Personalized Foundation Models
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Amortizing Federated Adaptation: Hypernetwork Driven LoRA for Personalized Foundation Models
new Abstract: Federated fine-tuning of foundation models using Low-Rank Adaptation (LoRA) offers a communication efficient solution for distributed learning. However, existing federated LoRA methods suffer from two fundamental limitations: (1) structural aggregation bias, where independently averaging low rank factors fails to approximate the true combined update, and (2) client side initialization lag, as clients repeatedly reinitialize LoRA parameters across communication rounds, slowing...
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Announce Type: replace Abstract: Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state on top of strong shared foundation models. In this framing, the base model provides shared competence while adapters carry instance-specific behavior such as preferences, skills, tool habits, and memory-like updates.
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
arXiv:2606.02437v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state on top of strong shared foundation models. In this framing, the base model provides shared competence while adapters carry instance-specific behavior such as preferences, skills, tool habits, and memory-like updates.
Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
arXiv:2602.07218v2 Announce Type: replace Abstract: Adaptability has been regarded as a central feature in the foundation models, enabling them to effectively acclimate to unseen downstream tasks. Parameter-efficient fine-tuning methods such as celebrated LoRA facilitate efficient adaptation of large foundation models using labeled, high-quality and generally scarce task data. To mitigate data scarcity in fine-tuning of foundation models, we propose to leverage task similarity across...
Re-Centering Humans in LLM Personalization
Announce Type: new Abstract: Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data. It remains unclear how well current personalization systems work for real users. In this paper, we study the gap in LLM personalization performance when using synthetic versus human data.
Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
arXiv:2606.08687v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of segmentation foundation models for medical imaging. However, most federated LoRA methods adopt a uniform aggregation rule, which breaks under the encoder-decoder asymmetry in medical segmentation: the encoder is dominated by appearance shifts, while the decoder is dominated by supervision variations. This mismatch entangles shared anatomy with site-specific biases and harms...
Correlation Is Not Enough: Embedding Human Metadata for Individual Causal Discovery
arXiv:2606.09672v1 Announce Type: new Abstract: Ask a pretrained biomedical language model whether "cortisol 28 ug/dL" and "stock-market volatility" are related, and it returns a cosine similarity of 0.83 on a scale where 1.0 means identical. The two share no mechanism. This is not a corner case: every off-the-shelf biomedical encoder we tested (BioBERT, PubMedBERT, BioM-ELECTRA) scores unrelated cross-domain pairs between 0.76 and 0.92 when the answer should be near zero.
Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
arXiv:2606.01858v1 Announce Type: new Abstract: Users increasingly expect image generation models to quickly adapt to highly diverse and personalized requirements, such as producing images with distinctive styles or characteristics. Traditional approaches rely on fine-tuning, which is costly and difficult to scale. To cope with these limitations, the community has accumulated a growing library of fine-tuned modules and adapters, where each component targets specific generation needs and...
Apple courts developers with privacy and context in AI comeback bid
At its 2026 Worldwide Developers Conference, Apple offered a vision of how to integrate AI with its products that stands out for its sobriety, responsibility, and plausibility. In contrast to the job-killing, security-breaking, human-replacing hype promulgated by the likes of Anthropic and OpenAI, company execs dialed down their usual superlative-laden effusiveness to convey how AI tools can actually help software developers, as well as those using Apple products. Capabilities like Safari's...
HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions
arXiv:2503.14229v4 Announce Type: replace Abstract: Vision-and-Language Navigation (VLN) has been studied mainly in either discrete or continuous spaces, with little attention to dynamic, crowded environments. We present HA-VLN 2.0, a unified benchmark introducing explicit social-awareness constraints. Our contributions are: (i) a standardized task and metrics capturing both goal accuracy and personal-space adherence; (ii) HAPS 2.0 dataset and simulators modeling multi-human interactions,...