A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review

Rhetorical robustness requires stable judgments across content-preserving rewrites and discrimination across papers; SciCore improves both via dual-branch science-core review.

Chenguang Wang, Ming Li, Chengrui Fan, Jianpeng Chen and 3 more

Published Sep 30, 2026 · 0 citations · ▲ 76 on Hugging Face

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

Kshitij Mishra, Abhijith Sharma, Nils Lukas, Salem Lahlou

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

Object Hallucination Mitigation in Large Vision-Language Models via Self-Vision Dual Masking and Uncertainty-Triggered Assembly

Ziji Sheng, Guiyao Tie, Weidong Wang, Jiawen Shi and 7 more

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

Seeing Together, Acting Apart: Shared Environmental Understanding for Multi-Robot Navigation

haihong hao, Lei Chen, Mingfei Han, Dong An and 6 more

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

Harmonic Torsional Diffusion for Flexible Protein-Ligand Docking

Maksim Zhdanov, Pavel Strashnov, Vladislav Kurenkov

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

When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction

Jinghui Zhang, Lang Gao, Zongfang Liu, Ruihong Zeng and 4 more

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

From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts

Ruihong Zeng, Puning Yang, Jinghui Zhang, Shen Gao and 3 more

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

VecUQ-OT: Aggregating Uncertainty Measures via Multivariate Ranks

Nikita Kotelevskii, Vladimir Kondratyev, Maiya Goloburda, Alexander Fishkov and 3 more

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

The Aleatoric-Epistemic Dichotomy of Uncertainty is Meaningful and Indispensable for Machine Learning

Yusuf Sale, Nikita Kotelevskii, Maxim Panov, Eyke Hüllermeier

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

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

Puning Yang, Qizhou Wang, Junchi Yu, Bo Han and 1 more

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

Geometric Instability of Hidden-State Trajectories Predicts Reasoning Failures in Large Language Models

Hoda Fakharzadehjahromy, Andreas C Bueff, Fredrik Heintz, Mattias Tiger and 3 more

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

VideoSailor: Navigating Video Deep Research via Trajectory-to-Policy Flywheel

Meng Cao, Pengfei Hu, Yingyao Wang, Chen Wang and 6 more

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

Provable Selective Auto-labeling with Reliability Guarantees

Huipeng Huang, Wenbo Liao, Huajun Xi, Hao Zeng and 2 more

Sydney Poster Session 1, Tue, Dec 8, 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

SODA: Selective Optimization with Deferred BN Alignment for Efficient Dataset Distillation

Xinyue Bi, Jiacheng Cui, Yaxin Luo, Xinyi Shang and 3 more

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

Training-Based Backdoors Are Not Cryptographic

Masahiro Kaneko

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

Identification and Bounding of Joint Expectation over Potential Outcomes

Yuta Kawakami, Jin Tian

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

FedSEM: Mitigating Cross-Client Evidence Drift in Federated Multiple Instance Learning

Zhiqiang Kou, Beidi Wang, Yuling Shi, Shengkun Zhu and 5 more

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

MEV: A Multi-Event Video Dataset for Long-Take Generation

Peiyuan Zhu, Shaoan Xie, Yifan Shen, Wen Tian and 3 more

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

MedCache: Training-Free Spatially Aware Caching for Accelerated Medical Video Generation

Ufaq Khan, Umair Nawaz, Sathira Silva, Numan Saeed and 6 more

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

Improving Continual Video Instance Segmentation via Spatial-Temporal Balanced Mixture-of-Experts Adapters

Hao Fu, Sihao Liu, Hanbin Zhao, Jiahua Dong and 2 more

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

Concise Reasoning Through the Lens of Lagrangian Optimization

Chengqian Gao, Haonan Li, Taylor Killian, Jianshu She and 5 more

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

REFORM-3D: A Representation-Centric Evaluation Framework for 3D Medical Vision Foundation Models

Maregu Assefa, Muhammad Muzammal Naseer, Divya Velayudhan, Gedamu Kumie and 1 more

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

The Agentic Oversight Tax: Human Supervision of AI Agents Has a Cost that Must be Accounted For

Olivier Oullier

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

Median-of-Means under Structured Heavy-Tailed Noise: High-Probability Bounds for Clipped Stochastic Optimization

Ahmed El Bajdali, Ohad Shamir, Samuel Horváth, Eduard Gorbunov

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

BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots

Jingchen Huang, Wenxi Li, Chenyang Lyu, Moran Liu and 2 more

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

The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents

Geyuan Wang, Shunyu Liu, Siyuan Liang, Chenyang Lyu and 1 more

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

Heterogeneity-aware Distillation for Federated Continual Learning

Gaozhuo Liu, Yichen Li, Xiuying Wang, Yulong Li and 3 more

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

Rehearsal-Free Statistical Prototype Regularization for Federated Incremental Learning

Xiuying Wang, Yichen Li, Jiahua Cheng, Xiwei Liu and 3 more

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

Towards Principled Fine-Grained MoE Expert Pruning via Pseudo-Boolean Approximation

Zongfang Liu, Ziheng Cheng, Shengkun Tang, Jinghui Zhang and 3 more

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

DELTA: Robustly Training Label-Conditional Diffusion Models with Weak Annotations

Dong-Dong Wu, Jiacheng Cui, Wei Wang, Zhiqiang Shen and 1 more

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

Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?

Jiale Liu, Huajun Xi, Shaokun Zhang, Yifan Zeng and 5 more

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

Uniform Diffusion Models revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

Standard uniform diffusion training uses a leave-one-out posterior rather than the true denoising posterior, causing a parameterization-objective mismatch that new conversions, samplers, and an absorbing-state reformulation fix to match masked diffusion.

Samson Gourevitch, Yazid Janati, Dario Shariatian, Umut Simsekli and 3 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026 · ▲ 4 on Hugging Face · Code ★ 11

DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding

DocScope benchmarks verifiable long-document reasoning via structured trajectory evaluation, finding correct answers rarely include complete evidence chains and region grounding remains weakest.

Xiang Feng, Jiawei Zhou, Zhangfeng Huang, Kewei Wang and 5 more

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

Convex Compositional Reasoning Models

Convex Compositional Energy Minimization uses input-convex factor networks and convex relaxation to enable scalable deterministic compositional reasoning that transfers to larger instances without retraining.

Meir Roketlishvili, Semen Semenov, Maksim Bobrin, Viktor Kovalchuk and 6 more

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

Gaussian Mixture Models in Hilbert Spaces via Kernel Methods

A kernel-based Gaussian mixture model for Hilbert-space data uses mean embeddings to cluster infinite-dimensional objects with theoretical guarantees and scalable estimation.

Daniel López Montero, Antonio Álvarez-López, Marcos Matabuena

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

CITE: Anytime Valid Statistical Inference in LLM Self-Consistency

CITE provides anytime-valid certification of a target answer as the unique mode under arbitrary data-dependent stopping without knowing the answer set, with optimal stopping-time rates and improved LLM self-consistency.

Hirofumi Ota, Naoto Iwase, Yuki Ichihara, Junpei Komiyama and 1 more

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

A Benchmark for Omni-Modal Reasoning in Long Videos

LongShOTBench evaluates long-form omni-modal video reasoning via rubric-scored open-ended questions, and LongShOTAgent achieves 66.64% as the top training-free system.

Mohammed Irfan Kurpath, Jaseel M Kaithakkodan, Jinxing Zhou, Sahal Shaji Mullappilly and 11 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face · Code ★ 26

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks

SCOPE co-evolves a task-generating challenger and retrieval solver with rubric-based self-judging to improve open-ended and QA performance without curated data.

Wai-Chung Kwan, Aryo Gema, Joshua O Leang, Pasquale Minervini

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 25 on Hugging Face · Code ★ 2

Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection

Standard video backbone readouts suppress patch-level temporal dynamics needed to detect AI-generated videos; a lightweight velocity-gated patch profiling readout reaches 95.28 AUC on frozen backbones.

Manni Cui, Ziheng Qin, ZiAn Wang, Ruiqi Liu and 7 more

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

On the Recoverability of Causal Relations from Bulk Gene Expression Data

Causal gene relations are recoverable from bulk expression only under linear aggregation and affine equations, which real data rarely satisfy.

Gongxu Luo, Boyang Sun, Kun Zhang

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

Path-Guided Flow Matching for Dataset Distillation

PGFM introduces flow matching for generative dataset distillation with deterministic ODE synthesis, continuous path-to-prototype guidance, and 7.6x efficiency gains over diffusion methods.

xuhui li, Zhengquan luo, Zixu Wu, Xiwei Liu and 3 more

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

Occupancy-based Quantile Risk Control

OQRC partitions calibration losses into ordered bins to tightly upper-bound quantile risk with finite-sample guarantees converging at rate O_p(n^{-1/2}).

Zihao Shi, Huajun Xi, Bingyi Jing, Hongxin Wei

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

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations

Temporal knowledge drift is geometrically orthogonal to correctness and uncertainty in LLM residual streams, making drift undetectable via standard signals despite linear probes reaching 0.83, 0.95 AUROC.

Rania Elbadry, Ahmed Heakl, Fan Zhang, Dani Bouch and 3 more

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

Efficient Image Synthesis with Sphere Latent Encoder

Decoupling sphere encoding into a fixed pretrained encoder and separate spherical latent denoiser improves few-step image generation efficiency and quality.

Tung Do, Thuan H Nguyen, Hao Li

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026 · ▲ 7 on Hugging Face

DoAtlas-1: A Causal Compilation Paradigm for Clinical AI

DoAtlas-1 introduces causal compilation to convert medical evidence into executable causal estimands, achieving 98.5% canonicalization accuracy and 80.5% query executability across 1,445 effect kernels.

Yulong Li, Jianxu Chen, Xiwei Liu, Chuanyue Suo and 7 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 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

Calibrating LLMs with Semantic-level Reward

Calibration with Semantic Reward improves LLM calibration by replacing token-level confidence with direct semantic-space rewards, reducing ECE by up to 40% and raising AUROC by up to 31%.

Fengfei Yu, Ruijia Niu, Dongxia Wu, Yian Ma and 1 more

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

Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents

FedSARSA with linear approximation and local training achieves linear agent speed-up and converges despite heterogeneous transitions and rewards, with explicit sample and communication complexity bounds.

Paul Mangold, Eloïse Berthier, Eric Moulines

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

Uncertainty Quantification for Large Language Diffusion Models

Lightweight zero-shot uncertainty signals from LLDM denoising dynamics achieve sampling-level hallucination detection at up to 100x lower cost.

Artem Vazhentsev, Vladislav Smirnov, David Li, Maxim Panov and 2 more

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

MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale

MemArena benchmarks on-device ego-centric personal memory assistants via simulated multi-session agents, showing memory backend choice dominates accuracy and permission-aware access fails universally.

Jiadong Zhang, Xiaosong Ma

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

FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation

FlowHOI generates semantically grounded hand-object interaction sequences via two-stage flow matching, achieving 1.7x higher simulation success and 40x faster inference than diffusion baselines.

Huajian Zeng, Lingyun Chen, Jiaqi Yang, Yuantai Zhang and 3 more

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

StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video

StableHand estimates world-space dual-hand motion from egocentric video via quality-aware flow matching, cutting W-MPJPE by 20-25% over baselines on occluded benchmarks.

Huajian Zeng, Chaohua Yao, Yuantai Zhang, Jiaqi Yang and 2 more

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

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

A scalable dual-learning framework applies parameter symmetry alignments to enable near-barrier-free linear merging of billion-parameter pretrained transformers.

Tianyi Li, Zhiqiang Shen

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

KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

KaliBench evaluates natural-language-to-CLI translation for 1,642 Kali Linux cybersecurity tools, finding open-weight models below 42% accuracy but training with verifiable rewards significantly improves smaller models.

Pengfei Li, Naufal Suryanto, Sicheng Zhang, Muhammad Muzammal Naseer

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