2 citations · 5 across the 29 of their papers we have counts for
12 papers · 1 filter
HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models
Erum Mushtaq, Zalan Fabian, Yavuz Faruk Bakman +3
Uncertainty Estimation (UE) plays a central role in quantifying the reliability of model outputs and reducing unsafe generations via selective prediction. In this regard, most exis…
From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna +5
Recent work has shown that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon, where models generate malicious responses even to prompts unrela…
Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models
Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna +2
Artificial Intelligence have profoundly transformed the technological landscape in recent years. Large Language Models (LLMs) have demonstrated impressive abilities in reasoning, t…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
BLUR: A Bi-Level Optimization Approach for LLM Unlearning
Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu +6
Enabling large language models (LLMs) to unlearn knowledge and capabilities acquired during training has proven vital for ensuring compliance with data regulations and promoting et…
Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models
Taha Entesari, Arman Hatami, Rinat Khaziev +2
Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information. Existing unlearning methods typi…