EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

EvoDuet co-evolves solutions and web queries via a retrieval gate to boost LLM discovery gains up to 82.3% across optimization tasks.

Young-Jun Lee, Jinheon Baek, Soyeong Jeong, Minki Kang and 4 more

Published Sep 30, 2026 · 0 citations · ▲ 109 on Hugging Face · Code ★ 4

Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym

Proactive LLM agents need joint optimization of task capability, temporal compute allocation, and user trust, with Proactivity-Gym exposing evaluation gaps and human preference for unobtrusive assistance.

Jio Oh, Seunghyun Do, Youngjun Lee, Steven Euijong Whang and 1 more

Published Sep 29, 2026 · 0 citations · ▲ 22 on Hugging Face

Lower-Level Agnostic Bilevel Optimization

Peiwen Qiu, Prashant Khanduri, Jia (Kevin) Liu

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

State Augmented Flows

Dwij Mehta, Arvind Renganathan, Vipin Kumar

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

Ensemble Selective Classification

Sinian Zhang, Chongwei Chen, Guanchen Li, Ju Sun

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

Aligning Language Models with Selective Prediction

RLSR aligns language models with selective prediction metrics via reinforcement learning, substantially improving risk-coverage trade-offs over baselines.

Gaoxiang Luo, Yifan Wu, Sinian Zhang, Aryan Deshwal and 1 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models

StreamPhy enables real-time streaming inference of high-dimensional physical fields from irregular sparse measurements via adaptive encoders and state-space updates, outperforming diffusion baselines by up to 48% accuracy and 20-100x speed.

Panqi Chen, Yifan Sun, Shikai Fang, Xiao Fu and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax

DarkVGGT uses physics-aware thermal modeling and geometry-shared routing to boost feed-forward 3D reconstruction in darkness without impairing daylight performance.

Minseong Kweon, Wenyuan Zhao, Nuo Chen, Lulin Liu and 5 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization

Subspace gradient orthogonalization unifies low-rank projection with spectral optimization into ZO-Muon, cutting zeroth-order queries by 75% versus MeZO while boosting accuracy on LLM and vision fine-tuning.

Yicheng Lang, Changsheng Wang, Yihua Zhang, Mingyi Hong and 3 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling

ANCRe learns residual connectivities from data to fix convergence gaps caused by fixed layouts, accelerating training of deep networks with under 1% overhead.

Yilang Zhang, Bingcong Li, Niao He, Georgios Giannakis

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction

UDT is a U-Net diffusion transformer using data-adaptive token merging for downsampling and upsampling that outperforms existing U-Net DiTs, achieves comparable performance to REPA, and reaches FID 1.35 with faster convergence.

Junno Yun, Yasar Utku Alcalar, Mehmet Akcakaya

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Meta$^n$: Recursive Self-Improvement through Emergent Depth

Meta^n fixes its meta-operation and recurses on growing inputs to build unbounded self-improving agent depth, outperforming prior agents across eight benchmark families including ARC-AGI-2.

Zae Myung Kim, Young-Jun Lee, Seungyeon Jwa, Dongyeop Kang

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 17 on Hugging Face