works on

From the 1 of 33 linked papers with an AI index.

collaborators

33 papers

cs.CL2026

RecurrentGPT: Expressive Depth through Recurrent Modulation in Transformers

Amr Hegazy, Amr Alanwar, Mostafa Elhoushi

Scaling transformer language models creates an inherent tension between expressivity and memory efficiency. While unique weights across layers preserve functional specialization---…

cs.LG2026

Matrix Zonotopic Attention: A Context-Adaptive Value Projection for Set Transformers

Zhen Zhang, Amr Alanwar

Multi-head attention combines an input-dependent softmax routing with an input-independent linear value projection, so the per-sample operator mapping aggregated values to outputs…

cs.LG2026

Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty

Zhen Zhang, Amr Alanwar

Probabilistic prediction heads in neural networks typically output either a Gaussian mixture or a single conformal region. Neither separates the distinct sources of uncertainty oft…

cs.RO2026

Probabilistic Reachable-Action Verification of Visuomotor Policies via Set-Based Training

Yanliang Huang, Zhuocheng Zhang, Peng Xie +5

Reachability analysis for visuomotor policies is difficult because large visual encoders make end-to-end set propagation computationally expensive and excessively conservative. We…

cs.RO2026

Certifying Plans under Model Mismatch: A Trilemma for Reachability from Scarce Data

Yanliang Huang, Zhen Zhang, Ahmad Hafez +4

Sim-to-real policies are designed under nominal dynamics, but target-system trials may yield only a few isolated one-step transitions. We study pre-execution certification of a fix…

cs.RO2026

GNN-DIP: Neural Corridor Selection for Decomposition-Based Motion Planning

Peng Xie, Yanliang Huang, Wenyuan Wu +1

The paper introduces GNN-DIP, a method that uses a graph neural network to score portals in a cell adjacency graph, guiding corridor selection for decomposition-based motion planni…