2 papers
cs.LG2026
Divide and Learn: Multi-Objective Combinatorial Optimization at Scale
Esha Singh, Dongxia Wu, Chien-Yi Yang +3
Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theor…
cs.CL2025
Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration
James Begin, Namit Agrawal, Eshan Singh +4
LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of ex…