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

Decentralized Q-Learning in Markov Potential Games

Onur Ünlü, Eilyan Bitar, Francesca Parise

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

Never Go Full Batch: Stochastic TMLE for Large-Scale Debiased Inference

Diyang Li, Fei Wang, Kyra Gan

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

Efficient Fine-Tuning for Structured Sparsity Under Group Repartitioning

Diyang Li

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

Regularization Paths for Continuous DAG Learning

Diyang Li, Fei Wang, Kyra Gan

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 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

On-Policy Hindsight Distillation for Early Risk Prediction

Qiannan Zhang, Fei Wang

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

AgentSSL: Can MLE Agents Leverage Unlabeled Data?

Akanksha Sarkar, Ethan Lin, Ziang Liu, Kristin Branson and 1 more

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

A Model of Diverse Sampling from Language Models

Manuel Prada-Corral, Yahya Emara, Timothy O'Donnell, Ryan Cotterell and 1 more

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

The Price of Locality: Why Forward-Forward Underperforms Backpropagation?

Zhaoxian Wu, Haichuan Liu, Tianyi Chen

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

Can 4D Foundation Models Remember?

Guangzhao He, Hadar Averbuch-Elor, Wei-Chiu Ma

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

Unsupervised Concept Discovery with Dirichlet Concept Diffusion Models

Yuchong Geng, Ao Tang

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

Refactoring Code Through Library Design

Žiga Kovačič, Justin Chiu, Celine Lee, Wenting Zhao and 1 more

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

Regret-Optimal Wasserstein-Robust Regression

Sloan Nietert, Daniel Kuhn

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

Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attributions

Toni Liu, Baran Zadeoğlu, Nicolas Boulle, Raphaël Sarfati and 2 more

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

TrunkFish: Making Model Width Incrementally Refinable

Owen M Dugan, Liam Dugan, Aaryan Singhal, Christopher De Sa and 1 more

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

The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks

Shuo Wen, Beixi Du, Edwin Meriaux, Junming Shi and 4 more

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

Autonomous Driving Research Requires a Community-Driven Data Paradigm

Jinsu Yoo, Zanming Huang, Katie Luo, Zheda Mai and 4 more

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

Beyond the Full Slate: Evaluating MNL Algorithms on All Slates

Flavio Chierichetti, Mirko Giacchini, Ravi Kumar, Silvio Lattanzi and 3 more

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

Narrowing the Collaboration Gap, Probably

Mirah Shi, Marcel Hussing, Natalie Collina, Ira Globus-Harris and 2 more

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

Predicting the Needle in a Petabyte Scale Haystack: Open-Vocabulary Event Anticipation in Satellite Imagery

Lekha Revankar, Mikhail Klassen, creon levit, Ash Hoover and 2 more

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

Thompson Sampling using Prior-fitted Diffusion Transformers

Sihwa Park, Jingsen Zhu, Vinamr Jain, Sheng-Yen Chou and 1 more

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

K-PWM: Control-Oriented Structured World Models under Partial Observation

Santosh M Rajkumar, Sriram Narayanan, Samuel E Otto, Debdipta Goswami

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

Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models

Aniket Kriplani, Yiwen Zhang, Angelina Wang, Hadar Averbuch-Elor

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

Language Denoising Objectives Extend the Value of Limited Data

Justin Lovelace, Christian Belardi, Srivatsa R Kundurthy, Shriya Sudhakar and 1 more

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

Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

Ziang Liu, James J Kim, Yijia Dai, Jennifer Sun

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

Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers

Sofian Zalouk, Vincent Counathe, Paul Jünger, Daniel Cao and 3 more

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

Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding

CRS unites geometric road graphs with open vocabulary semantics to generate structured reasoning data, showing small models trained on few scenes surpass large vision-language models at structured road reasoning.

Lena Wild, Katie Luo, Marco Pavone

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

MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP

MulCLIP aligns images with long captions via multi-level token and patch strategies, improving fine-grained vision-language understanding without region proposals.

Chau Truong, Hieu Ta, Zhenzhen Liu, Dung Le

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

GauS: Differentiable Scheduling Optimization via Gaussian Reparameterization

GauS models operator scheduling via Gaussian reparameterization to capture time's ordinal nature, cutting optimization space and yielding Pareto-optimal results.

Yaohui Cai, Vesal Bakhtazad, CUNXI YU, Zhiru Zhang

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

Joint Learning of Hierarchical Neural Options and Abstract World Model

AgentOWL jointly learns hierarchical neural options and an abstract world model for sample-efficient skill acquisition, outperforming baselines on object-centric Atari games with fewer samples and stronger generalization.

Top Piriyakulkij, Wolfgang Lehrach, Kevin Ellis, Kevin Murphy

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

PhotoFlow: Agentic 3D Virtual Photography Missions

PhotoFlow uses a Director-Reviewer-Reflector agent for closed-loop camera search to generate language-conditioned virtual photographs in arbitrary 3D scenes, outperforming baselines on quality, alignment, and success rate.

Jiarui Guo, Haojia Wei, Yiming Zhang, Yifei Liu and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 24 on Hugging Face · Code ★ 43

RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping

RaZeR remaps redundant NVFP4 zero values via block scaling bits to improve LLM quantization accuracy, reducing perplexity loss by up to 34.6%.

Yuzong Chen, Xilai Dai, Jake Hyun, Chi-Chih Chang and 5 more

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

QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems

QUTCC trains a U-Net for spatially adaptive quantile regression and calibrates tighter pixel-valid uncertainty intervals via non-linear conformal scaling for imaging inverse problems.

Cassandra T Ye, Shamus Li, Tyler King, Kristina Monakhova

Sydney Poster Session 6, Thu, Dec 10, 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

Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry

A self-supervised encoder learns subject-specific fMRI embeddings from repeated brain responses, and unsupervised orthogonal rotations align them across subjects into a shared geometry, demonstrating approximately isometric cross-subject visual representations.

Pablo Marcos Manchón, Rishi Jha, Lluís Fuentemilla

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

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

CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves

CurveBench introduces a 756-image benchmark for hierarchical containment reasoning over nested Jordan curves, showing top models achieve only 19% accuracy on hard cases.

Amirreza Mohseni, Mona Mohammadi, Morteza Saghafian, Naser Talebizadeh Sardari

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026 · ▲ 8 on Hugging Face · Code ★ 1

Learning Distributions from Multiple Data Providers

Pointwise consistency requires a connected co-occurrence graph and PAC learning needs completeness, with optimal sample complexity ranging from nearly linear to quadratic.

Jon Kleinberg, Amin Saberi, Xizhi Tan, Grigoris Velegkas

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

MAdam: Metric-Aware Multi-Objective Adam

MAdam removes Adam's weighting and geometric mismatches in multi-objective optimization via a preference-conditioned curvature preconditioner, consistently improving results across tasks.

Fengbei Liu, Rachit Saluja, Sunwoo Kwak, Ruibo Wang and 4 more

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

mRNABench: A curated benchmark for mature mRNA property and function prediction

mRNABench benchmarks mature mRNA property predictions across 59 tasks and 135K experiments, revealing synergies between self-supervised objectives that yield a compact state-of-the-art Mamba model using 700x fewer parameters.

Ruian (Ian) Shi, Taykhoom Dalal, Philip Fradkin, Divya Koyyalagunta and 9 more

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

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Flash-dLLM accelerates diffusion LLM inference via I/O-aware fused KV caching and self-draft verification, achieving up to 11x speedups.

Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 37 on Hugging Face · Code ★ 18

Continuity Laws for Sequential Models

State-space sequential models vary in temporal continuity, with continuous behavior aligning to task structure and enabling efficient subsampling.

Annan Yu, Dongwei Lyu, N. Benjamin Erichson

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

A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse

Eventually consistent generators cannot generate high-ranked strings before deadlines, but vanishing hallucination rates enable timely superlinear-deadline coverage, which is impossible under linear deadlines.

Atul Ganju, Travis McVoy, Shaddin Dughmi, Shang-Hua Teng

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

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents

Agents encountering benign errors suffer "accidental meltdowns", unsafe behaviors like unauthorized reconnaissance, across 64.7% of error rollouts, often unreported.

Rishi Jha, Harold Triedman, Vitaly Shmatikov, Arkaprabha Bhattacharya

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

Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction

ZendoWorld evaluates AI agents on active visual rule induction and finds high prediction accuracy does not imply rule recovery, with VLM agents proposing near-uninformative experiments.

Sophia Koehler, Antonia Wüst, Inga Ibs, Top Piriyakulkij and 4 more

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

Learning Unbiased Permutations via Flow Matching

PermFlow uses conditional flow matching on permutation affine subspaces to learn unbiased multimodal distributions and recover all valid permutations under ambiguity.

Yimeng Min, Carla Gomes

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

Agent Security is a Systems Problem

Agent security requires systems-level invariants treating AI as untrusted, since model robustness alone cannot prevent real-world agent attacks.

Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha and 10 more

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

GARDO: Reinforcing Diffusion Models without Reward Hacking

GARDO selectively regularizes high-uncertainty diffusion samples and adaptively updates reference models to prevent reward hacking while preserving diversity and sample efficiency.

Haoran He, Yuxiao YE, Jie Liu, Jiajun Liang and 7 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 30 on Hugging Face · Code ★ 63

SceneAligner: 3D-Grounded Floorplan Localization in the Wild

SceneAligner localizes images in large-scale floorplans by aligning 3D-reconstructed density proxies via adapted 2D foundation model correspondences, improving accuracy with sparse inputs.

Junhyeong Cho, Ruojin Cai, Hadar Averbuch-Elor

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 5 on Hugging Face · Code ★ 33

Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks

A feasibility-preserving graph neural network replaces SDP solvers in exact Max-Cut branch-and-bound, cutting bounding costs up to 10.6× versus Mosek.

Hao Chen, Chendi Qian, Christopher Morris, Andrea Lodi and 1 more

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

BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation

BEAGLE is a neuro-symbolic framework that embeds self-regulated learning theory to simulate novice programming behaviors and resists competency bias, producing student traces indistinguishable from real data in human evaluation.

Hanchen D Wang, Clayton Cohn, Zifan Xu, Siyuan Guo and 2 more

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

Strategic Decision Focused Learning

Strategic decision-focused learning predicts exogenous states for multi-agent games where better accuracy can reduce equilibrium payoffs, requiring strategic-aware predictors.

Tinashe Handina, Yuehan Diao, Adam Wierman, Eric Mazumdar

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

Provably Reliable Classifier Guidance via Cross-Entropy Control

Controlling per-step cross-entropy bounds classifier guidance error, linking classifier training to diffusion sampling accuracy. Conditional KL divergence ε² yields O(d ε) guidance mean squared error under mild smoothness.

Sharan Sahu, Arisina Banerjee, Yuchen Wu

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