3 papers
cs.DC2026
Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving
Muhammad Adnan, Rohan Mahapatra, Prashant J. Nair +4
The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy reques…
cs.CL2026
From Context Shift to Stylistic Collapse: Why Training Objectives Matter More Than Scale
Rohan Mahapatra
In modern LLMs, linguistic features function not as stylistic artifacts but as probes of probability mass, allocated under training alignment objectives. Language models trained wi…
cs.LG2026
REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving
Annabelle Sujun Tang, Christopher Priebe, Rohan Mahapatra +2
While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid…