AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

UAI 2026

PCU: Perturbation-Calibrated Uncertainty for Unsupervised Anomaly Detection

Mebarka Allaoui, Rachid Hedjam, Mohand Saïd Allili, Guoqiang Zhong

Unsupervised anomaly detection requires deciding whether a test observation belongs to the nominal data distribution when only normal data are available for training. In this setting, failures arise primarily from epistemic uncertainty: the model must determine whether a sample lies within the learned support of the data or in an unseen region of the input space. Existing methods rely on density surrogates, reconstruction error, or distance-based scores, which often become unreliable near the nominal manifold and do not explicitly encode uncertainty. We propose \emph{Perturbation-Calibrated Uncertainty ({PCU})}, a representation-learning framework that estimates epistemic uncertainty through controlled input perturbations. An encoder is trained on a ladder of known corruption magnitudes so that latent displacement varies predictably with perturbation strength, enforced by a ranked-sensitivity constraint, a scale-aware prediction head, and variance–covariance regularization. An exponential moving average of clean embeddings provides a reference, yielding an anomaly score that combines global displacement, learned perturbation sensitivity, and local stability. By making perturbation response an intrinsic property of the representation rather than a post hoc test, {PCU} provides a compact, label-free uncertainty signal for unsupervised anomaly detection. Experiments on diverse tabular benchmarks demonstrate stable anomaly scores and competitive detection performance, particularly in near-manifold regimes, while mixed-feature perturbation design remains a limitation of the current {Gaussian} instantiation. {PCU} source code is available on \href{https://github.com/M-Allaoui/{PCU}.git}{{GitHub}}.

UAI 2026

Contrastive Conformal Sets

Yahya Alkhatib, Wee Peng Tay

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack a principled construction of geometric sets in the semantic feature space with distribution-free guarantees at any user-specified coverage level. We extend conformal prediction to this setting by introducing covering sets equipped with learnable generalized hyper-ball constraints. We propose a method that constructs conformal sets guaranteeing user-specified coverage of positive samples while maximizing negative sample exclusion. We theoretically motivate volume minimization as a proxy for negative exclusion, enabling our approach to operate effectively even when negative pairs are unavailable. The positive inclusion guarantee inherits the distribution-free coverage property of conformal prediction, while negative exclusion is maximized through learned set geometry optimized on a held-out training split. Experiments on simulated and real-world image datasets demonstrate improved inclusion-exclusion trade-offs compared to standard distance-based conformal baselines.

UAI 2026

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

Motasem Alfarra, Cristina Pinneri, Dana Kianfar, Mohammed Almousa, Christos Louizos

Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-device deployment. This paper presents a comprehensive study of parameter-efficient safety alignment methods for resource-constrained settings. Through systematic evaluation across multiple LLM architectures, training objectives, and parameter-efficient fine-tuning approaches, we identify that soft prompts combined with distillation-based training consistently outperform alternative methods. We introduce distillation frameworks based on total variation and KL divergence that effectively transfer safety behaviors from guard models into learned soft prompts. Our evaluations on various benchmarks demonstrate that this combination achieves superior safety-usefulness trade-offs compared to LoRA adapters, steering vectors, and direct optimization methods, while requiring minimal additional memory and compute at inference time. These findings establish soft prompt distillation as the preferred approach for safety alignment in on-device LLM deployment.

RSS 2026

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

Jiangran Lyu, Kai Liu, Xuheng Zhang, Haoran Liao, Yusen Feng, Wenxuan Zhu, Tingrui Shen, Jiayi Chen, Jiazhao Zhang, Yifei Dong, Cui Wenbo, Senmao Qi, Shuo Wang, Yixin Zheng, Mi Yan, Xuesong Shi, Haoran Li, Dongbin Zhao, Ming-Yu Liu, Zhizheng Zhang, Li Yi, Yizhou Wang, He Wang

RSS 2026

Action-to-Action Flow Matching

Jindou Jia, Gen Li, Xiangyu Chen, Tuo An, Yuxuan Hu, Jingliang Li, Xinying Guo, Jianfei Yang

RSS 2026

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

Matthew M. Hong, Jesse Zhang, Anusha Nagabandi, Abhishek Gupta

RSS 2026

TAIL-Safe: Task-Agnostic Safety Monitoring for Imitation Learning Policies

Riad Ahmed, Momotaz Begum

RSS 2026

Mimic Intent, Not Just Trajectories

RenMing Huang, Chendong Zeng, Wenjing Tang, Jintian Cai, Cewu Lu, Panpan Cai

RSS 2026

HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

Xiaomeng Xu, Jisang Park, Han Zhang, Eric Cousineau, Aditya Bhat, Jose Barreiros, Dian Wang, Jeannette Bohg, Shuran Song

RSS 2026

Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration

Modi Shi, Shijia Peng, Jin Chen, Haoran Jiang, Tianyu Li, Ping Luo, Di Huang, Hongyang Li, Li Chen

RSS 2026

LAP: Language-Action Pre-training Enables Zero-Shot Cross-Embodiment Transfer

Lihan Zha, Asher James Hancock, Mingtong Zhang, Tenny Yin, Yixuan Huang, Dhruv Shah, Allen Z. Ren, Anirudha Majumdar

RSS 2026

Functional Force-Aware Retargeting from Virtual Human Demos to Soft Robot Policies

Uksang Yoo, Mengjia Zhu, Evan Pezent, Jom Preechayasomboon, Jean Oh, Jeffrey Ichnowski, Amirhossein H. Memar, Ben Abbatematteo, Homanga Bharadhwaj, Ashish Deshpande, Harsha Prahlad

RSS 2026

Long-Context Robot Imitation Learning by Focusing on Key History Frames

Max Sobol Mark, Maria Attarian, Chuyuan Fu, Debidatta Dwibedi, Jacky Liang, Dhruv Shah, Aviral Kumar

RSS 2026

Active Surface-Driven Reconfigurable Gripper: Robust Grasping and Sequential Manipulation of Thin Objects

Ziyi Zheng, Keqi Zhu, Hao Wu, Yanzhe Wang, Huixu Dong

RSS 2026

A Super-Resolution and Multi-Axis Tactile Sensor with Soft Artificial Skin

Hongxu Wei, Zhou Lu, Peisen Xu, Yang Xu, Xuanyi Yang, Wei Zhao, Jiming Chen, Gaofeng Li

RSS 2026

Continuum Robot Modeling with Action Conditioned Flow Matching

Jiong Lin, Jinchen Ruan, Hod Lipson

RSS 2026

A Dual-Mode Electrical Capacitance Tomography Sensor for Robotic Proximity Servoing and Grasping

Duanpeng Shi, Yuliang Wang, Yuming Huang, Huaping Liu, Di Guo

RSS 2026

Computational Design of a Low-Visibility UAV Using a Human-Aligned Perceptual Metric

Jingxian Wang, Chen Yu, David Matthews, Emma Alexander, Sam Kriegman, Michael Rubenstein

RSS 2026

Latent Diffeomorphic Co-Design of End-Effectors for Deformable and Fragile Object Manipulation

Kei Ikemura, Yifei Dong, Florian T. Pokorny

RSS 2026

Bridging Language and Physics: Automated Design of Continuum Robots with Large Language Models

Jingyi Chen, Mohan Zhang, Laura Yao, Yingtai Ni, Jianmin Ji, Jie Peng, Song Wang, Tianlong Chen

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.