openreview - Robuta Search

https://openreview.net/forum?id=NMvMYtRjkg An Investigation of Memorization Risk in Healthcare Foundation Models | OpenReview Foundation models trained on large-scale de-identified electronic health records (EHRs) hold promise for clinical applications. However, their capacity to... an investigation healthcare foundation memorization risk models https://openreview.net/forum?id=KviM5k8pcP AI Control: Improving Safety Despite Intentional Subversion | OpenReview As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful... ai control improving safety despite intentional subversion https://openreview.net/forum?id=6Mxhg9PtDE Safety Alignment Should be Made More Than Just a Few Tokens Deep | OpenReview The safety alignment of current Large Language Models (LLMs) is vulnerable. Simple attacks, or even benign fine-tuning, can jailbreak aligned models. We note... just a few https://openreview.net/group?id=ICML.cc/2024/Workshop/DMLR ICML 2024 Workshop DMLR | OpenReview Welcome to the OpenReview homepage for ICML 2024 Workshop DMLR icml workshop dmlr openreview https://openreview.net/forum?id=JPOW9FToYX Sampling Protein Language Models for Functional Protein Design | OpenReview Protein language models have emerged as powerful ways to learn complex representations of proteins, thereby improving their performance on several downstream... language models functional design sampling protein openreview https://openreview.net/forum?id=SJxSOJStPr A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning | OpenReview We propose an expansion-based approach for task-free continual learning for the first time. Our model consists of a set of neural network experts and expands... https://openreview.net/forum?id=VD_ozqvBy4W CoCon: A Self-Supervised Approach for Controlled Text Generation | OpenReview Pretrained Transformer-based language models (LMs) display remarkable natural language generation capabilities. With their immense potential, controlling text... text generation cocon self supervised approach https://openreview.net/group?id=MobiUK.org/2026/Symposium MobiUK 2026 Symposium | OpenReview Welcome to the OpenReview homepage for MobiUK 2026 Symposium mobiuk symposium openreview https://openreview.net/forum?id=FBkpCyujtS Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs | OpenReview Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. Popular... turning up the heat https://openreview.net/forum?id=2CttJRdVRC Byzantine Machine Learning: MultiKrum and an Optimal Notion of Robustness | OpenReview Aggregation rules are the cornerstone of distributed (or federated) learning in the presence of adversaries, under the so-called Byzantine threat model. They... machine learning byzantine https://openreview.net/forum?id=YKTJJCNXF4 Transport Clustering: Solving Low-Rank Optimal Transport via Clustering | OpenReview Optimal transport (OT) finds a least cost transport plan between two probability distributions using a cost matrix over pairs of points. Constraining the rank... transport clustering solving low rank https://openreview.net/forum?id=Lvy5MjyTh3 Inverting Gradient Attacks Makes Powerful Data Poisoning | OpenReview Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in... powerful data gradient attacks makes poisoning https://openreview.net/forum?id=e5Yky8Fnvj EPITOME: Experimental Protocol Inventory for Theory Of Mind Evaluation | OpenReview We address a growing debate about the extent to which large language models (LLMs) produce behavior consistent with Theory of Mind (ToM) in humans. We present... theory of mind epitome experimental protocol inventory https://openreview.net/forum?id=6ldD8Y4gBQ Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning | OpenReview Dataset ownership verification, the process of determining if a dataset is used in a model's training data, is necessary for detecting unauthorized data usage... data ownership verification via harmless https://openreview.net/forum?id=r1etN1rtPB Implementation Matters in Deep RL: A Case Study on PPO and TRPO | OpenReview We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization... a case study https://openreview.net/group?id=aclweb.org/ACL/ARR ACL ARR | OpenReview Welcome to the OpenReview homepage for ACL ARR acl arr openreview https://openreview.net/profile?id=~Benjamin_Schiller1 Benjamin Schiller | OpenReview Promoting openness in scientific communication and the peer-review process benjamin schiller openreview https://openreview.net/profile?id=~Vishwak_Srinivasan1 Vishwak Srinivasan | OpenReview Promoting openness in scientific communication and the peer-review process srinivasan openreview https://openreview.net/profile?id=~Alberto_D'Onofrio1 Alberto D'Onofrio | OpenReview Promoting openness in scientific communication and the peer-review process alberto openreview https://openreview.net/submissions?venue=automl.cc/AutoML/2024/Workshop_Track Submissions | OpenReview Promoting openness in scientific communication and the peer-review process submissions openreview https://openreview.net/forum?id=jDF2ZXI8AX&referrer=%5Bthe%20profile%20of%20Mikaela%20Angelina%20Uy%5D(%2Fprofile%3Fid%3D~Mikaela_Angelina_Uy1) MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images | OpenReview We present MV2Cyl, a novel method for reconstructing 3D from 2D multi-view images, not merely as a field or raw geometry but as a sketch-extrude CAD.... multi view extrusion cylinders images openreview https://aclrollingreview.org/statement-openreview-data-leakage Statement from ARR and EACL 2026 Organizers re OpenReview data leakage – ACL Rolling Review – A... Dec 17, 2025 - As noted in the ACL’s Nov 29 announcement, OpenReview was notified on Nov 27 of a software bug that allowed unauthorized access to authors, reviewers, and area... https://openreview.net/profile?id=~Alan_Yuille1 Alan Yuille | OpenReview Promoting openness in scientific communication and the peer-review process alan yuille openreview https://openreview.net/profile?id=~Seongho_Choi1 Seongho Choi | OpenReview Promoting openness in scientific communication and the peer-review process choi openreview https://openreview.net/login?redirect=/forum?id%3D2Co3DA4jY0 Login | OpenReview Promoting openness in scientific communication and the peer-review process openreview https://openreview.net/forum?id=7QRaAfbium Non-Vacuous Generalization Bounds for Large Language Models | OpenReview Modern language models can contain billions of parameters, raising the question of whether they can generalize beyond the training data or simply regurgitate... large language models non generalization bounds openreview https://openreview.net/forum?id=gdxUJvPng5 Reasoning and Tools for Forecasting | OpenReview Language models (LMs) trained on web-scale datasets are largely successful due to their ability to memorize large amounts of training data, even if only... reasoning tools forecasting openreview https://openreview.net/profile?id=~Aditya_Mate1 Aditya Mate | OpenReview Promoting openness in scientific communication and the peer-review process aditya mate openreview https://openreview.net/forum?id=q4mtFqw8PR Best Arm Identification for Prompt Learning under a Limited Budget | OpenReview The remarkable instruction-following capability of large language models (LLMs) has sparked a growing interest in automatically learning suitable prompts.... limited budget best arm identification prompt https://openreview.net/forum?id=5a27EE8LxX Toxicity Detection for Free | OpenReview Current LLMs are generally aligned to follow safety requirements and tend to refuse toxic prompts. However, LLMs can fail to refuse toxic prompts or be... toxicity detection for free openreview https://openreview.net/forum?id=TitmKQCIw0%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20https://repository.ubn.ru.nl/handle/2066/324614 Forum | OpenReview Promoting openness in scientific communication and the peer-review process forum openreview https://openreview.net/forum?id=cuFEpr3UU5 Generalizable Insights for Graph Transformers in Theory and Practice | OpenReview Graph transformers (GTs) have demonstrated strong empirical performance; however, current architectures exhibit significant variations in their utilization of... theory and practice insights graph transformers openreview https://openreview.net/profile?id=~Jeong_Yeon_Shin1 Jeong Yeon Shin | OpenReview Promoting openness in scientific communication and the peer-review process jeong yeon shin openreview https://openreview.net/profile?email=t-algaun%40microsoft.com | OpenReview Promoting openness in scientific communication and the peer-review process openreview https://openreview.net/profile?id=~Tal_Amir1 Tal Amir | OpenReview Promoting openness in scientific communication and the peer-review process tal amir openreview https://openreview.net/forum?id=JhTn1Lt04U Hopfield Boosting for Out-of-Distribution Detection | OpenReview Out-of-distribution (OOD) detection is crucial for real-world machine learning. Outlier exposure methods, which use auxiliary outlier data, can significantly... out of boosting distribution detection openreview https://openreview.net/profile?id=~Brendan_Kennedy2 Brendan Kennedy | OpenReview Promoting openness in scientific communication and the peer-review process brendan kennedy openreview https://openreview.net/profile?id=~Fangming_Feng2 Fangming Feng | OpenReview Promoting openness in scientific communication and the peer-review process feng openreview https://openreview.net/venue?id=ai-days.swiss-ai-center.ch/Swiss_AI_Days Venues | OpenReview Promoting openness in scientific communication and the peer-review process venues openreview https://openreview.net/forum?id=tMzPZTvz2H&referrer=%5Bthe%20profile%20of%20Fanghui%20Liu%5D(%2Fprofile%3Fid%3D~Fanghui_Liu1) Generalization of Scaled Deep ResNets in the Mean-Field Regime | OpenReview Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this... in the generalization scaled deep https://openreview.net/profile?id=~Joseph_Charles_Bingham1 Joseph Charles Bingham | OpenReview Promoting openness in scientific communication and the peer-review process joseph charles bingham openreview https://openreview.net/profile?id=~Luis_Espinosa-Anke1 Luis Espinosa-Anke | OpenReview Promoting openness in scientific communication and the peer-review process luis espinosa anke openreview https://openreview.net/forum?id=mVt55ZQqfTl Combinatorial Pure Exploration with Bottleneck Reward Function | OpenReview In this paper, we study the Combinatorial Pure Exploration problem with the Bottleneck reward function (CPE-B) under the fixed-confidence (FC) and fixed-budget... pure exploration bottleneck reward function https://openreview.net/forum?id=VvGIT6AOGsx CCVS: Context-aware Controllable Video Synthesis | OpenReview This presentation introduces a self-supervised learning approach to the synthesis of new videos clips from old ones, with several new key elements for improved... context aware controllable video synthesis openreview https://openreview.net/profile?id=~Mukund_Sudarshan1 Mukund Sudarshan | OpenReview Promoting openness in scientific communication and the peer-review process sudarshan openreview https://openreview.net/forum?id=k60XE_b0Ix6 Learning Label Encodings for Deep Regression | OpenReview We propose an end-to-end automated approach to learn label encodings for deep regression. learning label encodings deep regression https://openreview.net/forum?id=mnfzSF746z Combined Task and Motion Planning Via Sketch Decompositions | OpenReview The challenge in combined task and motion planning (TAMP) is the effective integration of a search over a combinatorial space, usually carried out by a task... motion planning combined task via sketch https://openreview.net/forum?id=nx9Z5Kva96 Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty Control | OpenReview Source-Free Domain Adaptation (SFDA) seeks to adapt a pre-trained source model to the target domain using only unlabeled target data, without access to the... a new perspective free domain https://openreview.net/login?redirect=/forum?id%3DFuRo7Ur5Ib Login | OpenReview Promoting openness in scientific communication and the peer-review process openreview https://openreview.net/profile?id=~Guoxiu_He1 Guoxiu He | OpenReview Promoting openness in scientific communication and the peer-review process openreview https://openreview.net/profile?id=~Jinghui_Qin1 Jinghui Qin | OpenReview Promoting openness in scientific communication and the peer-review process qin openreview https://openreview.net/profile?id=~Qianli_Liao1 Qianli Liao | OpenReview Promoting openness in scientific communication and the peer-review process qianli liao openreview https://openreview.net/forum?id=i39yXaUKuF Segment Any Point Cloud Sequences by Distilling Vision Foundation Models | OpenReview Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception. In this work, we... point cloud vision foundation segment sequences https://openreview.net/forum?id=78lTuD6wiO&referrer=%5Bthe%20profile%20of%20James%20Matthew%20Rehg%5D(%2Fprofile%3Fid%3D~James_Matthew_Rehg1) What is the Visual Cognition Gap between Humans and Multimodal LLMs? | OpenReview Recently, Multimodal Large Language Models (MLLMs) and Vision Language Models (VLMs) have shown great promise in language-guided perceptual tasks such as... what is the https://openreview.net/forum?id=MGDYQNXjCg A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems | OpenReview In order for agents in multi-agent systems (MAS) to be safe, they need to take into account the risks posed by the actions of other agents. However, the... a game managing risk https://openreview.net/profile?id=~Alexander_Ladd1 Alexander Ladd | OpenReview Promoting openness in scientific communication and the peer-review process alexander ladd openreview https://openreview.net/forum?id=7k2vOhYPnd Object-Flow Machine Learning: Active learning framework utilizing protocols information | OpenReview machine learning object flow active framework https://openreview.net/profile?id=~Jaakko_Lehtinen1 Jaakko Lehtinen | OpenReview Promoting openness in scientific communication and the peer-review process jaakko openreview https://openreview.net/profile?id=~shuang_ma1 shuang ma | OpenReview Promoting openness in scientific communication and the peer-review process shuang openreview https://openreview.net/forum?id=3YJ3JAI8Sz Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory | OpenReview Chain-of-thought (CoT) monitors are LLM-based systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest such as... chain of thought information theory analyzing improving https://openreview.net/forum?id=qxvlOypu7db&referrer=%5Bthe%20profile%20of%20Felix%20Biggs%5D(%2Fprofile%3Fid%3D~Felix_Biggs1) On Margins and Generalisation for Voting Classifiers | OpenReview We study the generalisation properties of majority voting on finite ensembles of classifiers, proving margin-based generalisation bounds via the PAC-Bayes... on margins voting classifiers openreview https://openreview.net/forum?id=rIx1YXVWZb Understanding Addition in Transformers | OpenReview Understanding the inner workings of machine learning models like Transformers is vital for their safe and ethical use. This paper provides a comprehensive... understanding addition transformers openreview https://openreview.net/profile?id=~Nicholas_Geneva1 Nicholas Geneva | OpenReview Promoting openness in scientific communication and the peer-review process nicholas geneva openreview https://openreview.net/profile?id=~Bowen_Jiang3 Bowen Jiang | OpenReview Promoting openness in scientific communication and the peer-review process bowen jiang openreview https://openreview.net/forum?id=sTjW3JHs2V Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets | OpenReview Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning... let flows tell solving https://openreview.net/forum?id=ntGPYNUF3t Latte: Latent Diffusion Transformer for Video Generation | OpenReview We propose Latte, a novel Latent Diffusion Transformer for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a... latent diffusion for video latte transformer generation https://openreview.net/profile?id=~P._Vaidyanathan1 P. Vaidyanathan | OpenReview Promoting openness in scientific communication and the peer-review process p https://openreview.net/revisions?id=o5D8i2zZ1l Revisions | OpenReview Promoting openness in scientific communication and the peer-review process revisions openreview https://openreview.net/forum?id=eT1QOsssRB Strategyproof Voting under Correlated Beliefs | OpenReview In voting theory, when voters have ranked preferences over candidates, the celebrated Gibbard-Satterthwaite Theorem essentially rules out the existence of... voting correlated beliefs openreview https://openreview.net/login?redirect=/forum?id%3Dc7nSUlJc34 Login | OpenReview Promoting openness in scientific communication and the peer-review process openreview https://openreview.net/forum?id=qmoVQbwmCY Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention | OpenReview Learning modular object-centric representations is said to be crucial for systematic generalization. Existing methods show promising object-binding... representation learning object centric via probabilistic https://openreview.net/profile?id=~Soham_Bakshi1 Soham Bakshi | OpenReview Promoting openness in scientific communication and the peer-review process soham openreview https://openreview.net/login?redirect=/forum?id%3D03boHXtK71 Login | OpenReview Promoting openness in scientific communication and the peer-review process openreview https://openreview.net/profile?id=~Nan_Jiang7 Nan Jiang | OpenReview Promoting openness in scientific communication and the peer-review process nan jiang openreview https://openreview.net/profile?id=~Max_Vladymyrov1 Max Vladymyrov | OpenReview Promoting openness in scientific communication and the peer-review process max openreview https://openreview.net/profile?id=~Yuanhong_Xu1 Yuanhong Xu | OpenReview Promoting openness in scientific communication and the peer-review process xu openreview https://openreview.net/profile?id=~Yepeng_Weng1 Yepeng Weng | OpenReview Promoting openness in scientific communication and the peer-review process weng openreview https://openreview.net/profile?id=~Hongyang_Chen2 Hongyang Chen | OpenReview Promoting openness in scientific communication and the peer-review process chen openreview https://openreview.net/profile?id=~Moritz_Grosse-Wentrup3 Moritz Grosse-Wentrup | OpenReview Promoting openness in scientific communication and the peer-review process moritz grosse openreview https://openreview.net/forum?id=3wBqoPfoeJ Twisting Lids Off with Two Hands | OpenReview Manipulating objects with two multi-fingered hands has been a long-standing challenge in robotics, due to the contact-rich nature of many manipulation tasks... two hands twisting lids openreview https://openreview.net/forum?id=O9EWFKXcXTU ProtoBrainMaps: Prototypical Brain Maps for Alzheimer's Disease Progression Modeling | OpenReview We propose a novel interpretable framework named Prototypical Brain Maps (ProtoBrainMaps) for modeling Alzheimer's disease progressions through a set of... disease progression prototypical brain maps https://openreview.net/forum?id=SJ1Xmf-Rb FearNet: Brain-Inspired Model for Incremental Learning | OpenReview FearNet is a memory efficient neural-network, inspired by memory formation in the mammalian brain, that is capable of incremental class learning without... brain inspired incremental learning model openreview https://openreview.net/profile?id=~Qiuyue_Wang2 Qiuyue Wang | OpenReview Promoting openness in scientific communication and the peer-review process wang openreview https://openreview.net/forum?id=fo5IUCMoFg&referrer=%5Bthe%20profile%20of%20Ji%20Shi%5D(%2Fprofile%3Fid%3D~Ji_Shi3) Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies | OpenReview Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect... https://openreview.net/forum?id=Q2xpIFubR8M On Narrative Information and the Distillation of Stories | OpenReview We introduce narrative information and use contrastive learning to distill the narrative essence out of music albums. and the narrative information distillation stories https://openreview.net/group?id=ICML.cc/2025/Workshop/CFAgentic ICML 2025 Workshop CFAgentic | OpenReview Welcome to the OpenReview homepage for ICML 2025 Workshop CFAgentic icml workshop openreview https://openreview.net/forum?id=eVuMspr9cu5 CATs: Cost Aggregation Transformers for Visual Correspondence | OpenReview We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images... cost aggregation cats transformers visual correspondence https://openreview.net/revisions?id=APElRzkmGY Revisions | OpenReview Promoting openness in scientific communication and the peer-review process revisions openreview https://openreview.net/profile?id=~Yang_Yang2 Yang Yang | OpenReview Promoting openness in scientific communication and the peer-review process yang openreview https://openreview.net/profile?id=~Weijie_Shi1 Weijie Shi | OpenReview Promoting openness in scientific communication and the peer-review process shi openreview https://openreview.net/profile?id=~Guy_Lever1 Guy Lever | OpenReview Promoting openness in scientific communication and the peer-review process guy lever openreview https://openreview.net/forum?id=Ayf90B1yESX The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation | OpenReview The goal of understanding decision-making behaviours in clinical environments is of paramount importance if we are to bring the strengths of machine learning... medkit learn ing environment https://openreview.net/forum?id=lRYfPNKCRu Predicting Deep Neural Network Generalization with Perturbation Response Curves | OpenReview We introduce a new approach to predict generalization and invariance of trained neural nets, by generating perturbation response curves and statistics inspired... deep neural network predicting generalization perturbation response https://openreview.net/profile?id=~Xing_Li6 Xing Li | OpenReview Promoting openness in scientific communication and the peer-review process xing li openreview https://openreview.net/forum?id=ubq7Co6Cbv Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks | OpenReview Simulators are powerful tools for autonomous robot learning as they offer scalable data generation, flexible design, and optimization of trajectories. However,... gaussian splatting real world https://openreview.net/forum?id=Bkg6RiCqY7 Decoupled Weight Decay Regularization | OpenReview L$_2$ regularization and weight decay regularization are equivalent for standard stochastic gradient descent (when rescaled by the learning rate), but as we... weight decay decoupled regularization openreview https://openreview.net/profile?id=~Paula_Rodriguez-Diaz1 Paula Rodriguez-Diaz | OpenReview Promoting openness in scientific communication and the peer-review process paula rodriguez diaz openreview https://openreview.net/profile?id=~Morgane_M_Moss1 Morgane M Moss | OpenReview Promoting openness in scientific communication and the peer-review process morgane moss openreview https://openreview.net/forum?id=ALRWSxT1rl Can Language Models Safeguard Themselves, Instantly and For Free? | OpenReview Aligning pretrained language models (LMs) to handle a new safety scenario is normally difficult and expensive, often requiring access to large amounts of... language models for free safeguard instantly openreview https://openreview.net/profile?id=~Yuxin_Yang3 Yuxin Yang | OpenReview Promoting openness in scientific communication and the peer-review process yuxin yang openreview