Tail-Influence Sampling for CVaR Policy Evaluation

Tail-Influence Sampling allocates evaluation budgets by tail influence to estimate CVaR with oracle variance and lower MSE than rollouts.

Pauline Bourigault, Xiaotong Ji, Matthieu Zimmer, Rasul Tutunov and 1 more

Published Sep 29, 2026 · 0 citations · ▲ 23 on Hugging Face · Code ★ 1

From Jumps to Signatures: a Generative Method for Temporal Point Processes

Niels Cariou-Kotlarek, Vasileios Lampos

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

L$^2$EAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks

Po-Nien Kung, Linfeng Song, Dawsen Hwang, Jinsung Yoon and 9 more

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

MFlowAudio: Efficient Text-to-Audio Synthesis via Mamba-based Stateful Flow Matching

Hao Dai, Panyu Chen, Jagmohan Chauhan

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

Dancing in Fetters: Pareto-Optimal On-Device LLMs under Hardware Constraints

Luoyang Sun, Jiwen Jiang, Yifeng Ding, Fengfa Li and 8 more

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

Graph and Simplicial Complex Prediction Gaussian Process via Hodgelet Representations

Mathieu Alain, So Takao, Bastian Rieck, Xiaowen Dong and 1 more

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

Physics-Constrained Generative World Model for Off-Road Terrain via Post-hoc Projection

Yuan Zhou, Hao Yu, Ruiran Cao, Haoran Yang and 4 more

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

Learning Gaussian Conditional Distributions using Neural Ratio Estimation is Hard

Pierre Glaser, Arthur Gretton

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

From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce

Xianyang Liu, Shangding Gu, Fan Xu, Manxi Wu and 4 more

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

The limbic navigation system as a hierarchical RNN

Zilong Ji, Huiwen Zhang, Krishna Gorantla, Neil Burgess

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

LLM-WikiRace: A Benchmark for Planning and Reasoning over Real-World Knowledge Graphs

Juliusz Ziomek, William Bankes, Lorenz Wolf, Shyam Sundhar Ramesh and 2 more

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

CLIOPATRA: Extracting Private Information from LLM Insights

CLIOPATRA attacks privacy-preserving LLM insight platforms with malicious chats to leak target medical histories with nearly 100% precision in 65% of cases, showing layered heuristic protections are insufficient.

Meenatchi Sundaram Muthu Selva Annamalai, Emiliano De Cristofaro, Peter Kairouz

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

Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization

ROVER pretrains exploration policies via occupancy coverage maximization using a resolvent world model and virtual sink state, yielding stronger initializations for sparse-reward downstream tasks.

Marco Pratticò, Pietro Novelli, Massimiliano Pontil, Carlo Ciliberto

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

Sobolev Regularized MMD Gradient Flow

Sobolev-regularized MMD gradient flow penalizes witness function gradients to ensure global convergence without isoperimetric assumptions, applying to both sampling and generative modeling.

Chenyang Tian, Bharath Sriperumbudur, Arthur Gretton, Zonghao Chen

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

Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology

Meow-Omni 1 integrates video, audio, physiological time-series, and text to reach 71.16% feline intent recognition, outperforming baseline multimodal models.

Jucheng Hu, Zhangquan Chen, Yulin Chen, Chengjie Hong and 8 more

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

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

Predicting Only from Selected Evidence: A Tempered Product-of-Experts Bottleneck for Auditable EEG Diagnosis

tPoE-EIB constrains EEG diagnosis to selected evidence via tempered product-of-experts fusion, improving auditable selection and integration faithfulness while preserving accuracy.

Yinghao WANG, Shujian Yu, Duc-Han LE, Zhikai Yu and 2 more

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

LinearARD: Linear-Memory Attention Distillation for RoPE Restoration

LinearARD restores RoPE-scaled LLMs via linear-memory attention self-distillation, recovering 98.3% short-text performance with 4.25M tokens versus 256M.

Ning Yang, Hengyu Zhong, Wentao Wang, Baoliang Tian and 3 more

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

LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling

LEMON-ZEST uses evolution-informed tokenization to embed domain-level biological priors directly into protein language models. Its 200M-parameter LEMON model outperforms 600M to 3B parameter models on remote homology detection despite training on a single H100 GPU for one week. Evolution-informed to

Biswajit Banerjee, Claudia Alvarez Carreno, Anton S Petrov

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

A Unified Framework for Adversary-Aware Differential Privacy Bounds

A unified framework bounds DP privacy leakage against multi-target membership, attribute, and reconstruction attacks using only privacy parameters and adversarial baseline success rates.

Marika Swanberg, Meenatchi Sundaram Muthu Selva Annamalai, Jamie Hayes, Borja Balle and 1 more

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

RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms

RepoLaunch automates cross-language repository builds and testing, achieving 78% build success and enabling fully automated SWE dataset pipelines.

Kenan Li, Rongzhi Li, Linghao Zhang, Qirui Jin and 16 more

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

GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models

GDSD improves diffusion language models via advantage-guided denoiser self-distillation that bypasses ELBO likelihood surrogates, boosting test accuracy up to 19.6%.

Xiaohang Tang, Keyue Jiang, Che Liu, Zhao and 3 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026 · ▲ 4 on Hugging Face · Code ★ 22

Normative Networks for Source Separation via Local Plasticity and Dendritic Computation

Predictive Entropy Maximization achieves blind source separation via local plasticity and dendritic error-driven rules with competitive robustness.

Bariscan Bozkurt, Efe Ali Gorguner, Francesco Innocenti, Rafal Bogacz

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

Tokenizer-Generator Coupling in Medical Image Generation

Latent medical image generator rankings depend jointly on tokenizer, generator, and sampler choices, with retuned samplers reducing FID to 0.09 and reconstruction PSNR failing as a selection criterion.

Liam Chalcroft

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

Conservative neural posterior estimation via distributionally robust training

DRO-NPE trains neural posterior estimators with distributionally robust worst-case losses to reduce overconfidence and improve calibration under limited simulation budgets.

William Laplante, Yuga Hikida, Charita Dellaporta, Francois-Xavier Briol and 1 more

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

FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics

FML-bench isolates agent strategy from infrastructure across 18 ML tasks, finding greedy hill-climbing nearly matches tree search, while adaptive exploration switching outperforms fixed strategies.

Qiran Zou, Hou Hei Lam, Wenhao Zhao, Tingting Chen and 10 more

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

Closed-Form Last Layer Optimization

Closed-form last-layer optimization treats final weights as backbone-dependent functions, yielding convergence guarantees and outperforming SGD and Adam on regression tasks.

Alexandre Galashov, Nathaël Da Costa, Liyuan Xu, Philipp Hennig and 1 more

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

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks

TerminalWorld automatically builds terminal benchmarks from wild recordings, yielding 1,530 tasks where top agents achieve only 62.5% success with weak correlation to expert benchmarks.

Zhaoyang Chu, Jiarui Hu, Xingyu Jiang, Pengyu Zou and 7 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026 · ▲ 8 on Hugging Face · Code ★ 48