Leveraging Suboptimal and Noisy Trajectories for Goal-Conditional Offline RLNingze ZhongYi Wanget al.2026ICLR 2026Workshop paper
Entropy-Aware On-Policy Distillation of Language ModelsWoogyeol JinTaywon Minet al.2026ICLR 2026Workshop paper
TSR: Trajectory‑Search Rollouts for Multi‑Turn RL of LLM AgentsAladin DjuheraSwanand Ravindra Kadheet al.2026ICLR 2026Workshop paper
Task Representational Dynamics for Compositional Generalization During Context-Dependent Cognitive TasksLakshman ChakravarthulaMichael Coleet al.2026ICLR 2026Workshop paper
Unifying Concept Representation LearningAmit DhurandharAmir-hossein Karimiet al.2026ICLR 2026Workshop
Discovering Bäcklund Transformations with PDE Foundation ModelsEloisa BentivegnaTong Luo2026ICLR 2026Workshop