2 papers
cs.AI2025
PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training
Sarat Chandra Bobbili, Ujwal Dinesha, Dheeraj Narasimha +1
Inference-time alignment enables large language models (LLMs) to generate outputs aligned with end-user preferences without further training. Recent post-training methods achieve t…
eess.SY2024
Structured Reinforcement Learning for Media Streaming at the Wireless Edge
Archana Bura, Sarat Chandra Bobbili, Shreyas Rameshkumar +3
Media streaming is the dominant application over wireless edge (access) networks. The increasing softwarization of such networks has led to efforts at intelligent control, wherein…