7 papers
CoRPO: Adding a Correctness Bias to GRPO Improves Generalization
Anisha Garg, Claire Zhang, Nishit Neema +3
Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating adv…
From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning
Nishit Neema, Srinjoy Mukherjee, Sapan Shah +2
Large Language Models (LLMs) excel at general tasks but underperform in specialized domains like economics and psychology, which require deep, principled understanding. To address…
The Conductor and the Engine: A Path Towards Co-Designed Reasoning
Yuanxin Wang, Pawel Filipczuk, Anisha Garg +4
Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as…
Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving
Anisha Garg, Engin Tekin, Yash More +3
Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Exp…
Read Quietly, Think Aloud: Decoupling Comprehension and Reasoning in LLMs
Yuanxin Wang, Ganesh Venkatesh
Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding text and generating high-quality responses. However, a critical distinction from human cognit…
Perceiving Beyond Language Priors: Enhancing Visual Comprehension and Attention in Multimodal Models
Aarti Ghatkesar, Ganesh Venkatesh
Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual inpu…