LiSeCo: Linear Semantic Control for Language Generation Emily Cheng, Carmen Amo Alonso Action editor: Bo Han https://openreview.net/forum?id=a3o2pzZuvE #semantic #semantics #embedding

ARROW: Augmented Replay for RObust World models Abdulaziz Alyahya, Abdallah Al Siyabi, Markus R. Ernst et al. Action editor: Michele Caprio https://openreview.net/forum?id=3FK2tFwNwK #forgetting #replays #memory

Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space Di Wu, Huan Liu, Zhixiang Chi, YUANHAO YU, Konstantinos N. Plataniotis, Yang Wang Action editor: Lechao Xiao https://openreview.net/forum?id=4fweEyVYLF #encoder #representations #deep

New #Featured Certification, #J2C Certification: Achieving Adaptivity and Optimality for Multi-armed Bandits using Exponential-Kullback Leibler Ma... Hao Qin, Kwang-Sung Jun, Chicheng Zhang https://openreview.net/forum?id=IuVkRmecVp #bandits #optimality #sampling

Efficient Block Bi-clustering by Alternating Semidefinite Programming Relaxation Yuxin Ma, Weiguo Gao, Xiang ZHOU Action editor: Patrick Flaherty https://openreview.net/forum?id=xPA4Xg0IvL #clustering #semidefinite #optimizing

Persistent homology for time series: a selective review Alexandre Bois, Hugo Henneuse, Brian Tervil, Laurent Oudre Action editor: Serguei Barannikov https://openreview.net/forum?id=tztKO9jzBR #homology #persistent #data

Encoding Without Influence: Dissociating Demographic Representation from Causal Effect in Large L... Aarushi Sharma, Phong Le Action editor: Shangtong Zhang https://openreview.net/forum?id=TQbXHsI3Lm #demographics #demographic #autoencoder

Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping Linzh Zhao, Aki Rehn, Mikko A. Heikkilä, Razane Tajeddine, Antti Honkela Action editor: Marco Mondelli https://openreview.net/forum?id=UlzcKSHVoN #privacy #clipping #private

New #Survey Certification: A Survey on Efficient Protein Language Models Shouren Wang, Debargha Ganguly, Vinooth Rao Kulkarni et al. https://openreview.net/forum?id=PTReuOwsXz #protein #memory #embedding

Video Generation Models: A Survey of Post-Training and Alignment Chaoyu Li, Xiaoyi Gu, Yogesh Kulkarni et al. Action editor: Sungwoong Kim https://openreview.net/forum?id=YlUEWLESIu #clips #video #generative

Querying Kernel Methods Suffices for Reconstructing their Training Data Daniel Barzilai, Yuval Margalit, Eitan Gronich, Gilad Yehudai, Meirav Galun, Ronen Basri Action editor: Joonas Jälkö https://openreview.net/forum?id=qikuoG0Th2 #privacy #kernel #memorization

Diffusion-based Cumulative Adversarial Purification for Vision Language Models Jia Fu, Yongtao Wu, Yihang Chen et al. Action editor: Jakub Tomczak https://openreview.net/forum?id=kpuV3mzwqw #adversarial #vision #robust

A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data Kaituo Zhang, Mingzhi Hu, Hoang Anh Duy Le et al. Action editor: Yu Meng https://openreview.net/forum?id=f2gS9Ly6tA #evaluations #evaluation #models

CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs Raman Dutt, Pedro Sanchez, Yongcheng Yao et al. Action editor: Chang Xu https://openreview.net/forum?id=wrKmzYQACp #generative #benchmark #privacy

Amnesia: A Stealthy Replay Attack on Continual Learning Dreams Ahmed Sharshar, K Naveen Kumar, Mohsen Guizani Action editor: Eleni Triantafillou https://openreview.net/forum?id=QSTg7z06GH #replay #forgetting #amnesia

CAPTAIN: Conformal-Prediction-Based Multi-Source Time-Series Forecasting Shuaicheng Zhang, Tuo Wang, Adithya Kulkarni et al. Action editor: Taylor Killian https://openreview.net/forum?id=WJjlXHo4yS #forecasting #copulas #prediction

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Cla... Antonio De Santis, Riccardo Campi, Matteo Bianchi, Marco Brambilla Action editor: Fernando Perez-Cruz https://openreview.net/forum?id=SLh00W5rhu #saliency #cnns #explanations

New #Survey Certification: Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions Sarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang et al. https://openreview.net/forum?id=mM3r03Xw1V #forgetting #adaptation #adapting

Mitigating Embedding Leakage via Latent Disruption with Controlled Reconstruction Zhiyuan Wu, Changkyu Choi, Shujian Yu, Robert Jenssen, Ali Ramezani-Kebrya Action editor: Feng Liu https://openreview.net/forum?id=nZWBrxJyrS #embeddings #embedding #encoders

RPWithPrior: Label Differential Privacy in Regression Haixia Liu, Ruifan Huang Action editor: Antti Koskela https://openreview.net/forum?id=FiUe0OCMaj #privacy #randomized #classification

New #J2C Certification: MatchEx: Model-Level GNN Explanations with Multi-Granular Insights Sayan Saha, Sanghamitra Bandyopadhyay https://openreview.net/forum?id=YMETLG2WvM #motifs #motif #explanations

It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-di... Leonhard F. Feiner, Manuel Nickel, Martin J. Menten et al. Action editor: Jes Frellsen https://openreview.net/forum?id=zw5EuUnBny #robust #robustness #uncertainty

Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition Cem Üyük, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou Action editor: Yoshitomo Matsubara https://openreview.net/forum?id=vbS7Z8Zswe #transformer #sparse #tensor

Rectified Flows for Fast Multiscale Fluid Flow Modeling Victor Armegioiu, Yannick Ramic, Siddhartha Mishra Action editor: Markus Lange-Hegermann https://openreview.net/forum?id=2tMD6YXgkp #flow #flows #diffusion

Adaptive and Stratified Subsampling for High-Dimensional Robust Estimation Prateek Mittal, Joohi Chauhan Action editor: Xiaojie Mao https://openreview.net/forum?id=R8y19hU9Ab #subsampling #estimation #estimators

Learning Materials Interatomic Potentials via Hybrid Invariant-Equivariant Architectures Keqiang Yan, Montgomery Bohde, Andrii Kryvenko et al. Action editor: Chang Liu https://openreview.net/forum?id=fq3nrVqNmL #potentials #models #nvariant

Disjoint Generation of Synthetic Data Anton Danholt Lautrup, Muhammad Rajabinasab, Tobias Hyrup et al. Action editor: Stefan Feuerriegel https://openreview.net/forum?id=LSzXkAWBKI #privacy #datasets #dataset

LLM-Guided Search for Deletion-Correcting Codes Franziska Weindel, Reinhard Heckel Action editor: Zhengzhang Chen https://openreview.net/forum?id=qZ69Ozpo6v #funsearch #deletions #constructions

Index2Sort: Sorting Algorithm Using Static Index Structure Atsuki Sato, Yusuke Matsui Action editor: Jeff Phillips https://openreview.net/forum?id=YUmVxjMhpm #index2sort #sorting #complexity

Twin: Tuning Learning Rate and Weight Decay of Deep Homogeneous Classifiers without Validation Lorenzo Brigato, Stavroula Mougiakakou Action editor: Ikko Yamane https://openreview.net/forum?id=1SIP2M2HJa #classifiers #twin #deep

Robust Recourse via Kernel Distributionally Robust Optimization and Bayesian Posterior Predictive... Sita bissu, Navnit Kumar Yadav, APARNA MEHRA, Sandeep Kumar Action editor: Samuel Vaiter https://openreview.net/forum?id=LmEDkCTY0X #robustness #robust #uncertainties

BitLogic: A Framework for Gradient-Based LUT-Native Neural Networks Simon Jonas Bührer, Andreas Plesner, Till Aczel, Roger Wattenhofer Action editor: Robert Legenstein https://openreview.net/forum?id=ZbsSZAfDod #logicnets #fpga #bitlogic

Insights From a Data- and Space-Agnostic Approach to Zero-Cost Proxies Timotée Ly-Manson, Mathieu Léonardon, Abdeldjalil AISSA EL BEY Action editor: Mathieu Salzmann https://openreview.net/forum?id=sVWJczov4Q #benchmarking #benchmarks #search

Transforming Language Models into Program Interpreters via Execution Trace Chain of Thought Koshi Eguchi, Kazusato Oko, Kenshin Yamauchi, Makoto Shing, Takuya Akiba Action editor: Varun Kanade https://openreview.net/forum?id=pOg7iub4Pz #interpreters #interpreter #execution

LARP: Learner-Agnostic Robust Data Prefiltering Kristian Minchev, Dimitar Iliev Dimitrov, Nikola Konstantinov Action editor: Ozan Sener https://openreview.net/forum?id=gI6VOV3jfO #prefiltering #learners #learner

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs Yi-Lin Sung, Prateek Yadav, Jialu Li, Jaehong Yoon, Mohit Bansal Action editor: Gustavo Carneiro https://openreview.net/forum?id=kBezrKXHVS #attention #quantization #quantize

ReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction Jianan Nie, Peiyao Xiao, Kaiyi Ji, Peng Gao Action editor: Stanislaw Jastrzebski https://openreview.net/forum?id=ODlxgod5e3 #crystals #crystal #lattice

Family Matters: A Systematic Study of Spatial vs. Frequency Masking for Continual Test-Time Adapt... Chandler Timm Cagmat Doloriel, Yunbei Zhang, Yeonguk Yu et al. Action editor: Stephen Lin https://openreview.net/forum?id=pBI64qNXHp #adaptation #masking #masked

Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees Yilei Chen, Vittorio Giammarino, James Queeney, Ioannis Paschalidis Action editor: Bo Dai https://openreview.net/forum?id=OahvMeRgKP #imitation #adversarial #sampling

When Glass Disappears at Night: A Novel NIR-RGB Multimodal Solution Tao Yan, Yiwei Lu, Ke Xu, Hao Chen, Hui Li, Xiaojun Chang, Xiaojun Wu, Rynson W. H. Lau Action editor: Yuheng Jia https://openreview.net/forum?id=hdh3vHsakv #nighttime #reflectance #rgb

Implicit geometric regularization in flow matching via density weighted Stein operators Shinto Eguchi Action editor: Geoff Pleiss https://openreview.net/forum?id=LBlkVBDRdu #regularization #flows #flow

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answ... Mahdi Astaraki, Mohammad Arshi Saloot, Ali Shiraee Kasmaee et al. Action editor: Zhangyang Wang https://openreview.net/forum?id=pa5TnBdyDP #retrieval #iterative #knowledge

Scalable Ensemble Federated Learning with Enhanced Open-Set Recognition Mustafa Siddiqui, Muhammad Tahir Action editor: Eugene Belilovsky https://openreview.net/forum?id=QnnCYOfuUI #ensemble #averaging #consensus

Random Character-Level Perturbations Amplify LLM Jailbreak Attacks Shuyi Yu, Zhe Cao, Kohei Tsuji et al. Action editor: Hanwang Zhang https://openreview.net/forum?id=BXsOIppKEI #tokenization #jailbreak #adversarially

MSTN: A Lightweight and Fast Model for General Time-Series Analysis Sumit S Shevtekar, Chandresh Kumar Maurya Action editor: Markus Lange-Hegermann https://openreview.net/forum?id=je2N2nnDry #recurrent #temporal #attention

Uncovering Language Model Processing Strategies with Non-Negative Per-Example Fisher Factorization Michael S Matena, Colin Raffel Action editor: Mengnan Du https://openreview.net/forum?id=UjeDVujI8q #learns #factorization #autoencoders

Let Me Explain, Again: Multiplicity in Local Sufficient Explanations Ryan Pilgrim, Beepul Bharti, Kyle Poe, Rene Vidal, Jeremias Sulam Action editor: Dennis Wei https://openreview.net/forum?id=d6FMg4hozX #explanations #classification #feature

Towards Preventing Global Knowledge Forgetting in Federated Learning with Non-IID Data Abhijit Chunduru, Majid Morafah, Mahdi Morafah, Vishnu Pandi Chellapandi, Ang Li Action editor: Gintare Dziugaite https://openreview.net/forum?id=lhTWPh3Tjm #forgetting #federated #ensemble

Discovering Meaningful Units with Visually Grounded Semantics from Image Captions Melika Behjati, James Henderson Action editor: Martha Lewis https://openreview.net/forum?id=kndKGnE0tb #captions #visually #caption

Trip-to-Gaussian: A Versatile Framework for Unconditional 3D Generation Youngwoo Jeon, Inhyeok Choi, Jaehyeok Shim, Sangjune Park, Kyungdon Joo Action editor: Peilin Zhao https://openreview.net/forum?id=9uL23Jcjvj #3d #vision3d #3dgs