Receiver-Conditioned Latent Communication gives 94% CacheBack

CacheBack uses receiver-conditioned filtering of sender KV caches via attention weights to cut transferred state by 75%, boosting multi-agent accuracy by 14.7 points and reducing latency 3.2x versus text.

Maximillian Rossi, Prajwal Raghunath, Haoqing Xuan, Yusen Zhang and 1 more

Published Sep 25, 2026 · 0 citations · ▲ 11 on Hugging Face · Code ★ 6

Growing a Neural Network in Breadth, Depth, and Time

Eivinas Butkus, Kedar Garzón Gupta, Nikolaus Kriegeskorte

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

Nearly Optimal Attention Coresets

Alexandr Andoni, Eldar Kleiner, Edo Liberty

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

Forward Shapley Scoring for Non-Myopic Active Feature Acquisition

Guoliang Xu

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

Announced Breaks Separate Conformal Reliability from Frequency Calibration

Karl Li

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

MedVTok: A General-Purpose Medical Visual Tokenizer

Chenglong Ma, Yuanfeng Ji, Junzhi Ning, Jiyao Liu and 17 more

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

Counterfactual Debugging the World Model Transfer Gap

Mingxuan Li, Kai-Zhan Lee, Michael Dennis, Elias Bareinboim

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

Robust and Efficient Backdoor Mitigation for ML Models via Tolerant Property Testing

Xi Chen, Anindya De, Rocco A Servedio

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

From Perception to Punchline: Empowering VLM with the Art of In-the-wild Memes

Xueyan Li, Yingyi Xue, Mengjie Jiang, Qingzi Zhu and 1 more

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

Speed Predictions for Online Energy-Efficient Scheduling

Eric Balkanski, Jingwei Li, Clifford Stein, Cherlin Zhu

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

Crosscoding Through Time: Sparse Feature Discovery Across Sequence Positions

Dmitry Manning-Coe, Han Xuanyuan, Aniket Deshpande, Andrii Shportko and 1 more

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

SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

Lei Xiong, Kun Luo, Ziyi Xia, Wenbo Zhang and 5 more

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

PF-SGS: Pose-Free Streaming 3D Gaussian Splatting for Large-Scale Scene Reconstruction

wenjie mu, ziniu liu, Tong Wu, Zhan Li and 7 more

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

Robust Approximate Nearest Neighbor Search for Any Dataset

Alexandr Andoni, Themistoklis Haris, Esty Kelman, Krzysztof Onak

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

Finite-Resolution Decision Sufficiency for Linear Optimization

Mohammed Jamal, Soufiane Fafe

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

DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents

Yun-Shiuan Chuang, Ruixuan Tu, Chengtao Dai, You Li and 7 more

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

Diagnosing and Correcting Bias in MLLM for Long Video Understanding

Xusheng Liang, Jianqiao Sun, Hao Zhang, Yulei Niu and 2 more

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

Structural Blindness in Latent Data Assimilation: Representation Geometry Misleads Sensor Design

Yongquan Qu, Pierre Gentine

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

How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies

Bowei He, Yankai Chen, Xiaokun Zhang, Changjiang Han and 3 more

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

Causal Discovery over Clusters of Variables in Non-Markovian Systems

Tara Anand, Adèle H Ribeiro, Jin Tian, George Hripcsak and 1 more

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

Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative RLHF

Daniel Jiang, Ankur Samanta, Yukai Yang, Jalaj Bhandari and 2 more

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

NeuralFieldManifold: Reconstruction of LFP manifold with Lag Embedding

Kasra Fallah, Haoyu N Chen, Rudramani Singha, Eunji Kong and 3 more

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

DictLLM: Post-training Compression of Large Language Model with Dictionary Kernels

Jinho PARK, Se Young Chun, Mingoo Seok

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

Bias, Measurement Error, and Double-Dipping: When Can GNN Convolutions Help Brain Connectome Prediction?

Tommaso Castellani, Jiaqi Li, Muriah D Wheelock, Rezwana R Razzaque and 3 more

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

PhysEval.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models

Emma Kasteleyn, Timo Maier, Axel Lauer, Veronika Eyring and 2 more

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

ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling

Yilie Huang, Wenpin Tang, XUNYU ZHOU

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

Amortized Guidance for Image Inpainting with Pretrained Diffusion Models

Yilie Huang, XUNYU ZHOU

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

Be CARE-ful with Text-to-SQL Benchmarks

Haonan Wang, Jiaxiang Liu, Elaine Ang, Tiancheng Ge and 7 more

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

Answering At Any Cost: Frontier LLMs Are Consequence-Insensitive

Arka Pal, Kwok C Au, Louai Zahran, Rahul K Thomas and 3 more

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

Learning in Causal Markov Games

Aurghya Maiti, Elias Bareinboim

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

Variance-Adaptive Optimal Algorithm for Reinforcement Learning with MNL Function Approximation

Wonyoung Kim, Garud Iyengar, Assaf Zeevi, Min-hwan Oh

Sydney Poster Session 5, Thu, Dec 10, 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

Structure-Adaptive Estimation of Heterogeneous Treatment Effects with Kernel Methods

Seok-Jin Kim

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

Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Runjin Chen, Andy Arditi, Henry Sleight, Owain Evans and 1 more

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

A mathematical theory of balancing relational generalization and memorization

A theory of transitive inference with exceptions shows relational generalization and memorization depend on representational geometry, with pretrained language models exhibiting predicted systematic errors.

Luke Cheng, Samuel Lippl

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

Re-evaluating Continual Learning with Few-Shot Adaptation

Few-shot evaluation of continual learning reveals that meta-learning future tasks improves per-shot plasticity and stability across sequences.

Amogh Inamdar, Matthew So, Vici I Milenia, Richard Zemel

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

Reinforcement World Model Learning for LLM-based Agents

RWML learns action-conditioned world models for LLM agents via self-supervised sim-to-real alignment, outperforming direct task-success RL by up to 6.9 points without expert data.

Xiao Yu, Baolin Peng, Ruize Xu, yelong shen and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 28 on Hugging Face

Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models

PACE wraps AdamW to pull live weights toward their EMA with clipped per-coordinate control, improving iterate-averaged LM training and reducing error by arbitrarily large factors in quadratics while boosting 1-2B SFT and GPT-2 pretraining.

Kwok C Au, Adam Block

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

BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting

BEAST3D relates 3D behavioral features from multi-view video to neural activity via Gaussian splatting. It establishes a versatile framework for behavioral analysis using 3D structure in laboratory recordings.

Yanchen Wang, Lenny Aharon, Wangshu Zhu, Kyle Daruwalla and 6 more

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

Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness

Pan-FM, a pan-organ foundation model using saliency-guided masking, improves whole-body disease prediction and robustness under realistic missing-organ conditions across seven organs.

Qiangqiang Wu, Grace McIlvain, Zhou Yu, Junhao Wen

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

Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards

NFPO augments PPO with an N-step forward trace to reduce structural bias and control variance via cumulative token likelihood ratios, improving reasoning performance.

Deokgyu Yoon, Hyungkyu Kang, Joongkyu Lee, Byeongchan Kim and 3 more

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

Group-Aware Matrix Estimation and Latent Subspace Recovery

GAME regularizes overlapping subgroup submatrices with nuclear norms for local low-rank matrix completion, improving reconstruction and subspace recovery under structured missingness.

Hamza Golubovic, Matthew Shen, Genevera Allen, Tarek M Zikry

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

One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models

ORA proposes a marked time-to-event pretraining objective that jointly models clinical event timing and measurements to surpass next-token prediction for structured EHR foundation models.

Zilin Jing, Vincent Jeanselme, Yuta Kobayashi, Simon Lee and 5 more

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

Manifold Random Features

Manifold Random Features approximate bivariate manifold functions via graph discretization and continuous fields, yielding positive bounded features with low variance.

Ananya Parashar, Derek Long, Dwaipayan Saha, Krzysztof M Choromanski

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

Block Sphere Vector Quantization

BlockQuant quantizes rotated vector blocks spherically to improve reconstruction and inner-product distortion over coordinate-wise methods, with unified analysis showing rotation-quantizer tradeoffs depend on distortion criteria.

Heesang Ann, Joongkyu Lee, Min-hwan Oh

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

SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

SpreadsheetBench 2 evaluates agents on end-to-end spreadsheet workflows, finding best models achieve only 34.89% accuracy with debugging at 12%.

Jian Zhu, Yuzheng Zhang, Zeyao Ma, Bohan Zhang and 10 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · Code ★ 39

Fixed Universal Transformers

Fixed universal transformers simulate any target transformer via input embeddings with frozen internal parameters, and random initialization achieves universality almost surely.

Jingwen Liu, Alexandr Andoni, Daniel Hsu

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

Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoG

Fine-tuning language models on slow fMRI improves fast ECoG encoding predictions despite lower temporal resolution, with performance scaling with fMRI data volume.

Aditya Vaidya, Richard Antonello, Alexander Huth

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

Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs

A pseudo-labeling framework for kernel GLM domain adaptation minimizes target error via imputation-based model selection with non-asymptotic excess-risk bounds.

Nathan Weill, Kaizheng Wang

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

LensVLM: Selective Context Expansion for Compressed Visual Representation of Text

LensVLM lets VLMs scan compressed rendered text and selectively expand only relevant regions via learned tools, maintaining near-full accuracy at 4.3x compression and outperforming baselines up to 10.1x across text QA benchmarks.

Roy Xie, Dan Friedman, Donghan Yu, Bowen Pan and 6 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face

PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics

PointZero predicts full 3D point tracks from sparse tracks and RGB-D to learn transferable dynamics without robot actions, outperforming baselines on dynamics and manipulation tasks.

Bardienus Duisterhof, Kaifeng Zhang, Adam Hung, Bowen Wen and 4 more

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

Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning

Solly achieves elite human-level play in multi-player Liar's Poker via self-play reinforcement learning, outperforming both humans and large language models.

Richard Dewey, Janos Botyanszki, Ciamac C Moallemi, Andrew Zheng

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 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

Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models

LLMs overpredict social punishment relative to human judgments and align less with distant observers, revealing distorted second-order metanorm reasoning.

Sunny Rai, Jinyi Kuang, Reyhan Jamalova, Niyati Malhotra and 6 more

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

Wavelet Flow Matching for Multi-Scale Physics Emulation

Wavelet Flow Matching performs optimal-transport in multi-scale wavelet space via U-Net velocity prediction for stable, accurate generative PDE emulation without autoencoders.

Gabriele Accarino, Juan Nathaniel, Carla Roesch, Pierre Gentine and 3 more

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

Trimming the Long-Tail of Visual World Modeling Evaluation

Tailor-Bench evaluates visual world models on rare physical interactions via regular, unconventional, and impossible scenarios, revealing long-tail performance gaps and superficial visual-pattern reliance.

Bingxuan Li, Yining Hong, Cheng Qian, Hyeonjeong Ha and 5 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 40 on Hugging Face · Code ★ 1

OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping

OS-Pruner formulates chain-of-thought pruning as optimal stopping to learn dynamic termination, cutting generation length 20-60% with minimal accuracy loss.

Mohammed Ehab, Aymane El Gadarri, Vivek Farias, Adam Jozefiak and 1 more

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

Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation

RISE sketches LLM output-layer influence hotspots into compressed dual-channel sketches, reducing storage up to 112x versus gradient methods while scaling to 32B parameters for attribution and data valuation.

yide ran, Jianwen Xie, Minghui Wang, W. Jim Zheng and 3 more

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