Anatomy-Preserving Unpaired Medical Image Translation via Shared Latent Anchoring

Zhilin Zou, Hieu Le, Saumya Gupta, Jingyi Xu and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Mixture of Probes: Learning with Privileged Modalities in Multimodal LLMs Through Probing

Dominick Reilly, Qiyu Wu, Hiromi Wakaki, Srijan Das and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Importance-Aware OBS Pruning for Diffusion Models

Importance-aware pruning for diffusion models uses spatial importance maps to retain parameters critical to semantically salient regions, preserving subject fidelity and structural correctness at high compression ratios.

Ba-Thinh Lam, Srijan Das, Hieu Le

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Learning to Generate Multiple Objects from Dense and Occluded Layouts

Layout-aware attention biases and amodal-balanced loss prevent instance ownership collapse, substantially improving object count accuracy in dense, occluded scenes.

Bach H Ngo, Ngo Tri, Hieu Le, Trung Nghia Le

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution

LoRIF exploits low-rank gradient structure to reduce storage and query I/O to O(c√D) and inverse Hessian memory to O(Dr), achieving up to 20× speedups over LoGRA at scale.

Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand

Conservative-Markdown Redirect-UCB Pricing achieves optimal Õ(T^{2/3}) regret for contextual dynamic pricing with agnostic non-Lipschitz demand, closing the prior regret gap.

Jianyu Xu, Yu-Xiang Wang

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026