1 citations · 2 across the 4 of their papers we have counts for
4 papers
Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
Davide Romano, Kanak Raj, Jerrod Parker +1
Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over partial sequences, or iteratively…
LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models
Sourav Chattaraj, Kanak Raj
Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood. From patient health logs tracking evolvi…
K-PERM: Personalized Response Generation Using Dynamic Knowledge Retrieval and Persona-Adaptive Queries
Kanak Raj, Kaushik Roy, Vamshi Bonagiri +3
Personalizing conversational agents can enhance the quality of conversations and increase user engagement. However, they often lack external knowledge to appropriately tend to a us…
Cook-Gen: Robust Generative Modeling of Cooking Actions from Recipes
Revathy Venkataramanan, Kaushik Roy, Kanak Raj +4
As people become more aware of their food choices, food computation models have become increasingly popular in assisting people in maintaining healthy eating habits. For example, f…