which also favors to boost the diversity of hierarchical features. Since the implementation of EA and SLKA does not involve complex computations (such as extensive matrix multiplications), the proposed method can achieve faster nonlinear inference than Transformer-based SR models while maintaining better SR performance. Extensive experiments show that the proposed model can significantly reduce the delay of model inference while achieving the SR performance comparable with other advanced models.

eess.IV↗

arXiv2024

Diff-Shadow: Global-guided Diffusion Model for Shadow Removal

We propose Diff-Shadow, a global-guided diffusion model for shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover images with obvious boundaries. In contrast, diffusion-based methods can generate better content but they are not exempt from issues related to inconsistent illumination. In this work, we combine the advantages of diffusion models and global guidance to achieve shadow-free restoration. Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images. A Reweight Cross Attention (RCA) module is designed to integrate global contextual information of non-shadow regions into the local branch. We further design a Global-guided Sampling Strategy (GSS) that mitigates patch boundary issues and ensures consistent illumination across shaded and unshaded regions in the recovered image. Comprehensive experiments on datasets ISTD, ISTD+, and SRD have demonstrated the effectiveness of Diff-Shadow. Compared to state-of-the-art methods, our method achieves a significant improvement in terms of PSNR, increasing from 32.33dB to 33.69dB on the ISTD dataset.

cs.CV↗

arXiv2024

E5-V: Universal Embeddings with Multimodal Large Language Models

Multimodal large language models (MLLMs) have shown promising advancements in general visual and language understanding. However, the representation of multimodal information using MLLMs remains largely unexplored. In this work, we introduce a new framework, E5-V, designed to adapt MLLMs for achieving universal multimodal embeddings. Our findings highlight the significant potential of MLLMs in representing multimodal inputs compared to previous approaches. By leveraging MLLMs with prompts, E5-V effectively bridges the modality gap between different types of inputs, demonstrating strong performance in multimodal embeddings even without fine-tuning. We propose a single modality training approach for E5-V, where the model is trained exclusively on text pairs. This method demonstrates significant improvements over traditional multimodal training on image-text pairs, while reducing training costs by approximately 95%. Additionally, this approach eliminates the need for costly multimodal training data collection. Extensive experiments across four types of tasks demonstrate the effectiveness of E5-V. As a universal multimodal model, E5-V not only achieves but often surpasses state-of-the-art performance in each task, despite being trained on a single modality.

cs.CL↗

arXiv2024

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. In this paper, we analyze the impact of low-rank updating, as implemented in LoRA. Our findings suggest that the low-rank updating mechanism may limit the ability of LLMs to effectively learn and memorize new knowledge. Inspired by this observation, we propose a new method called MoRA, which employs a square matrix to achieve high-rank updating while maintaining the same number of trainable parameters. To achieve it, we introduce the corresponding non-parameter operators to reduce the input dimension and increase the output dimension for the square matrix. Furthermore, these operators ensure that the weight can be merged back into LLMs, which makes our method can be deployed like LoRA. We perform a comprehensive evaluation of our method across five tasks: instruction tuning, mathematical reasoning, continual pretraining, memory and pretraining. Our method outperforms LoRA on memory-intensive tasks and achieves comparable performance on other tasks.

cs.CL↗

arXiv2024

Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation

In this paper, we address the Bracket Image Restoration and Enhancement (BracketIRE) task using a novel framework, which requires restoring a high-quality high dynamic range (HDR) image from a sequence of noisy, blurred, and low dynamic range (LDR) multi-exposure RAW inputs. To overcome this challenge, we present the IREANet, which improves the multiple exposure alignment and aggregation with a Flow-guide Feature Alignment Module (FFAM) and an Enhanced Feature Aggregation Module (EFAM). Specifically, the proposed FFAM incorporates the inter-frame optical flow as guidance to facilitate the deformable alignment and spatial attention modules for better feature alignment. The EFAM further employs the proposed Enhanced Residual Block (ERB) as a foundational component, wherein a unidirectional recurrent network aggregates the aligned temporal features to better reconstruct the results. To improve model generalization and performance, we additionally employ the Bayer preserving augmentation (BayerAug) strategy to augment the multi-exposure RAW inputs. Our experimental evaluations demonstrate that the proposed IREANet shows state-of-the-art performance compared with previous methods.

cs.CV↗