More Like this

1. Visual Prompt Tuning

   https://doi.org/10.1007/978-3-031-19827-4_41  

   Jia, Menglin; Tang, Luming; Chen, Bor-Chun; Cardie, Claire; Belongie, Serge; Hariharan, Bharath; Lim, Ser-Nam (October 2022, European Conference on Computer Vision)

   The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as an efficient and effective alternative to full fine-tuning for large-scale Transformer models in vision. Taking inspiration from recent advances in efficiently tuning large language models, VPT introduces only a small amount (less than 1% of model parameters) of trainable parameters in the input space while keeping the model backbone frozen. Via extensive experiments on a wide variety of downstream recognition tasks, we show that VPT achieves significant performance gains compared to other parameter efficient tuning protocols. Most importantly, VPT even outperforms full fine-tuning in many cases across model capacities and training data scales, while reducing per-task storage cost. 

   more » « less
2. WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models

   Savadikar, Chinmay; Song, Xi; Wu, Tianfu (May 2025, Proceedings of the 42 nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025.)

   Fine-tuning large pretrained Transformer models can focus on either introducing a small number of new learnable parameters (parameter efficiency) or editing representations of a small number of tokens using lightweight modules (representation efficiency). While the pioneering method LoRA (Low-Rank Adaptation) inherently balances parameter, compute, and memory efficiency, many subsequent variants trade off compute and memory efficiency and/or performance to further reduce fine-tuning parameters. To address this limitation and unify parameter-efficient and representation-efficient fine-tuning, we propose Weight-Generative Fine-Tuning (WeGeFT, pronounced wee-gift), a novel approach that learns to generate fine-tuning weights directly from the pretrained weights. WeGeFT employs a simple low-rank formulation consisting of two linear layers, either shared across multiple layers of the pretrained model or individually learned for different layers. This design achieves multifaceted efficiency in parameters, representations, compute, and memory, while maintaining or exceeding the performance of LoRA and its variants. Extensive experiments on commonsense reasoning, arithmetic reasoning, instruction following, code generation, and visual recognition verify the effectiveness of our proposed WeGeFT. 

   more » « less
3. GC-LoRA: Gated Convolutional LoRA for Parameter-Efficient Acoustic Adaptation

   Shankar, B; Wang, Z; Zhang, K; Shi, M; Alwan, A (September 2026, Proceedings of Interspeech 2026. ISCA.)

   Transformer-based Speech Foundation Models excel in most Automatic Speech Recognition tasks but often suffer performance degradation when applied to domains with mismatched acoustic characteristics. While Parameter Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), adjust global attention, they lack the local context modeling crucial for capturing domain-specific variations. We propose GC-LoRA, a novel adapter architecture that injects Conformer-style local convolutional processing into pretrained Transformer encoders. By integrating a lightweight adapter to encoder attention output projections, our method efficiently captures local acoustic dependencies without disrupting pretrained global representations. Experiments across diverse datasets (acoustically-degraded, bandlimited, dialectal, child) demonstrate the efficacy of our approach, achieving Word Error Rate (WER) reductions of up to 10.9% compared to baselines while adding minimal trainable parameters. 

   more » « less
4. ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

   https://doi.org/10.52202/079017-0782  

   Fu, Yichao; Guo, Yipin; Kundu, Souvik; Lin, Yingyan Celine; Shi, Huihong; Yazdanbakhsh, Amir; You, Haoran; Zhang, Xiaofan; Zhou, Wei (October 2024, Neural Information Processing Systems Foundation, Inc. (NeurIPS))

   Large language models (LLMs) have shown impressive performance on language tasks but face challenges when deployed on resource-constrained devices due to their extensive parameters and reliance on dense multiplications, resulting in high memory demands and latency bottlenecks. Shift-and-add reparameterization offers a promising solution by replacing costly multiplications with hardware-friendly primitives in both the attention and multi-layer perceptron (MLP) layers of an LLM. However, current reparameterization techniques require training from scratch or full parameter fine-tuning to restore accuracy, which is resource-intensive for LLMs. To address this, we propose accelerating pretrained LLMs through post-training shift-and-add reparameterization, creating efficient multiplication-free models, dubbed ShiftAddLLM. Specifically, we quantize each weight matrix into binary matrices paired with group-wise scaling factors. The associated multiplications are reparameterized into (1) shifts between activations and scaling factors and (2) queries and adds according to the binary matrices. To reduce accuracy loss, we present a multi-objective optimization method to minimize both weight and output activation reparameterization errors. Additionally, based on varying sensitivity across layers to reparameterization, we develop an automated bit allocation strategy to further reduce memory usage and latency. Experiments on five LLM families and eight tasks consistently validate the effectiveness of ShiftAddLLM, achieving average perplexity reductions of 5.6 and 22.7 points at comparable or lower latency compared to the most competitive quantized LLMs at 3- and 2-bit precision, respectively, and more than 80% memory and energy reductions over the original LLMs. Codes and models are available at https://github.com/GATECH-EIC/ShiftAddLLM. 

   more » « less
5. LoRAFusion: A Crossbar-aware Multi-task Adaption Framework via Efficient Fusion of Pretrained LoRA Modules

   https://doi.org/10.1145/3716368.3735213  

   Guo, Jingkai; Ali, Asmer; Yang, Li; Fan, Deliang (June 2025, ACM)

   The non-volatile Resistive RAM (ReRAM) crossbar has shown great potential in accelerating inference in various machine learning models However, it suffers from high reprogramming energy, hindering its usage for on-device adaption to new tasks. Recently, parameter-efficient fine-tuning methods, such as Low-Rank Adaption (LoRA), have been proposed to train few parameters while matching full fine-tuning performance. However, in ReRAM crossbar, the reprogramming cost of LoRA is non-trivial and will increase significantly when adapting to multi-tasks on the device. To address this issue, we are the first to propose LoRAFusion, a parameter-efficient multi-task on-device learning framework for ReRAM crossbar via fusion of pre-trained LoRA modules. LoRAFusion is a group of LoRA modules that are one-time learned based on diverse domain-specific tasks and deployed to the crossbar, acting as the pool of background knowledge. Then given a new unseen task, those LoRA modules are frozen (i.e., no energy-hungry ReRAM cells reprograming), only the proposed learnable layer-wise LoRA fusion coefficient and magnitude vector parameters are trained on-device to weighted-combine pre-trained LoRA modules, which significantly reduces the training parameter size. Our comprehensive experiments show LoRAFusion only uses 3% of the number of trainable parameters in LoRA (148K vs. 4700K), with 0.19% accuracy drop. Codes are available at https://github.com/ASU-ESIC-FAN-Lab/LoRAFusion 

   more » « less