Pith. sign in

REVIEW 31 cited by

LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.13269 v3 pith:IVYAGBOX submitted 2023-07-25 cs.CL cs.AI

LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

classification cs.CL cs.AI
keywords loralorahubmodulestaskscompositioncross-taskexamplesgeneralization
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Low-rank adaptations (LoRA) are often employed to fine-tune large language models (LLMs) for new tasks. This paper investigates LoRA composability for cross-task generalization and introduces LoraHub, a simple framework devised for the purposive assembly of LoRA modules trained on diverse given tasks, with the objective of achieving adaptable performance on unseen tasks. With just a few examples from a new task, LoraHub can fluidly combine multiple LoRA modules, eliminating the need for human expertise and assumptions. Notably, the composition requires neither additional model parameters nor gradients. Empirical results on the Big-Bench Hard benchmark suggest that LoraHub, while not surpassing the performance of in-context learning, offers a notable performance-efficiency trade-off in few-shot scenarios by employing a significantly reduced number of tokens per example during inference. Notably, LoraHub establishes a better upper bound compared to in-context learning when paired with different demonstration examples, demonstrating its potential for future development. Our vision is to establish a platform for LoRA modules, empowering users to share their trained LoRA modules. This collaborative approach facilitates the seamless application of LoRA modules to novel tasks, contributing to an adaptive ecosystem. Our code is available at https://github.com/sail-sg/lorahub, and all the pre-trained LoRA modules are released at https://huggingface.co/lorahub.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 31 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates

    cs.LG 2026-06 unverdicted novelty 7.0

    MergeProbe forecasts LoRA adapter mergeability from first-few-percent training signals and outperforms interference-aware baselines on retention while adding low overhead on a five-domain benchmark.

  2. User as Engram: Internalizing Per-User Memory as Local Parametric Edits

    cs.AI 2026-06 unverdicted novelty 7.0

    User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and comp...

  3. Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter

    cs.LG 2026-06 unverdicted novelty 7.0

    CtM merges T LoRAs into one rank-r LoRA by computing shared r-dimensional subspaces from the LoRA weights, projecting adapters into r x r coordinates, and merging in that reduced space, outperforming merge-then-compre...

  4. LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models

    cs.CR 2026-05 unverdicted novelty 7.0

    LoRA-Key creates a standalone user-specific Watermark LoRA trained with a latent watermark prior and GOP, attachable via training-free superposition to protect LoRA ownership while preserving quality.

  5. Interference-Aware Multi-Task Unlearning

    cs.AI 2026-05 unverdicted novelty 7.0

    Introduces interference-aware multi-task unlearning with task-aware gradient projection and instance-level gradient orthogonalization, reducing interference scores by 30.3% and 52.9% on vision benchmarks.

  6. CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

    cs.SE 2026-05 unverdicted novelty 7.0

    CRANE merges Instruct and Thinking model checkpoints via constrained nullspace editing to improve code agent reasoning and benchmark performance without retraining.

  7. Time-LLM: Time Series Forecasting by Reprogramming Large Language Models

    cs.LG 2023-10 conditional novelty 7.0

    Time-LLM reprograms frozen LLMs for time series forecasting via text prototypes and Prompt-as-Prefix, outperforming specialized models in standard, few-shot, and zero-shot settings.

  8. TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination

    cs.LG 2026-05 accept novelty 6.5

    Stale-occupancy sequential fine-tuning of multi-agent LLMs incurs an O(n²) certificate penalty; TeamTR resamples under intermediate occupancy and enforces token-level trust regions to restore O(n) scaling and stable gains.

  9. MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration

    cs.CV 2026-07 conditional novelty 6.0

    Domain-supervised MoE routing plus per-domain temperature scaling restores global logit calibration when merging frozen LoRA experts, cutting cross-domain interference in multi-domain VLM classification.

  10. Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing

    cs.LG 2026-07 conditional novelty 6.0

    Block-wise and cell-wise LoRA-MoE routers break static LoRA gradient conflicts on multi-context matrix tasks, with cell-level gates matching a global router on uniform shifts and beating it on heterogeneous ones.

  11. ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection

    cs.AI 2026-06 unverdicted novelty 6.0

    ARIADNE routes queries to the best adapter via embedding-space centroid proximity, recovering 97.44% of upper-bound performance on 23 NLP tasks and 89.7% selection accuracy on 44 tasks without training or internal access.

  12. Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

    cs.CL 2026-06 unverdicted novelty 6.0

    User memory in LLMs factors into three orthogonal axes where parametric adapters and retrieval show opposite strengths, with causal evidence from attention interventions and an alignment tax on RLHF models.

  13. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

    cs.SE 2026-06 unverdicted novelty 6.0

    Code2LoRA generates repo-specific LoRA adapters via hypernetwork for code LMs, matching per-repo LoRA on static tasks and exceeding shared LoRA by 5.2 pp on evolving code in a 604-repo benchmark.

  14. GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech

    cs.SD 2026-06 unverdicted novelty 6.0

    GLASS enables composable acoustic style control in zero-shot TTS by training independent GRPO-optimized LoRA adapters on style rewards that can be linearly combined.

  15. Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

    cs.LG 2026-06 conditional novelty 6.0

    Sleep-time Knowledge Seeding plus Dreaming lets LLMs expand capacity, distill fragile in-context memories into stable parameters, and self-improve without human labels.

  16. Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

    cs.LG 2026-06 unverdicted novelty 6.0

    Language models can use a two-stage sleep process of upward distillation for memory consolidation and RL-based dreaming for unsupervised self-improvement to enable continual learning.

  17. Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs

    cs.CV 2026-06 unverdicted novelty 6.0

    Polaris retrieves and integrates relevant models from a large library of checkpoints and adapters to enable scalable instruction-guided image generation and editing without additional training.

  18. PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play

    cs.AI 2026-05 unverdicted novelty 6.0

    PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.

  19. CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

    cs.SE 2026-05 unverdicted novelty 6.0

    CRANE applies magnitude thresholding, a Conservative Taylor Gate, and Graduated Sigmoidal Projection to the Thinking-Instruct delta to improve code agent pass rates on Roo-Eval, SWE-bench-Verified, and Terminal-Bench ...

  20. PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts

    cs.CL 2026-05 unverdicted novelty 6.0

    PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.

  21. Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation

    cs.CL 2026-05 unverdicted novelty 6.0

    Summing outputs from separately trained QLoRA PEFT modules provides strong performance for attribute-controlled text generation, often matching or exceeding single-task modules even on single-attribute tests.

  22. TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination

    cs.LG 2026-05 unverdicted novelty 6.0

    TeamTR is a trust-region framework for multi-agent LLM fine-tuning that resamples trajectories after each update to convert quadratic compounding occupancy shift into linear scaling and yields per-update improvement l...

  23. The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

    cs.LG 2026-04 conditional novelty 6.0

    Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering raise deep-conflict accura...

  24. Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies

    cs.AI 2026-04 unverdicted novelty 6.0

    A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.

  25. SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning

    cs.CL 2026-04 unverdicted novelty 6.0

    SAMoRA is a parameter-efficient fine-tuning framework that uses semantic-aware routing and task-adaptive scaling within a Mixture of LoRA Experts to improve multi-task performance and generalization over prior methods.

  26. LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing

    cs.LG 2025-06 unverdicted novelty 6.0

    LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.

  27. Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting

    cs.CL 2026-05 unverdicted novelty 5.0

    A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.

  28. The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

    cs.LG 2026-04 unverdicted novelty 5.0

    Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering close the gap.

  29. Efficient Handwriting-Based Alzheimer,s Disease Diagnosis Using a Low-Rank Mixture of Experts Deep Learning Framework

    cs.LG 2026-04 unverdicted novelty 4.0

    A low-rank mixture of experts model trained on handwriting data delivers strong Alzheimer's diagnosis performance with substantially reduced parameter activation during inference.

  30. Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey

    cs.LG 2024-03 accept novelty 4.0

    A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.

  31. Low-Rank Adaptation Redux for Large Models

    cs.LG 2026-04 unverdicted novelty 3.0

    An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.