25 citations · 32 across the 25 of their papers we have counts for
30 papers
DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation
Peyman Hosseini, Ondrej Bohdal, Ahmed Alajrami +6
Large Language Model (LLM)-based agents can solve complex procedural tasks by interacting with environments over multiple turns, but this ability typically depends on large models,…
Diffusion Alignment Beyond KL: Variance Minimisation as Effective Policy Optimiser
Zijing Ou, Jacob Si, Junyi Zhu +4
Diffusion alignment adapts pretrained diffusion models to sample from reward-tilted distributions along the denoising trajectory. This process naturally admits a Sequential Monte C…
Feature-Space Generative Models for One-Shot Class-Incremental Learning
Jack Foster, Kirill Paramonov, Mete Ozay +1
Few-shot class-incremental learning (FSCIL) is a paradigm where a model, initially trained on a dataset of base classes, must adapt to an expanding problem space by recognizing nov…
Clustering-driven Memory Compression for On-device Large Language Models
Ondrej Bohdal, Pramit Saha, Umberto Michieli +2
Large language models (LLMs) often rely on user-specific memories distilled from past interactions to enable personalized generation. A common practice is to concatenate these memo…
Data-driven Clustering and Merging of Adapters for On-device Large Language Models
Ondrej Bohdal, Taha Ceritli, Mete Ozay +4
On-device large language models commonly employ task-specific adapters (e.g., LoRAs) to deliver strong performance on downstream tasks. While storing all available adapters is impr…
MemLoRA: Distilling Expert Adapters for On-Device Memory Systems
Massimo Bini, Ondrej Bohdal, Umberto Michieli +3
Memory-augmented Large Language Models (LLMs) have demonstrated remarkable consistency during prolonged dialogues by storing relevant memories and incorporating them as context. Su…
Continual Error Correction on Low-Resource Devices
Kirill Paramonov, Mete Ozay, Aristeidis Mystakidis +11
The proliferation of AI models in everyday devices has highlighted a critical challenge: prediction errors that degrade user experience. While existing solutions focus on error det…
CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models
Peyman Hosseini, Ondrej Bohdal, Taha Ceritli +4
Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages…
On-device System of Compositional Multi-tasking in Large Language Models
Ondrej Bohdal, Konstantinos Theodosiadis, Asterios Mpatziakas +10
Large language models (LLMs) are commonly adapted for diverse downstream tasks via parameter-efficient fine-tuning techniques such as Low-Rank Adapters (LoRA). While adapters can b…
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
Donald Shenaj, Ondrej Bohdal, Taha Ceritli +3
On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address…
MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
Elena Camuffo, Francesco Barbato, Mete Ozay +2
Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples. Lightweight models often struggle in this sett…
HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging
Taha Ceritli, Ondrej Bohdal, Mete Ozay +4
Large language models (LLMs) often leverage adapters, such as low-rank-based adapters, to achieve strong performance on downstream tasks. However, storing a separate adapter for ea…
Efficient Compositional Multi-tasking for On-device Large Language Models
Ondrej Bohdal, Mete Ozay, Jijoong Moon +3
Adapter parameters provide a mechanism to modify the behavior of machine learning models and have gained significant popularity in the context of large language models (LLMs) and g…
Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning
Kirill Paramonov, Mete Ozay, Eunju Yang +2
Class-incremental learning in the context of limited personal labeled samples (few-shot) is critical for numerous real-world applications, such as smart home devices. A key challen…
LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
Donald Shenaj, Ondrej Bohdal, Mete Ozay +2
Recent advancements in image generation models have enabled personalized image creation with both user-defined subjects (content) and styles. Prior works achieved personalization b…
DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
Emanuele Aiello, Umberto Michieli, Diego Valsesia +2
Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different con…
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation
Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud +4
Fine-tuning has become a popular approach to adapting large foundational models to specific tasks. As the size of models and datasets grows, parameter-efficient fine-tuning techniq…
Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search
Kirill Paramonov, Jia-Xing Zhong, Umberto Michieli +2
In this paper, we address a recent trend in robotic home appliances to include vision systems on personal devices, capable of personalizing the appliances on the fly. In particular…
Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics
Elena Camuffo, Umberto Michieli, Simone Milani +2
Developing a reliable vision system is a fundamental challenge for robotic technologies (e.g., indoor service robots and outdoor autonomous robots) which can ensure reliable naviga…
Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection
Francesco Barbato, Umberto Michieli, Jijoong Moon +2
Recent years have seen object detection robotic systems deployed in several personal devices (e.g., home robots and appliances). This has highlighted a challenge in their design, i…
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati +4
Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. H…
Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition
Umberto Michieli, Jijoong Moon, Daehyun Kim +1
Nowadays, users demand for increased personalization of vision systems to localize and identify personal instances of objects (e.g., my dog rather than dog) from a few-shot dataset…
FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images
Elena Camuffo, Umberto Michieli, Jijoong Moon +2
Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents. Particularly, robust te…
A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation
Francesco Barbato, Umberto Michieli, Mehmet Kerim Yucel +2
In multimedia understanding tasks, corrupted samples pose a critical challenge, because when fed to machine learning models they lead to performance degradation. In the past, three…