Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Program-as-Weights compiles natural-language specs into compact local neural adapters that match large-model prompting with far less memory and faster offline execution.

Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published Jul 2, 2026 · 0 citations · ▲ 307 on Hugging Face · Code ★ 359

MoCo: A One-Stop Shop for Model Collaboration Research

MoCo unifies 26 model collaboration methods and 25 benchmarks to show collaboration outperforms single models in 61% of settings by up to 25.8%.

Shangbin Feng, Yuyang Bai, Ziyuan Yang, Yike Wang and 16 more

Published Jan 29, 2026 · 0 citations · Code ★ 63

KDM1A promotes tumor cell invasion by silencing TIMP3 in non-small cell lung cancer cells

KDM1A promotes non-small cell lung cancer metastasis by demethylating H3K4me2 to silence TIMP3, activating MMP2 and JNK to drive invasion.

Lingzhi Kong, Peng Zhang, Wang Li, Yan Yang and 11 more

Published Apr 2, 2016 · 47 citations

Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners

Botos Csaba, Sreejan Kumar, Austin T D Andrews, Laurence T Hunt and 5 more

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

Temporal Smoothness Constraints on Efficient Neurobiological Codes Imply Temporal Specialization

John Vastola, Samuel J Gershman

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

Express Language Modeling

Albert Gong, Annabelle M Carrell, Raaz Dwivedi, Lester Mackey

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

A Solvable Model of Chain-of-Thought in In-Context Learning

Kaito Takanami, Cengiz Pehlevan

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

Render Structure Uncertainty for HTML Repair in MLLM-based UI-to-Code Generation

Haoran Ma, Jiechao Gao, Shisong Tang, bing han and 2 more

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

Multigroup Fairness and Omniprediction: Separations and Equivalences

Sílvia Casacuberta, Parikshit Gopalan, Varun Kanade, Omer Reingold and 2 more

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

Reading Positional Coupling in Transformers with Diffusion Scores

Savik Kinger, Johannes Bertram, Luciano Dyballa, Andy Keller and 1 more

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

AudioAgentBench: Evaluating Multi-Turn Voice Agents on Real-World Tasks

Gardenia Liu, Yi-Hao Peng, Kamryn Ohly, Oliver Johansson and 3 more

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

Text-side fragility in contrastive vision-language retrieval

Yanyu Lei

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

Hindsight Relabeling is All You Need for Reach-Avoid Learning

Kevin Li, Marinka Zitnik

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

The Cost of Symmetry: Universality and Hardness for Permutation-Invariant Neural Networks

Dashiell Bhattacharyya

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

Diagnosing Math-Reasoning Failure Structure with Milestone Oracles

Zhuohan Wang, Haoran Ma, Tianyu Wu, Yuanlin Duan and 2 more

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

Computational Dynamic Mechanism Design

Sadie Zhao, Amy Greenwald, Yanchen Jiang, Denizalp Goktas and 1 more

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

Irreducible Supervision Enables Compositional Generalization in Post-Training

Ellen Ma, Nikhil Anand

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

Strategic Causal Policy Learning: Welfare, Safety, and Fairness Thresholds

Suhwan Bong

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

Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal Supervision

Arya Tschand, Kesavan Ramakrishnan, Alexander Ingare, Simon Guo and 5 more

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

ProgramBench: Can Language Models Rebuild Programs From Scratch?

John Yang, Kilian Lieret, Jeffrey Ma, Parth Thakkar and 8 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

Iterative Gumbel Planning for Continuous Control

Shaohuai Liu, Weirui Ye, Yilun Du, Le Xie

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

Weird Generalization from Narrow Finetuning: Persona Shifts and Inductive Backdoors

Jan Betley, Jorio Cocola, Dylan Feng, James Chua and 3 more

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

StereoPep: Do Molecular Models Understand Stereochemistry? A Benchmark on Synthetic Diastereomeric Peptides

Michael Desgagné, Amirabbas Kazeminia, Kübra Kaygisiz, Bradley Pentelute and 1 more

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

Aligning AI Teams

Siddarth Srinivasan, Morgan J Matthews, Jascha Sohl-Dickstein, Erik Jones

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

A latent control model for realistic rodent motion

Aidan Sirbu, Charles Y Zhang, Yuanjia Yang, Bence Olveczky and 2 more

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

Gaeta-Lie Neural SDEs: Symmetry-Regularized Learning of Stochastic Dynamics

Shida Liu, Sumit Sinha, L Mahadevan

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

Large language models can not and should not be banned from peer review

Anat Kleiman, Gustaf Ahdritz

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

Memory is Not Search: Towards Proactive, Lifelong Memory in AI

Will Xiao, Sanket Deshpande, Guha Mahesh, Spandan Madan and 1 more

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

Claude Coke: Prevent Automated Crime by Agents

Gabor Hollbeck, Baran Peters, Alexander von Recum, Jan Granacher and 3 more

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

Algorithmic Impact Reveals the Hidden Structure of Alignment

Zachary Wojtowicz, Michelle Si, Finale Doshi-Velez, Ariel Procaccia

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

Settling Pure Differentially Private Covariance Estimation

Tommaso d’Orsi, Gleb Novikov, Walter McKelvie

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

A Matter of Interest: Understanding Interestingness Judgments of Math Problems in Humans and Language Models

Shubhra Mishra, Yuka Machino, Gabriel Poesia, Albert Q. Jiang and 8 more

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

Auditing Evidence Framing at NeurIPS: A Decade-Scale Study of Accepted Papers

Jason Godfrey

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

Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation

Haoran Ma, Linxiao Li, Chenyue Wang, Haochen Sui and 1 more

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

Toward Executable Multi-framework Front-end Code Generation with Self-Correction

Linxiao Li, Haoran Ma, Chenyue Wang, Jiaye Lin and 2 more

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

Learning What's Real: Disentangling Signals and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics

Pablo Mercader-Perez, Carolina Cuesta Lazaro, Daniel Muthukrishna, Jeroen Audenaert and 4 more

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

Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling

Tong Ding, Caiwei Tian, Dongmin Bang, Ming Yang Lu and 5 more

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

Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima

John Vastola, Ann Huang, Satpreet Harcharan Singh, Samuel J Gershman and 1 more

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

Finetuning with Sampling: Make SFT Generalize, Not Forget

Aayush Karan, Sitan Chen, Yilun Du

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

Unified Generative-Predictive Modeling for 4D Scene Understanding

Amani Kiruga, Zhiyi Li, Ruojin Cai, Hansen Lillemark and 3 more

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

Provably Efficient Representation Learning for Low-Rank CMDPs

Kaixuan Liu, GUOJUN XIONG, Shengpu Tang, Wanyun Si and 1 more

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

A Unified Spectral Theory of Multimodal Losses

Yu-Ang Cheng, Sixuan Chen, Zhouyang Lu, Xizheng Yu and 2 more

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

Model-Based Online Decision Making via Generative Trajectory Planning

Haldun Balim, Yilun Du, Na Li

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

Test-time Scaling of Diffusions with Flow Maps

Flow Map Trajectory Tilting uses flow maps to enable principled diffusion test-time scaling with reward gradients, improving reward ascent and enabling complex image editing via vision-language models.

Amirmojtaba Sabour, Michael Albergo, Carles Domingo i Enrich, Nicholas Boffi and 3 more

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

Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents

ADWM estimates LLM agent performance offline via a latent diffusion world model that alternates step-by-step with the policy, avoiding online interaction errors.

Kaixuan Liu, GUOJUN XIONG, Weinan Zhang, Shengpu Tang

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

LoopRPT: Reinforcement Pre-Training for Looped Language Models

LoopRPT applies reinforcement pre-training to looped language models by assigning rewards to latent reasoning steps, improving per-step quality and accuracy-computation trade-offs.

Guo Tang, Shixin Jiang, Heng Chang, Zihan Zhang and 6 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026 · ▲ 16 on Hugging Face

AI GAMESTORE: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games

AI GameStore proposes evaluating general intelligence via scalable synthesis of human games, finding frontier vision-language models score under 10% of human averages on most generated games.

Lance Ying, Ryan Truong, Prafull Sharma, Kaiya Zhao and 8 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 9 on Hugging Face

Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves

A Hilbert bundle convolutional framework defines HilbNets for infinite-dimensional manifold signals, proving discrete versions converge to continuous architectures and transfer across samplings.

Kartik Tandon, Julian J Gould, Tanishq Bhatia, Francesca Dominici and 2 more

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

MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models

MedKIT evaluates medical LLM knowledge integration via clinical updates, revealing strong recall but limited relational, compositional, and operational generalization across 12 strategies.

Lukas Thede, Yash Kumar, David Chen, Danielle Bitterman and 3 more

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

Learning to Persuade a Biased Receiver

Proposes safe exploration to learn a receiver's unknown belief bias via signaling, achieving optimal O(log log T) regret by exploiting asymmetric probing costs.

Yuqi Pan, Sadie Zhao, Milind Tambe, Yiling Chen

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

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent

A representation-readout decomposition attributes grokking and double descent to competing encoder and classifier dynamics, showing delayed generalization stems from gradual representation learning rather than lazy-to-rich transitions.

Chi-Ning Chou, Oscar Uzdelewicz, Neng-Chun Chiu, Yao-Yuan Yang and 1 more

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

Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods

Heavy ball and ASGD face compute-efficiency versus serial-runtime tradeoffs in linear regression, with heavy ball extending SGD's efficient batch window by up to √κ and ASGD trading small-batch efficiency for runtime on fast-decaying spectra.

Depen Morwani, Alexandru Meterez, Pranav Nair, Sham Kakade

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

Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance

An inference-time, model-agnostic method uses transformation equivariance to estimate uncertainty in pretrained registration networks, with maps correlating to errors.

Lin Tian, Xiaoling Hu, Juan Eugenio Iglesias

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

MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence

MedVIGIL evaluates medical vision-language models under broken visual evidence via clinician-supervised probes, revealing a 14.1-point gap between top models and radiologist reliability.

Hanqi Jiang, Junhao Chen, Yi Pan, Lifeng Chen and 9 more

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

Social Choice Foundations for Simulation-Augmented Generation

SAGE formalizes efficient inference-time viewpoint simulation via metric proportional justified representation, proving small simulated pools and dynamic routing preserve approximate proportional representation for contentious queries.

Sonja Kraiczy, Smitha Milli, Ratip Emin Berker, Avinandan Bose and 5 more

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

DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments

DARTS sequentially acquires prognostic covariates within budget constraints to minimize variance while preserving valid causal inference coverage.

Kateryna Husar, Alexander Volfovsky

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

Scaling Reward Modeling without Human Supervision

Unsupervised reward modeling via web document prefix-suffix preference learning improves RewardBench accuracy up to 7.7 points and matches supervised baselines without human annotations.

Jingxuan Fan, Yueying Li, Zhenting Qi, Dinghuai Zhang and 3 more

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

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

A decentralized agent economy using auctions and economic selection emerges multi-step reasoning and outperforms monolithic baselines without centralized coordination.

Zhenting Qi, Ao Qu, Huangyuan Su, Chenyu Wang and 12 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 10 on Hugging Face · Code ★ 59

Fisher Decorator: Refining Flow Policy via A Local Transport Map

Fisher Decorator refines flow policies via local transport maps and Fisher-metric anisotropic optimization to fix isotropic approximation errors in offline RL.

Xiaoyuan Cheng, Haoyu Wang, Wenxuan Yuan, Ziyan Wang and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · Code ★ 26

How Post-Training Shapes Biological Reasoning Models

Continued pre-training aligns biological language, supervised fine-tuning improves in-domain but harms out-of-domain reasoning, and reinforcement learning recovers generalization when rewards align.

Lukas Fesser, Hanlin Zhang, Michelle M Li, Eric Wang and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 3 on Hugging Face

STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations

STRAND predicts single-cell transcriptional responses to perturbations by conditioning on regulatory DNA sequence, enabling zero-shot inference across ~95% of the genome with improved discrimination and transfer performance.

Boyang Fu, Sameer Gabbita, George Dasoulas, xiang lin and 4 more

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

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

AutoScientists is a decentralized AI team that self-organizes around promising hypotheses, critiques proposals, and shares failures to improve long-running scientific experiments across biomedical, language model, and protein tasks.

Shanghua Gao, Ada Fang, Marinka Zitnik

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

Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model

Optimal LR schedules for a solvable random feature model reveal easy-phase polynomial decay and hard-phase warmup-stable-decay regimes that improve scaling over constant or power-law schedules, with momentum and batch ramps further enhancing wall-clock time.

Blake Bordelon, Francesco Mori

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

LLM Active Alignment: A Nash Equilibrium Perspective

A game-theoretic framework predicts and steers LLM populations via Nash equilibrium analysis, deriving closed-form alignments that prevent political exclusion and guide socially desirable outcomes.

Tonghan Wang, Yuqi Pan, Xinyi Yang, Xinrui Song and 3 more

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

World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories

World Motion Models unify dynamic 3D entities via sparse SE(3) trajectories and flow-matching, enabling any-to-any conditioning across prediction, control, and retargeting tasks.

Jiahui Lei, Qianqian Wang, Trevor Darrell, Angjoo Kanazawa

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

Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy

For binary hypothesis testing under local differential privacy, optimal mechanisms sort inputs by likelihood ratio, partition into contiguous blocks, and apply randomized response to block labels, enabling exact O(k³)-time computation via dynamic programming.

Elena Ghazi, Jawad Nasser, Flavio Calmon, Ibrahim Issa

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

LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators

LiFT generates high-resolution 3D medical images via inter-slice feature trajectories, achieving strong coherence with much lower inference cost.

Xinhe Zhang, Yuyang Zhang, Pengfei Jin, Arnau Marin-Llobet and 2 more

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

Mitigating Label Bias with Interpretable Rubric Embeddings

Rubric embeddings replace black-box features with expert-defined criteria to reduce label bias, cutting group disparities and improving cohort quality in admissions predictions.

Calvin Isley, Johann D. Gaebler, Sharad Goel

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

CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support

CoMMa is a decentralized multi-agent oncology framework using partitioned data, specialized fine-tuning, and deterministic contribution-aware aggregation to enable interpretable, privacy-preserving decision support across diverse clinical settings.

Yichen WU, Yujin Oh, Sangjoon Park, Kailong Fan and 9 more

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

Mechanisms of Misgeneralization in Physical Sequence Modeling

Standard generative sequence models suffer physical misgeneralization, where local trajectory errors propagate through physical measurements to shift aggregate distributions; a data deviation kernel predicts these shifts and guides mitigation.

Kento Nishi, Raphael Tang, Karun Kumar, Core Francisco Park and 1 more

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

Itô maps for any-step SDEs

The paper introduces Itô maps as any-step stochastic flow maps for SDEs that enable efficient single-pass future state prediction, posterior sampling, and inference-time control.

Zhengkai Pan, Peter Potaptchik, Wenxi Yao, Michael Albergo and 1 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens

Open-weight LLMs perform hidden multi-step reasoning over filler tokens that unsupervised hidden-state decoding recovers at 82-94% accuracy, showing monitorability requires internal traces.

Kaley Brauer, Claudio Mayrink Verdun, Samuel Marks

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

Embeddings for Preferences, Not Semantics

Text embeddings should encode preferential rather than semantic similarity for collective decisions; breaking nuisance correlation with synthetic training improves preference prediction across 11 deliberation datasets.

Carter Blair, Ariel Procaccia, Milind Tambe

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

Interleaved Head Attention

Interleaved Head Attention mixes attention heads via pseudo-heads to enable cross-head reasoning, cutting parameters on synthetic tasks and improving retrieval and math benchmarks over standard multi-head attention.

Sai Surya Duvvuri, Chanakya Ekbote, Rachit Bansal, Rishabh Tiwari and 5 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face

Bridging Compute- and Data-Optimal Pretraining

A unified compute-data scaling framework introduces token effectiveness to bridge data-rich and fixed-corpus regimes, showing diminishing returns and three operational regimes that render classical compute-optimal allocations suboptimal.

Tian Qin, Kimia Hamidieh, David Alvarez-Melis

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

Bernini: Latent Semantic Planning for Video Diffusion

Bernini unites MLLM semantic planning with DiT video rendering via latent ViT embeddings to achieve state-of-the-art video generation and editing.

Chenchen Liu, Junyi Chen, Lei Li, Lu Chi and 7 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 20 on Hugging Face

Efficient Transferable Optimal Transport via Min-Sliced Transport Plans

Min-sliced transport plans transfer optimized slicers across related distributions with theoretical guarantees and efficient minibatch scaling for matching and generation.

Xinran Liu, Elaheh Akbari, Rocio Diaz Martin, Navid NaderiAlizadeh and 1 more

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

Vermeer: Autoregressive generative modeling of microscopy predicts protein localization

Vermeer is an autoregressive generative model that predicts protein localization microscopy from sequences and cell landmarks, enabling zero-shot transfer across imaging conditions.

Sandeep Kambhampati, Eric Zimmermann, Emre Hayir, Kevin K Yang and 2 more

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

Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs

ProCauEval reveals LMMs perceive video but ignore it for causal reasoning, and ADPO reduces textual shortcuts via negative teacher alignment.

Jiafeng Liang, Zhihao Zhu, Zihan Zhang, Baoqi Ren and 6 more

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