17 citations · 51 across the 24 of their papers we have counts for
28 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…
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…
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…
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…
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…
Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models
Raman Dutt, Pedro Sanchez, Ondrej Bohdal +2
In this work, we present compelling evidence that controlling model capacity during fine-tuning can effectively mitigate memorization in diffusion models. Specifically, we demonstr…
Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted
Ruchika Chavhan, Ondrej Bohdal, Yongshuo Zong +2
Large-scale text-to-image diffusion models excel in generating high-quality images from textual inputs, yet concerns arise as research indicates their tendency to memorize and repl…
MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection
Raman Dutt, Ondrej Bohdal, Pedro Sanchez +2
Diffusion models excel in generating images that closely resemble their training data but are also susceptible to data memorization, raising privacy, ethical, and legal concerns, p…
VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
Yongshuo Zong, Ondrej Bohdal, Timothy Hospedales
Large language models (LLMs) famously exhibit emergent in-context learning (ICL) -- the ability to rapidly adapt to new tasks using few-shot examples provided as a prompt, without…
Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models
Yongshuo Zong, Ondrej Bohdal, Tingyang Yu +2
Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks.…
FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Raman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris +1
Training models with robust group fairness properties is crucial in ethically sensitive application areas such as medical diagnosis. Despite the growing body of work aiming to mini…
Label Calibration for Semantic Segmentation Under Domain Shift
Ondrej Bohdal, Da Li, Timothy Hospedales
Performance of a pre-trained semantic segmentation model is likely to substantially decrease on data from a new domain. We show a pre-trained model can be adapted to unlabelled tar…
Feed-Forward Source-Free Domain Adaptation via Class Prototypes
Ondrej Bohdal, Da Li, Timothy Hospedales
Source-free domain adaptation has become popular because of its practical usefulness and no need to access source data. However, the adaptation process still takes a considerable a…
Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks
Martin Ferianc, Ondrej Bohdal, Timothy Hospedales +1
Enhancing the generalisation abilities of neural networks (NNs) through integrating noise such as MixUp or Dropout during training has emerged as a powerful and adaptable technique…
Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn
Ondrej Bohdal, Yinbing Tian, Yongshuo Zong +5
Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and den…
Fairness in AI and Its Long-Term Implications on Society
Ondrej Bohdal, Timothy Hospedales, Philip H. S. Torr +1
Successful deployment of artificial intelligence (AI) in various settings has led to numerous positive outcomes for individuals and society. However, AI systems have also been show…
Feed-Forward Latent Domain Adaptation
Ondrej Bohdal, Da Li, Shell Xu Hu +1
We study a new highly-practical problem setting that enables resource-constrained edge devices to adapt a pre-trained model to their local data distributions. Recognizing that devi…
PASHA: Efficient HPO and NAS with Progressive Resource Allocation
Ondrej Bohdal, Lukas Balles, Martin Wistuba +3
Hyperparameter optimization (HPO) and neural architecture search (NAS) are methods of choice to obtain the best-in-class machine learning models, but in practice they can be costly…