NeRP corrects asymmetric class confusion in VLMs for unseen classes by combining neutral-prompt priors with sample likelihood to flip predictions on confusable pairs, improving new-class accuracy while preserving base-class performance.
hub Canonical reference
Towards a unified view of parameter-efficient transfer learning
Canonical reference. 100% of citing Pith papers cite this work as background.
21
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
method 1
citation-polarity summary
polarities
background 6representative citing papers
The paper offers a comprehensive survey and proposes a new taxonomy for continual learning strategies in VLMs and MLLMs to combat catastrophic forgetting beyond traditional methods.
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.
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
CAKI generates class-specific prompts from few-shot samples of the same class, stores them in a knowledge bank, and uses query-key matching to inject relevant class knowledge into test instance predictions for improved VLM performance.
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
Activation prompts on intermediate layers outperform input-level visual prompting and parameter-efficient fine-tuning in accuracy and efficiency across 29 datasets.
HPT uses histograms of feature embeddings to modulate pre-trained models for sonar classification, achieving higher accuracy than standard adapters on passive sonar datasets like VTUAD.
LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.
Mixture-of-Depths enables transformers to dynamically allocate compute by routing only the top-k tokens through each layer's full computations, matching baseline performance with a fraction of the FLOPs per forward pass and up to 50% faster sampling.
ReWOO decouples reasoning from tool observations in augmented language models, delivering 5x token efficiency and 4% higher accuracy on multi-step reasoning benchmarks like HotpotQA.
DRD introduces a reprogramming module and CKA-based distillation to enable efficient, robust adaptation of medical foundation models to downstream 2D/3D classification and segmentation tasks, outperforming prior PEFT and KD methods on 18 tasks.
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.
SEATrack combines AMG-LoRA for cross-modal attention alignment with HMoE for global relation modeling to improve the performance-efficiency trade-off in multimodal tracking.
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
A competition entry achieved efficient fine-tuning of LLaMa2 70B on one GPU in 24 hours with competitive QA benchmark performance.
A literature survey of Small Language Models (1-8B parameters) that can perform comparably or better than larger models, covering general-purpose and task-specific approaches plus creation techniques.
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.
citing papers explorer
-
Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
The paper offers a comprehensive survey and proposes a new taxonomy for continual learning strategies in VLMs and MLLMs to combat catastrophic forgetting beyond traditional methods.
-
Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
-
Deep Reprogramming Distillation for Medical Foundation Models
DRD introduces a reprogramming module and CKA-based distillation to enable efficient, robust adaptation of medical foundation models to downstream 2D/3D classification and segmentation tasks, outperforming prior PEFT and KD methods on 18 tasks.
-
Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)
A literature survey of Small Language Models (1-8B parameters) that can perform comparably or better than larger models, covering general-purpose and task-specific approaches plus creation techniques.
-
A Comprehensive Overview of Large Language Models
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.