Multi-Lora

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, down 75% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 28

All topics

Doc2LoRA Provides Decodable Representations of Scientific Ideas
Sep 29, 2026Chand Sahil Mansuri, Joel Zachariah, Sadamori KojakuScientific Discovery Multi-Lora
School of Systems Science and Industrial Engineering Binghamton University, Binghamton, NY, USA
G $^3$ -LoRA: Organizing Reward-Weighted Video Data with Gradient-Guided Grouped LoRA
Sep 28, 2026Jia Song, Wenhow Li, Lichen Bai +2Video Foundation Models Multi-Lora
The Hong Kong University of Science and Technology · Tencent
Resource-Aware Parameter-Efficient Model Adaptation for Onboard High-Dimensional Data
Sep 27, 2026Qiyang Zhang, Xinhao Li, Lei Shi +4Parameter-Efficient Adaptation Multi-Lora
Beijing University of Posts and Telecommunications · Wuhan University · Communication University of China +1
LoRA-GA $^2$ : Low Rank Adaptation with Multi-step Gradient Adaptive Alignment
Aug 20, 2026Haonan He, Xinyue FanMulti-Lora Model Fine-Tuning
University of Science and Technology of China · Independent Researcher
Market-Information-Aware Gated-LoRA of Foundation Models for Transferable Day-Ahead Electricity Price Forecasting
Aug 11, 2026Hang Fan, Wei Wei, Shengwei MeiElectricity Price Forecasting Electricity Markets
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Aug 10, 2026Mind Lab, :, Vin Bo +74Replay-Based Continual Learning Mixture-Of-Agents
LoCA: Forward-Only LLM Tuning after One-Shot Calibration with Local Credit Assignment
Aug 4, 2026Linhan Xia, Rui Liu, Zhaofeng Zhang +3Multi-Lora Per-Node Correction
University of Oklahoma · 4Tencent · 2Imperial College London +5
Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
Aug 1, 2026Xuefei Wang, Jun Han, Zixuan Wang +4Preference Alignment Learning Multi-Lora
Beihang University · Nankai University
Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning
Jul 26, 2026Reza Rahimi Azghan, Gautham Krishna Gudur, Giulia Pedrielli +2Replay-Based Continual Learning Catastrophic Forgetting
College of Health Solutions, Arizona State University, Phoenix, Arizona, USA · Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA · School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona, USA +1
\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating
Jul 24, 2026Jianghui Wang, Silong Yong, Francesco Orabona +3Multi-Lora Low-Rank Structure
King Abdullah University of Science and Technology · Carnegie Mellon University
On the Convergence of Stochastic Low-Rank Adaptation
Jul 24, 2026Ru Wang, Chengchang Liu, John C. S. LuiLow-Rank Adaptation Framework Multi-Lora
The Chinese University of Hong Kong · Westlake University
The Hidden Power of Scaling Factor in LoRA Optimization
Jun 11, 2026Zicheng Zhang, Haoran Li, Jiaxing Wang +10Batch Multi-Lora
JD · School of Mathematical Sciences, UCAS · School of Mathematical Sciences, NKU +1
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Jun 4, 2026Liliana Hotsko, Yinxi Li, Yuntian Deng +1Codebases Multi-Lora
University of Waterloo
Frames2LoRA: Parametric Video Internalization for Vision-Language Models
Jun 3, 2026Manan Suri, Sarvesh Baskar, Dinesh ManochaMulti-Lora Captions
University of Maryland, College Park
G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs
Jun 1, 2026Yuhan Wang, Yibo Ding, Yutong Ye +4Replay-Based Continual Learning Multi-Lora
School of Computer Science and Engineering, Beihang University Beijing, China · Department of Statistics, Columbia University New York, NY, USA · College of Computer Science, Beijing University of Technology Beijing, China
FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation
May 28, 2026Zehao Wang, Guanglei Yang, Yihan Zeng +4Multi-Lora Smoothing
1Harbin Institute of Technology · 2Huawei Noah’s Ark Lab · University College Dublin
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
May 25, 2026Fangtai Wu, Hailong Guo, Shijie Huang +7Multi-Lora Training-Side Stage-Aware Low-Rank Adaptation
Zhejiang University · Qwen Applications Business Group of Alibaba · Xi’an Jiaotong University
FedSDR: Federated Self-Distillation with Rectification
May 18, 2026Ziheng Ren, Zhanming Shen, Hao Wang +2Multi-Lora Rectification
Beijing University of Aeronautics and Astronautics · Zhejiang University · Stevens Institute of Technology +1
FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation
May 16, 2026Ramakrishnan SathyavageeswaranMulti-Lora Fisher Information Matrix
Intuit
Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
May 12, 2026Chengqian Zhang, Wei Zhu, Kyumin LeeMulti-Lora Model Fine-Tuning
Worcester Polytechnic Institute · University of Hong Kong
Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA
May 7, 2026Jinqian Chen, Chang Liu, Jihua ZhuMulti-Lora Low-Rank Structure
School of Software Engineering Xi’an Jiaotong University Xi’an, China 710000
Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection
May 5, 2026Yihang Peng, Peng Jin, Jie Gong +4Parameter-Efficient Fine-Tuning Methods Multi-Lora
School of Computer Science and Software Engineering, Southwest Petroleum University · School of Electronic Information and Artificial Intelligence, Leshan Normal University
Ortho-Hydra: Orthogonalized Experts for DiT LoRA
May 5, 2026Seunghyun JiDiffusion Transformers Multi-Lora
DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning
May 4, 2026Abdullah Ahmad Khan, Ferdous SohelMachine Unlearning Catastrophic Forgetting
Murdoch University
SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability
May 2, 2026Shuaipeng Zhou, Yu ZhangMulti-Lora Low-Rank Adaptation Framework
School of Computer Science and Technology, Shenyang University of Chemical Technology · 2Liaoning Key Laboratory of Intelligent Technology for Chemical Process Industry
BoostLoRA: Growing Effective Rank by Boosting Adapters
Apr 30, 2026Raviteja Anantha, Nick Levato, Layne C. PriceParameter-Efficient Fine-Tuning Methods Multi-Lora
Amazon
Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
Apr 20, 2026Sravanth Kodavanti, Sowmya Vajrala, Srinivas Miriyala +13LLM Inference Optimization Multi-Lora
Samsung Research Institute Bangalore, India · Samsung Electronics, Suwon, South Korea
Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation
Apr 17, 2026Habibeh Naderi, Behrouz Haji Soleimani, Stan MatwinParameter-Efficient Fine-Tuning Methods Large Language Model Adaptation
Dalhousie University, Halifax NS, Canada

Sep 29, 2026, cs.CLJ/K move · Enter open · S save

Doc2LoRA Provides Decodable Representations of Scientific Ideas

Chand Sahil Mansuri, Joel Zachariah, Sadamori Kojaku

School of Systems Science and Industrial Engineering Binghamton University, Binghamton, NY, USA

Scientific Discovery Multi-Lora

Open paper AskPDF arXiv

Representing scientific papers as points in a space lets us search for similar papers and inquire about how fields relate to one another and drive innovation. Beyond search, the vector space of papers invites generation: mixing papers through simple vector operations creates new points, mirroring combinatorial novelty, the recombination of existing ideas into new ones. However, a mixed point often represents an idea no paper has yet realized, with no papers nearby to identify the idea. We propose representing each paper by a LoRA adapter generated by the Doc-to-LoRA hypernetwork. Every point in the space, including mixtures, thus represents a large language model (LLM) open to questions and instructions in natural language. On papers from the American Physical Society (APS), we instruct the LLM at the average of each subfield to name the field in a few words and obtain labels closer to the official names than the labels of five baselines, as judged by word overlap and a panel of five LLM judges. We also ask the LLMs at points between two APS papers to write an abstract and obtain descriptions shifting from one paper to the other in step with the mixing weight. While Doc-to-LoRA is trained for generation, a small invertible transform makes the embeddings competitive for search, on par with SPECTER2 and EmbeddingGemma and close to SBERT. Because the transform is invertible, every point in the transformed space still maps back to an LLM. The embeddings thus serve both search and generation, enabling researchers to question the idea at any point in the space as a starting point for generating new ideas.

Momentum

Related topics

Latest papers 28