logo
today local_bar
adaptive computation

4 papers across 3 sessions

Poster Session 1

2 papers
Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
#3600 · Anthony Fuller, Yousef Yassin, Junfeng Wen, Tarek Ibrahim, Daniel Kyrollos, James Green, Evan Shelhamer

We introduce a selector-extractor framework that extracts high-res features without ever seeing full high-res images to save compute.
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
#5413 · Sangmin Bae, Yujin Kim, Reza Bayat, Sungnyun Kim, Jiyoun Ha, Tal Schuster, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Aaron Courville, Se-Young Yun

Poster Session 2

1 paper
Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
#3410 · Soyoung Yoon, Gyuwan Kim, Gyu-Hwung Cho, seung-won hwang

AcuRank adaptively reranks documents using uncertainty, improving ranking accuracy with fewer LLM calls.

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy
#2313 · Inkook Chun, Seungjae Lee, Michael Albergo, Saining Xie, Eric Vanden-Eijnden

A framework that dynamically adjusts computational resources for robot controllers based on real-time task difficulty, reducing computation time by 2.6-4.4× while maintaining success rates, using the Stochastic Interpolant (SI) framework.