Persona Dosing: Calibrated Activation Steering for Graded Trait Control

PersonaDose calibrates activation-steering controllers to control language-model persona traits by requested intensity, reducing targeting errors to 4.7-6.2 points across models.

Zehao Jin, Junran Wang, Ruixuan Deng, Jiahao Chen and 3 more

Published Sep 28, 2026 · 0 citations · ▲ 54 on Hugging Face

PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers

Eshed Gal, Moshe Eliasof, Eldad Haber

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

Short-Context Dominance: How Much Local Context Natural Language Actually Needs?

Vala Vakilian, Zimeng Wang, Ankit Rawat, Christos Thrampoulidis

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity

Nico Policzer, James Ho, Joseph Soo, Xin Tang

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

Routing as a Singular Reparameterization: A Closed-Form Pushforward Prior and Exact Bayesian Complexity in a Minimal Proxy

Ali Mehrabian, Mahdi Mazloum

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

RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models

Ruinan Jin, Xinting Liao, Hanlin Yu, Deval Pandya and 1 more

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

Beyond Real or Fake: A Dual-Channel Authenticity and Reasoning Protocol for Photographic Assessment

Xiaoxiao Li, Ruinan Jin, Lili Meng, Miaosen Wang and 2 more

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

Bet Imaginatively, not Historically in Independent-Data Sequential Testing

Nathaniel Xu, Feng Liu, Danica J. Sutherland

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

IDEA: Unwrapping Visual Black-box Models by Interaction Decomposition

Chaojie Ji, Jian Xu, He Zhang, Hongyan Wu and 2 more

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

Causal Gradient Steering: Exposing Shortcut Gradients by Destroying Causal Signal

Ahmed Radwan, Ahmad Abdel-Qader, Mahmoud Soliman, Omar Abdelaziz and 3 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

Learning Transferable Representations from Operating System Entities via Provenance Graph Distillation

Tristan Bilot, Xueyuan Han, Thomas Pasquier

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute

Ali Salamatian, Anthony Fuller, Pritam Sarkar, James Green and 2 more

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

RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud

Jinze Li, Xin Yang, Shuo Yang, Jinfeng Xu and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Mitigating Memorization Where It Happens

Xuanqi Zhang, HaoYang Shang, Xiaoxiao Li

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

Preserving Exploration for LLM Reasoning via Mean Order-Statistic Alignment

Ruotian Peng, Yi Ren, Long-Fei Li, Yandong Wen

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

In-Context Benign Overfitting: A Feature-Selection Model in Linear Regression ICL

Puneesh Deora, Bhavya Vasudeva, Christos Thrampoulidis

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

Learning to Continually Learn via Meta-learning Agentic Memory Designs

ALMA meta-learns executable memory designs for agentic systems, outperforming hand-crafted alternatives across sequential decision-making benchmarks.

Yiming Xiong, Shengran Hu, Jeff Clune

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 8 on Hugging Face · Code ★ 295

Preconditioned Flow Matching

Ill-conditioned intermediate covariances make flow matching regress low-variance directions slowly; preconditioning into isotropic space improves optimization and generation quality.

Shadab Ahamed, Eshed Gal, Md Shahriar Rahim Siddiqui, Simon Ghyselincks and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization

Exploiting spherical latent geometry yields nearly closed-form Bayesian optimization with 100x speedups and matching performance in generative discovery pipelines.

Donney Fan, Colin Doumont, Aleksandra Kalisz, Paul Duckworth and 3 more

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

SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws

Multiclass logistic regression learns Gaussian mixtures sequentially by class frequency, producing power-law risk phases and compute-optimal scaling laws.

Konstantinos Tsiolis, Denny Wu, Christos Thrampoulidis, Murat Erdogdu

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

A second order regret bound for NormalHedge

A NormalHedge variant achieves second-order ε-quantile regret O(sqrt(V_T log(V_T/ε))) for easy sequences via self-concordance analysis.

Yoav S Freund, Nicholas Harvey, Victor S. Portella, Yabing Qi and 1 more

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

CoRDS: Coreset-Based Representative and Diverse Selection for Streaming Video Understanding

CoRDS selects coreset subsets of key-value caches to cover accumulated visual history geometry, improving streaming video understanding with fixed memory budgets.

Ailar Mahdizadeh, Puria Azadi Moghadam, Muchen Li, Xiangteng He and 1 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Hyperagents

Hyperagents integrate editable task and meta agents to enable metacognitive self-modification, with DGM-H improving across domains and accumulating meta-level improvements.

Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster and 4 more

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

DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models

DDMS distills multi-view geometric knowledge into single-view models via discriminative ranking to produce 3D-consistent, locally distinctive foundational features preserving semantic structure.

Jeonggi Kwak, Sho Kagami, Yuki Ono, Kwang Moo Yi

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

MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup

MoME replaces fixed token memory entries with context-gated mixtures of slots to disambiguate polysemous tokens, improving sparse lookup performance across small-scale language model backbones with favorable scaling.

Muchen Li, Leonid Sigal, Renjie Liao

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 12 on Hugging Face · Code ★ 7

Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again

Multistage Defer Trees use sequential sparse decision trees to route most samples through interpretable rules before deferring to black boxes, matching ensemble accuracy with high interpretability.

Zakk Heile, Hayden McTavish, Margo Seltzer, Cynthia Rudin

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

OpenMedReason: Scientific Reasoning Supervision for Medical Vision–Language Models

OpenMedReason is a 450K-instance open medical reasoning dataset derived from scientific articles that improves LVLM diagnostic accuracy by 20% and enhances perception, knowledge, and reasoning.

Negin Baghbanzadeh, Pritam Sarkar, Michael Colacci, Abeer Badawi and 5 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Taking the Road Less Scheduled with Adaptive Polyak Steps

Adaptive Polyak step sizes for Schedule-Free SGD and Adam compute iteration-wise learning rates from losses and gradients, achieving anytime convergence without tuning base rates or horizons.

Dimitris Oikonomou, Matthew Buchholz, Yuen-Man Pun, Robert Gower and 1 more

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

Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems

Single-loop perturbed stochastic extragradient and optimistic gradient methods achieve last-iterate convergence for constrained convex-concave minimax problems with O(T^{-1/4}) and O(T^{-1/5}) rates.

Taoli Zheng, Jiajin Li, Anthony Man-Cho So

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