Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems

SciUtopia is a closed-loop LLM simulation framework modeling entire academic ecosystems; it finds resubmission amplifies reviewer burden, cautious exploration balances impact and diversity, and inequality can emerge without cumulative funding advantage.

Yiqiao Jin, Yiyang Wang, Lucheng Fu, Bing He and 7 more

Published Oct 1, 2026 · 0 citations · ▲ 40 on Hugging Face · Code ★ 29

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

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models

Modality-aware neuron pruning removes target knowledge from multimodal LLMs by selectively pruning modality-specific neurons to enable precise unlearning.

Zheyuan Liu, Guangyao Dou, Xiangchi Yuan, Chunhui Zhang and 2 more

Published 2025 · 4 citations

Kernel Selection is Model Selection: A Unified Complexity-Penalised Approach for MMD Two-Sample Tests

Yijin Ni, Xiaoming Huo

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

Spectral Representations for Provably Robust Offline Meta-Reinforcement Learning from Bagged Rewards

Yashas Vaidya, Bo Dai

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

Coupling-Aware Reinforcement Learning for Co-Evolving Graph Games

Mina Kim, Guanghui Lan, Benoit Montreuil

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

Near-optimal Explainable $k$-means Clustering under $\ell_p$ Norm

Xinyuan Cao, Konstantin Makarychev, Ilias Papanikolaou, Liren Shan

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation

Biao Xiang, Ali Eshragh, Yuexing Li, Kai Wang

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

Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Process

Minh-Quan Le, Armand Comas, Alexandros Lattas, Stylianos Moschoglou and 6 more

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

Understanding Graph Self-Supervised Pre-training under Distribution Shifts: A Scaling Law Perspective

Bingheng Li, Shikun Liu, Yu Song, Jay Revolinsky and 4 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation

Zhixu Li, Keqian Tang, Litian Gong, Jingyu Yao and 6 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

MICE: Multi-animal Interaction Context Encoder — A Hierarchical Foundation Model for Mouse Behavior

Yen-Shuo Su, Weihan Li, Anqi Wu

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

When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

Runxuan Tang, Haoyu Gao, Yuyan Ding, Junyi Yao and 3 more

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

DBPS: Doob-Bridge Posterior Sampler with Balanced Endpoint-Population Control for Unpaired Neurodegenerative Pathology Transport

Xinyu Guo, Jiajia Xie, Xin He, Christophe Ye and 3 more

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

FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices

Jonathan McCart, Pranav Deevi, Mehdi Azabou, Nanda H Krishna and 4 more

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

Beyond Task Success: Probing Cognitive Primitives in Web Agents

Xunjian Yin, Tianchen Guan, Jinao Wang, Weili Cao and 7 more

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

Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation

Onur Selim Kilic, Afra Nawar, Cem O Yaldiz, Michael J Cho and 5 more

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

Online Control with Multiple Sensors

Matthew Faw, Siva Theja Maguluri

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

FedCF: Fair Federated Conformal Prediction

Anutam Srinivasan, Aditya T. Vadlamani, Amin Meghrazi, Srinivasan Parthasarathy

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

PhysAgentGym: Free Physical-Law Verifiers for Training Small Code-Reasoning Agents

Lama Moukheiber

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

Sparse Multimodal Switching State-Space Models for Regime-Dependent Neural Connectivity under Partial Observations

Rahul K Sharma, Feng Liu, Xiaochen Xian

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Learning Actionable Information Landscapes for Multimodal Active Sensing in Hawkmoths

Abdelrahman Sharafeldin, Yaqing Wang, Simon Sponberg, Hannah Choi

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

RnR: a meta-solver for causal discovery in undersampled time series data

Mohammadsajad Abavisani, Kseniya Solovyeva, David Danks, Vince D. Calhoun and 1 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

EpiPivot: Learning to Control the Simplex Method under Epistemic Uncertainty

Guantao Zhao, Mahdi Noorizadegan, Shihao Yang, Nicoleta Serban

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Masked Sobolev Training for Feasibility-Reliable Optimization Proxies

Andrew ROSEMBERG, Joaquim Dias Garcia, Russell Bent, Pascal Van Hentenryck

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

When Expert Disagreement Hurts: Auditing Prestige-Sensitive Revision in LLM Decision Pipelines

Yupeng Tang, Mingfeng Lin

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

OpenBrain: An Auditable Generated-Label Release for Whole-Brain MRI Parcellation

Qizhen Lan, Yu-Chun Hsu, YUXIANG WEI, Lijing Zhu and 4 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks

Jiyi Wang, Chenxiao Yang, Yujia Zhao, Jingzhao Zhang and 1 more

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

How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study

Junran Wang, Xinjie Shen, Zehao Jin, Pan Li

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

On the Efficiency of Structured Pruning in Small Language Model Pretraining

Yixiao Li, Xianzhi Du, AJAY JAISWAL, Tao Lei and 3 more

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

Debiasing Sketched Ridge Regression: A Functional Estimation Perspective

Yucong Liu, Florian Schäfer

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Simultaneous Individual, Group and Multigroup Fairness in Set Covering Problems

Sharmila Duppala, Nathaniel Grammel, Tyler He, Aravind Srinivasan

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

Hearing is Believing? Evaluating and Analyzing Audio Language Model Sycophancy with SYAUDIO

Junchi Yao, Lokranjan Lakshmikanthan, Annie Zhao, Danielle Zhao and 4 more

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

Decision-Focused Learning in MDPs: An Occupancy Measure Approach

Zihao Zhao, Ashwath K Karunakaram, Ali Eshragh, Yuexing Li and 1 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Geometry-Aware Representation Denoising for Multi-view Image Restoration and 3D Reconstruction

Jin Hyeon Kim, Jaeeun Lee, Claire Kim, Kyoungjin Oh and 8 more

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

Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions

Bhavini Jeloka, Yue Guan, Panagiotis Tsiotras

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model

SGD learns linear spurious correlations exponentially faster than XOR signals in two-layer ReLU networks, with dynamics that suppress true feature learning.

Tyler LaBonte, Vidya Muthukumar

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

Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows

Parallel-Synthesis lets LLM synthesizers consume parallel agents' KV caches directly via a cache mapper and adapter, matching text synthesis on seven of nine benchmarks while cutting time-to-first-token by 2.5x-11x.

Shikun Liu, Mufei Li, Dongqi Fu, Haoyu Wang and 4 more

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

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

AgentArk distills multi-agent reasoning into a single LLM via hierarchical strategies, achieving multi-agent performance with single-agent efficiency.

Yinyi Luo, Yiqiao Jin, Weichen Yu, Mengqi Zhang and 5 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 8 on Hugging Face · Code ★ 216

Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity

Transformers approximate α-Hölder functions via softmax partition of unity with two encoder blocks, achieving near minimax-optimal generalization rates.

Zhongjie Shi, Wenjing Liao

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

Global Convergence of Four-Layer Matrix Factorization under Random Initialization

Gradient descent globally converges for randomly initialized four-layer matrix factorization with balanced regularization, avoiding saddles in polynomial time.

Minrui Luo, Weihang Xu, Xiang Gao, Maryam Fazel and 1 more

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

K9-Bench: Evaluating Multimodal LLMs on Canine-Centric Videos

K9-Bench evaluates multimodal LLMs on dog videos via 5,000 QA pairs and finds limited zero-shot reasoning over long-horizon canine interactions.

Khush Attarde, Yusuf Ali, Megha Thukral, Divye Bhutani and 2 more

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

Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis

SNAP uses a pose-conditioned local decoder and latent-space reconstruction objective for self-supervised geometric representation learning via novel view synthesis, yielding transferable multi-view features competitive with supervised methods.

Keerthi Kaashyap, Dennis Anthony, Akshay Krishnan, Nhi Nguyen and 4 more

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

Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control

LA-LQR applies reduced-order linear optimal control to steer video generation activations via anticipative feedback, reducing unsafe outputs while preserving visual quality.

Jihoon Hong, Alice Chan, Qiyue Dai, Julian Skifstad and 1 more

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

Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models

Flow Mismatching detects anomalies via velocity discrepancies between normal flow dynamics and geometric paths to test images, yielding pixel heatmaps and image scores without test-time optimization and achieving state-of-the-art results.

Shengzhe Chen, Mehrdad Moradi, Kamran Paynabar, Hao Yan

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning

CoFi separates global structure formation from local refinement via coarse scaffolds, improving long-horizon compositional diffusion coherence with 2-8x fewer denoiser evaluations.

Byoungwoo Park, Utkarsh Mishra, Jaemoo Choi, Juho Lee and 1 more

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

Faster Rates For Federated Variational Inequalities

Refined analysis and a new LIPPAX algorithm improve federated stochastic variational inequality convergence rates and reduce client drift.

Guanghui Wang, Satyen Kale

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

FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance

FLAG augments states with flow latents to localize sampling and prevent importance weight collapse, enabling scalable high-dimensional expressive MaxEnt-RL policies with state-of-the-art performance.

Sungha Kim, Gawon Lee, Jusuk Lee, Jonghae Park and 2 more

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

Trust Region Continual Learning as an Implicit Meta-Learner

Trust region continual learning merges generative replay with Fisher-metric trust regions to implicitly meta-learn rapid task reconvergence without explicit bilevel optimization, outperforming replay and regularization baselines.

Zekun Wang, Anant Gupta, Christopher MacLellan

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

Beyond Maximum Likelihood: Variational Inequality Estimation for Generalized Linear Models

A variational-inequality framework estimates generalized linear models via equilibrium conditions, yielding finite-sample bounds, asymptotic normality, and improved stability over maximum likelihood for non-canonical links.

Linglingzhi Zhu, Jonghyeok Lee, Yao Xie

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

Continuous Diffusion Scales Competitively with Discrete Diffusion for Language

RePlaid, a continuous diffusion language model aligned with modern discrete architectures, achieves scaling laws rivaling discrete diffusion and sets a continuous diffusion perplexity record of 22.1 on OpenWebText.

Zhihan Yang, Wei Guo, Shuibai Zhang, Subham Sahoo and 4 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling

LEMON-ZEST uses evolution-informed tokenization to embed domain-level biological priors directly into protein language models. Its 200M-parameter LEMON model outperforms 600M to 3B parameter models on remote homology detection despite training on a single H100 GPU for one week. Evolution-informed to

Biswajit Banerjee, Claudia Alvarez Carreno, Anton S Petrov

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

MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory

Multimodal AI agents retain forgotten facts via implicit visual cues, with MemLeak showing 12% image-based recovery and content-aware deletion reducing residuals to 2%.

Kuan Wang, Chao Zhang

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

RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms

RepoLaunch automates cross-language repository builds and testing, achieving 78% build success and enabling fully automated SWE dataset pipelines.

Kenan Li, Rongzhi Li, Linghao Zhang, Qirui Jin and 16 more

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

LEVDA: Latent Ensemble Variational Data Assimilation via Differentiable Dynamics

LEVDA is a latent ensemble variational smoother using differentiable neural dynamics to assimilate sparse irregular observations without adjoint models, improving accuracy and uncertainty quantification over baselines.

Phillip Si, Peng Chen

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

Soft Token Alignment for Cross-Lingual Reasoning

SOLAR aligns soft-token representations across languages during supervised fine-tuning to improve multilingual reasoning consistency, boosting accuracy up to 17.7 points with largest gains on low-resource languages.

Ivy He, Jungsoo Park, Wei "Coco" Xu, Alan Ritter

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

Bounding Global and Local Compression Error of Signal Parameterizations

A framework predicts reconstruction error of compressive signal parameterizations via scaled differences between model predictions at different compression levels without ground truth. It yields non-asymptotic, signal-specific bounds that closely track global errors and local error heatmaps across i

Quang Luong Nhat Nguyen, Sara Fridovich-Keil

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

Conditional Optimal Bridge for Riemannian Activation Steering

Cobras casts activation steering as a Riemannian Schrödinger Bridge to derive a principled, query-adaptive log-density-ratio objective that improves alignment and avoids out-of-distribution degradation.

Seyed Arshan Dalili, Ajay Narayanan Sridhar, Vijaykrishnan Narayanan, Mehrdad Mahdavi

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

Proposed correlation-aware contextual bandit algorithms use coupled and decoupled surrogate rewards to improve LLM routing efficiency and robustness.

Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi, Vijaykrishnan Narayanan

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

CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series

CAST is a causal successor operator for distribution-valued time series that preserves the simplex via transport, avoiding transition-kernel aliasing to achieve top ranks across 11 benchmarks.

Jiecheng Lu, Jieqi Di, Runhua Wu, Yuwei Zhou

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

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

DynaFLIP pre-trains dynamics-aware visual encoders via image-language-3D flow alignment, boosting robot manipulation generalization by up to 22.5%.

Jusuk Lee, Seungjae Lee, Jonghun Shin, Hoseong Jung and 5 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 9 on Hugging Face

On the Error Correcting Effects of Stochasticity in Discrete Diffusion

Discrete diffusion stochasticity trades convergence speed against error correction via redundant transitions, and DCRS injects controlled randomness to improve low-step sampling efficiency.

William Yuan, Sungwon Jeong, Amirali Aghazadeh

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

Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs

A synthetic framework with ParallelEvents and Synapse evaluates and updates LLM knowledge via simulated future worlds, improving insertion by 14.23%.

Jonathan Zheng, Zirui Shao, Alan Ritter, Wei "Coco" Xu

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

Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning

BOOST uses bilevel optimization to learn trajectory weights from held-out validation, improving multi-turn LLM fine-tuning by upweighting high-quality synthetic data aligned with real distributions.

Shresth Verma, Mauricio Tec, Cheol Woo Kim, Kai Wang and 1 more

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

Neural Harmonic Measure Operator

NHMO parameterizes harmonic measure via a boundary kernel supervised by Walk-on-Spheres samples to solve elliptic PDEs on variable-shape domains without retraining. It extends to Poisson via source decomposition and outperforms prior baselines on 3D variable-shape benchmarks.

Jinjin He, Sinan Wang, Yuchen Sun, Bo Zhu

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces

Actor-accelerated PDA learns a policy network to approximate PDA optimization subproblems, speeding up continuous-action reinforcement learning while preserving convergence guarantees and outperforming PPO.

Ji Gao, Caleb Ju, Guanghui Lan, Zhaohui Tong

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

Attack Selection In Agentic AI Control Evaluations Meaningfully Decreases Safety

Strategic attack selection via start and stop policies substantially lowers measured AI control safety without changing attack capability, reducing safety by up to 28 percentage points and yielding overly optimistic estimates.

Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad, Joachim Schaeffer and 2 more

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

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention

FLAS learns a concept-conditioned flow field for multi-step activation steering that outperforms prompting on AxBench without per-concept tuning.

Zehao Jin, Ruixuan Deng, Junran Wang, Xinjie Shen and 1 more

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