10 papers
Against the Monolithic Wireless World Model: Why NextG Needs Composable and Agentic Intelligence
Aladin Djuhera, Farhan Ahmed, Vlad C. Andrei +4
AI-native 6G visions increasingly invoke wireless foundation models, large multimodal models, and wireless world models as the natural endpoint of AI-native networking, drawing an…
TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
Aladin Djuhera, Swanand Kadhe, Swanand Ravindra Kadhe +4
Advances in large language models (LLMs) are driving a shift toward using reinforcement learning (RL) to train agents from iterative, multi-turn interactions across tasks. However,…
When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
Aladin Djuhera, Farhan Ahmed, Swanand Ravindra Kadhe +3
Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct prefer…
Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance
Aladin Djuhera, Swanand Ravindra Kadhe, Syed Zawad +3
Recent work on large language models (LLMs) has increasingly focused on post-training and alignment with datasets curated to enhance instruction following, world knowledge, and spe…
SafeCOMM: A Study on Safety Degradation in Fine-Tuned Telecom Large Language Models
Aladin Djuhera, Swanand Ravindra Kadhe, Farhan Ahmed +4
Fine-tuning large language models (LLMs) on telecom datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to…
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
Aladin Djuhera, Swanand Ravindra Kadhe, Farhan Ahmed +2
Fine-tuning large language models (LLMs) is a common practice to adapt generalist models to specialized domains. However, recent studies show that fine-tuning can erode safety alig…
GneissWeb: Preparing High Quality Data for LLMs at Scale
Hajar Emami Gohari, Swanand Ravindra Kadhe, Syed Yousaf Shah +29
Data quantity and quality play a vital role in determining the performance of Large Language Models (LLMs). High-quality data, in particular, can significantly boost the LLM's abil…
Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks
Kevin Eykholt, Farhan Ahmed, Pratik Vaishnavi +1
The vulnerability of machine learning models in adversarial scenarios has garnered significant interest in the academic community over the past decade, resulting in a myriad of att…
Turning Generative Models Degenerate: The Power of Data Poisoning Attacks
Shuli Jiang, Swanand Ravindra Kadhe, Yi Zhou +3
The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through po…
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
Swanand Ravindra Kadhe, Farhan Ahmed, Dennis Wei +2
Large language models (LLMs) have shown to pose social and ethical risks such as generating toxic language or facilitating malicious use of hazardous knowledge. Machine unlearning…