activity
20242026
collaborators

11 papers

cs.CL2026

APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection

Fei Wang, Si Si, Cho-Jui Hsieh +1

Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential. While evolutionary algorithms have eme…

cs.IR2026

LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval

Nilesh Gupta, Wei-Cheng Chang, Ngot Bui +2

Search systems are increasingly used for reasoning-intensive queries, where what makes a document relevant requires understanding or reasoning over the query-document relation rath…

cs.LG2026

ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization

Nirmal Patel, Fei Wang, Inderjit S. Dhillon

The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedback (RLAIF) for non-verifiable domains such as long-form question answering and open-ende…

cs.LG2026

Learning, Fast and Slow: Towards LLMs That Adapt Continually

Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal +6

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific informat…

cs.LG2026

Interleaved Head Attention

Sai Surya Duvvuri, Chanakya Ekbote, Rachit Bansal +6

Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H…

cs.LG2026

LUCID: Attention with Preconditioned Representations

Sai Surya Duvvuri, Nirmal Patel, Nilesh Gupta +1

Softmax-based dot-product attention is a cornerstone of Transformer architectures, enabling remarkable capabilities such as in-context learning. However, as context lengths increas…