Sharpening Tax in Post-Training

Post-training sharpens base model behaviors at the cost of solution coverage, introducing a quantifiable "Sharpening Tax"; a posterior-tempered group sampler reduces this tax while boosting accuracy.

Changdae Oh, Qi Zeng, Qi Qi, Andrey Zhmoginov and 6 more

Published Oct 1, 2026 · 0 citations · ▲ 102 on Hugging Face · Code ★ 25

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

HeteroFold enables prefill-free cross-family KV cache transfer between frozen heterogeneous LLM agents, accelerating 32K context transfer up to 10.7x while matching text-based multi-agent performance.

Vincent-Daniel Yun, Woosang Lim, Haneul Yoo, Sungjoo Yoo and 2 more

Published Sep 26, 2026 · 0 citations · ▲ 95 on Hugging Face · Code ★ 1

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

BDH-CQ combines in-context learning with recurrent latent reasoning, achieving 29.5% ARC-AGI-1 pass@2 at $0.0007 per task to set a new cost-efficiency frontier.

Björn Engdahl, Adrian Kosowski, Jan Chorowski, Zuzanna Stamirowska and 5 more

Published Aug 10, 2026 · 0 citations · ▲ 797 on Hugging Face · Code ★ 11,072

AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis

AskChem indexes 2.4M atomic chemistry claims with provenance for cross-paper synthesis, achieving 100% resolvable DOIs and highest citation density.

Bing Yan, Gregory Wolfe, Stefano Martiniani, Kyunghyun Cho

Published Jul 30, 2026 · 0 citations · ▲ 308 on Hugging Face · Code ★ 16

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

When One LLM Drools, Multi-LLM Collaboration Rules

Multi-LLM collaboration outperforms single LLM reasoning on tasks where individual models fail, demonstrating collective rule over solo drooling.

Shangbin Feng, Wenxuan Ding, Alisa Liu, Zifeng Wang and 9 more

Published 2026 · 1 citation

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration

Modular Pluralism plugs specialized community LMs into base LLMs to enable Overton, steerable, and distributional pluralistic alignment across diverse communities.

Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher and 3 more

Published 2024 · 15 citations

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

When do Prophets Profit in Prediction Markets?

Anri Gu, Nicole Kagan, Alec Sun, Jibang Wu and 1 more

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

On the Last-Iterate Convergence of Clipped Gradient Methods

Zijian Liu

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

Requential Coding: Measuring Model Compressibility by Coding Data Instead of Parameters

Shikai Qiu, Marc Finzi, Yujia Zheng, Kun Zhang and 1 more

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

Token-Conditional Expert Dropout: Implicit Regularization for Stable MoE Pretraining

Haili Wang

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

Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes

Ethan Baron, Alan Amin, Andrew Wilson

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

Decomposing Temporal and Job-Induced Dynamics for Probabilistic Computing Workload Forecasting via Graph-Conditioned Dual-Branch Diffusion

Baozhen Luo, Minbo Ma, Honglin Zhang, Yuan Yuan and 3 more

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

Reading, Not Thinking: Bridging the Modality Gap When Text Becomes Pixels

Kaiser Sun, Xiaochuang Yuan, Hongjun Liu, Chen Zhao and 3 more

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

Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries

Enpei Zhang, Feiyu Qu, Zheng Huang, Dawei Zhou and 2 more

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

Reasoning Pathologies in Large Language Models: A Diagnostic Perspective

Rohan Surana, Junda Wu, Sheldon Yu, Gagan Mundada and 5 more

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

The Geometry of Agent Skills: Non-Commutative Composition in Representation Space

Junda Wu, Yifan Wang, Zihan Huang, Xunyi Jiang and 5 more

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

Can LLMs explain themselves truthfully with code?

Nhi Nguyen, Shauli Ravfogel, Rajesh Ranganath

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

From Click Imitation to Transition Equivalence: Rethinking Supervision for GUI Agents

Zhiming Lin, Tianxiang Xu, zizhao zhang, Yixue Liu and 5 more

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

Beyond Ground Truth: Evaluating Non-Verifiable Reasoning in LLMs through Moral Robustness

Elizaveta Tennant, Benjamin Henke, Anita Keshmirian, Murray Shanahan and 4 more

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

Scaling Arbitrary Architectures and Optimizers with Automatic Parameterization

Shikai Qiu, Charlie Chen, Andres Potapczynski, Martin Marek and 1 more

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

Are Easier or Harder Examples Better? Rethinking Data Selection for Reward Models and Preference Optimization

Kevin Christian Wibisono, Aya Ismail, Pedro O. Pinheiro, Yixin Wang and 3 more

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

A Regularization-Based Approach to Public Belief State Search for Adversarial Games

Sobhan Mohammadpour, Samuel Sokota, Brandon Kaplowitz, Zico Kolter and 2 more

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

When Form Changes but Logic Doesn’t: Building Logic-invariant LLMs through Structures

Xuyuan Liu, Xinshuai Dong, Elynn Chen, Yujun Yan

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

Competing Event Models: Next Event Prediction Under Interventions

Yoav Wald, Xiang Gao, Sumit Chopra, Juho Lee and 1 more

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

IntegrityBench: Can LLMs Be Trusted as Co-Scientists? A Research Integrity Benchmark

Sai Sidhanth Manoharan Jayanthi, Yash Tripathi, Silu Sharma, Shivank Garg and 1 more

Sydney Poster Session 6, Thu, Dec 10, 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

Neural Circuit Architectural Priors for Rat Locomotion

Nikhil Bhattasali, Jaron Cui, Lerrel Pinto, Grace Lindsay

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

Linear approximations to HMM filtering

Andrew Mah, Joshua L Pughe-Sanford, Sarah Harvey, Alex Williams

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

On the Impact of Side-Information in Bandit Learning: More is Not Always Merrier

Ramakrishnan Krishnamurthy

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

Distributionally Robust Mixture-of-Experts Training

Xin Teng, Muxiao Li, Hongyi Wen

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

Probabilistic Recursive Reasoning

Junyeob Baek, Mingyu Jo, Minsu Kim, Mengye Ren and 2 more

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

Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel

Jayoung Ryu, Kyunghyun Cho, Romain Lopez

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

A Control-Theoretic Approximation to Predictive Coding Dynamics

Ryan Fayyazi, Kyle Daruwalla, Mitra Javadzadeh

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

Your Benchmark Is an Empirical Measure Over Difficulty

Yifan Sun, Naicheng Yu, Jiawen Gong, Jingyan Shen and 1 more

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

Whole-Body Compliant Control via Learned Force-Regulation Modules

Diego Aldarondo, Aadhithya Iyer, Daniel Giebisch, Nina Mortensen and 3 more

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

nnTrace: Detecting and Localizing Silent Bugs in Distributed Training

Haitian Jiang, Shaowei Zhu, Zhen Zhang, Zhenyu Song and 4 more

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

On Worst-Case Guarantees for Graph-Based Nearest-Neighbor Search

Majid Daliri, Mohammadreza Daneshvaramoli, Purna Dutta, Edo Liberty and 3 more

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

LSVD: Loss-Aware Low-Rank Approximation for Efficient Low-Precision Vision-Language Models

Haiyu Wang, Yutong Wang, Leshu Li, Yihui Ren and 1 more

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

Understanding Reasoning from Pretraining to Post-Training: Chess as a Controlled Testbed

Jingyan Shen, Ang Li, Salman Rahman, Yifan Sun and 3 more

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

Learning Neuronal Wiring Rules from Morphological Token Sequences

Sidharth Goel, Erdem Varol

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

Hierarchical World Models with Implicit Dynamics

Gaoyue Zhou, Yvonne Wu, Zichen Cui, Nicolas Ballas and 3 more

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

MLLMs Fail to Refuse when Using Tools Agentically

Rikiya Takehi, Ryo Hachiuma, Shaona Ghosh, Dan Zhao and 2 more

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

A Unified Merge Calculus for Learning-Rate Scaling on Neural Computation Graphs

Haosong Zhang, Wu Shenxi, Zhiyuan Che, Xi Chen and 2 more

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

ClusQuant: Mitigating Outliers with Clustering-Based Representations for Low-Precision LRMs

Xingyu Liu, Xiangyang Yin, Tianhua Xia, Haiyu Wang and 1 more

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

UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression

ziqi wang, Su Chen, Qiance Tang, Jieyu Lin and 3 more

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

Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension

George Andriopoulos, Zixuan Dong, Bimarsha Adhikari, Keith Ross

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

How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning

A stopgrad regression principle characterizes stationary points of stopgrad objectives and proves convergence to true flow maps while halving training memory.

Mark Goldstein, Max Shen, Zichu Wang, Aahlad Manas Puli and 1 more

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

From Isolated feature to Orbits:\\Discovering Music Concepts via Multi-SAE Alignment

Multi-SAE alignment with pitch-shifted pairs recovers structured feature orbits for chords, keys, and melodies in music models with minimal anchoring.

Liwei Lin, Gus Xia

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

Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation

RIG-BENCH evaluates reasoning-driven image generation across four cognitive domains, revealing that state-of-the-art models produce locally plausible but globally illogical outputs.

Yutong Liu, Nan Huang, Xu Cao, James Rehg

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

Norm Anchors Make Model Edits Last

Locate-and-Edit editing fails via a norm-feedback loop that exponentially amplifies weights; Norm-Anchor Scaling fixes it by anchoring norms to reference values, extending editing horizons 4x with minimal overhead.

Mingda Liu, Zhenghan Zhu, Ze‘an Miao, Katsuki Fujisawa

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

Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching

Condition-dependent source distributions for flow matching improve text-to-image generation via variance regularization and directional alignment, accelerating convergence up to 3x in FID.

Junwan Kim, Jiho Park, Seonghu Jeon, Seungryong Kim

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

Discrete Stochastic Localization for Non-autoregressive Generation

Discrete stochastic localization uses unit-sphere embeddings with SNR-invariant denoisers to enable flexible continuous-state non-autoregressive generation with improved fidelity and hybrid sampling.

Yunshu Wu, Jiayi Cheng, Longxuan YU, Partha Thakuria and 3 more

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

Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization

Epiplexity guides data selection and synthetic generation to improve out-of-distribution transfer by favoring structurally rich training data.

Ellen Su, Andres Potapczynski, Shikai Qiu, Edward Hughes and 1 more

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

RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space

RepFusion conditions a diffusion transformer on multimodal LLM outputs to denoise visual representations, outperforming comparable newly initialized denoisers.

Xichen Pan, Satya Narayan Shukla, Aashu Singh, Shlok K Mishra and 1 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 17 on Hugging Face

Exposing and Mitigating Temporal Attack in Deepfake Video Detection

SpInShield defends deepfake detectors against temporal spectral attacks by suppressing unstable spectral shortcuts and learning robust semantic motion cues, improving attack resilience by over 21 AUC points.

Zheyuan Gu, Minghao Shao, Zhen Wang, Keyu Mao and 6 more

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

Modelling Opinion Dynamics at Scale with Deep MARL

Deep MARL scales opinion dynamics to 1000 agents, finding high conformity in large networks reduces accuracy and promotes dishonesty, unlike small groups, revealing a mismatch with modern media.

Lukas Seier, Brandon Kaplowitz, Sebastian Towers, Richard M Bailey and 1 more

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

CruxBench: A Benchmark of Information Discovery

CruxBench evaluates LLM information discovery via Value of Information for decomposing forecasting problems into key subquestions, finding frontier models barely exceed random baselines.

Lina Piao, Amelia Hui Dai, Nick Merrill, Nadja Flechner and 2 more

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

Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks

Prospective bottom-up inputs via two-tap updates mitigate depth-dependent gradient attenuation in deep continuous-time recurrent networks, boosting RQF accuracy on Speech Commands and Path-X.

Shivang Rawat, Mirko Morello, Flaviano Morone, David Heeger

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

Two-Fidelity Best-Action Identification for Stochastic Minimax Tree

2FFS adaptively combines cheap biased heuristics and expensive accurate rollouts to identify best actions in stochastic minimax trees with fewer samples than baselines.

Peter Chen, Xi Chen

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 2 on Hugging Face

Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning

Creativity frames a frozen diffusion model as a Creator and an adaptive observer as an Appraiser, using meta-learning gradients to generate novel, quickly learnable concepts.

Mengye Ren

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

Learning Options for Compositional Motor Control with Adapter Banks

A shared recurrent core with residual adapter banks learns compositional motor skills via emergent low-rank dynamics, cutting generalization error versus multitask baselines by up to an order of magnitude.

Sreejan Kumar, Marcelo G Mattar, Lea Duncker

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

On the Convergence of Multicalibration Gradient Boosting

Multicalibration gradient boosting converges at O(1/sqrt(T)) with linear rates under smoothness, plus adaptive guarantees backed by experiments.

Daniel Haimovich, Fridolin Linder, Lorenzo Perini, Niek Tax and 1 more

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

RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering

RVR uses retrieve-verify-retrieve loops with verified documents to augment queries, improving multi-answer recall by at least 10% relative over baselines.

Deniz Qian, Hung-Ting Chen, Eunsol Choi

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

On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation

On-Policy Consistency Training improves LLM safety across sycophancy, jailbreaks, and safety awareness while avoiding the capability regressions of supervised fine-tuning.

Andy Q Han, Kristina Fujimoto, Avidan Shah, Kiet Nguyen and 4 more

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

Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models

LLMs exhibit confirmation bias by proposing confirming triples rather than falsifying hidden rules, reducing discovery rates, though prompting counterexample consideration improves success from 42% to 56%.

Ayush Rajesh Jhaveri, Anthony GX-Chen, Ilia Sucholutsky, Eunsol Choi

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

Computer Use at the Edge of the Statistical Precipice

A 1MB replay script outperforms frontier agents on static benchmarks because of flawed environment design and evaluation; the paper proposes PRISM principles, DigiWorld, and hierarchical bootstrap aggregation to fix both.

Pierluca D Oro, Sneha Silwal, William R Wong, Yuxuan Sun and 5 more

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

The Smart Buildings Control Suite: A Diverse Open Source Benchmark to Evaluate and Scale HVAC Control Policies for Sustainability

The Smart Buildings Control Suite is an open-source HVAC benchmark using multi-year data from 11 buildings and scalable simulators to test control policies across diverse climates and structures.

Judah Goldfeder, Victoria Dean, Zixin Jiang, Xuezheng Wang and 3 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference

This paper models parallel inference-time reasoning via particle filtering, deriving non-asymptotic guarantees and fundamental limits for sequential Monte Carlo with process reward models.

Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal and 3 more

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

DiscoverPhysics: Benchmarking LLMs for out-of-the-box scientific thinking

DiscoverPhysics benchmarks LLM agents on simulated worlds with non-standard physics, finding frontier models pass only half and fail at uncovering latent structure.

Lindsay Smith, Matt Sampson, Siddharth Mishra-Sharma, Peter Melchior and 3 more

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

The Stability of Online Algorithms in Performative Prediction

No-regret online algorithms unconditionally converge to mixed performatively stable equilibria via randomized martingale arguments, avoiding distribution-response assumptions and PPAD hardness.

Gabriele Farina, Juan C Perdomo

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 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

Improved Baselines with Representation Autoencoders

Using summed last-k encoder layers and combining RAE with REPA, RAEv2 achieves state-of-the-art gFID of 1.06 in 80 epochs with 10x faster convergence and free guidance.

Jaskirat Singh, Boyang Zheng, Zongze Wu, Richard Zhang and 2 more

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

AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals

AVSD separates cross-view consensus from privileged residuals in multi-view self-distillation to adaptively supervise reasoning models, improving math and code benchmarks over single-view methods and GRPO.

Duy Nguyen, Hanqi Xiao, Archiki Prasad, Zaid Khan and 6 more

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