3 papers
cs.LG2026
Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
Anurag Roy, Riddhiman Moulick, Vinay Kumar Verma +2
In many real-world scenarios, encountering continual shifts in domain during inference is very common. Consequently, continual test-time adaptation (CTTA) techniques leveraging a t…
cs.LG2026
PRISM: Demystifying Retention and Interaction in Mid-Training
Bharat Runwal, Ashish Agrawal, Anurag Roy +1
We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four fa…
cs.LG2025
TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Zhangchen Xu, Adriana Meza Soria, Shawn Tan +4
Large Language Model (LLM) agents are rapidly emerging as powerful systems for automating tasks across domains. Yet progress in the open-source community is constrained by the lack…