iiinova — where your digital self keeps evolving

TMLR Published Papers @tmlr-pub.bsky.social · 2m

Scene Layout Generation with Rectified Flow Cameron Braunstein, Hevra Petekkaya, Jan Eric Lenssen, Mariya Toneva, Eddy Ilg Action editor: Zhe Gan openreview.net/forum?id=YGsQxG5ubd #layouts #layout #scene

000

TMLR Published Papers @tmlr-pub.bsky.social · 4h

Generate the Forest before the Trees - A Hierarchical Diffusion model for Climate Downscaling Declan Jacques Curran, Sanaa Hobeichi, Hira Saleem, Hao Xue, Flora D. Salim Action editor: Russell Tsuchida openreview.net/forum?id=OhTYgFpMU2 #downscaling #downsampling #climate

000

TMLR Published Papers @tmlr-pub.bsky.social · 8h

ESLM: Risk-Averse Selective Language Modeling with Hierarchical Batch Selection Melis Ilayda Bal, Volkan Cevher, Michael Muehlebach Action editor: Tianlong Chen openreview.net/forum?id=vcynsg6rMN #risk #token #batch

000

TMLR Published Papers @tmlr-pub.bsky.social · 12h

Scaling Agents for Computer Use Gonzalo Gonzalez-Pumariega, Vincent Tu, Chih-Lun Lee, Jiachen Yang, Ang Li, Xin Eric Wang Action editor: Yi R. Fung openreview.net/forum?id=eve4jBYa8D #agent #agents #androidworld

000

TMLR Published Papers @tmlr-pub.bsky.social · 15h

New #Survey Certification: Diffusion Models in Simulation-Based Inference: A Tutorial Review Jonas Arruda, Niels Leif Bracher, Ullrich Koethe, Jan Hasenauer, Stefan T. Radev openreview.net/forum?id=86Q261z005 #modeling #models #diffusion

010

TMLR Published Papers @tmlr-pub.bsky.social · 16h

A Symmetry-Matching Approach to Blind-Spot Reduction in Sparse Autoencoders Csaba Balogh Action editor: David Rügamer openreview.net/forum?id=NWWpKC9CZH #autoencoders #autoencoder #regularisation

000

TMLR Published Papers @tmlr-pub.bsky.social · 20h

TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting Lingyu Jiang, Lingyu Xu, Peiran Li et al. Action editor: Andres Masegosa openreview.net/forum?id=yQLnvkJMbP #timepre #forecasting #perceptron

000

TMLR Published Papers @tmlr-pub.bsky.social · 23h

When Vision Needs a Second Look: Tool-Augmented Active Perception for Earth Observation Atul Dev, Shivank Garg, Gaurav Kumar Nayak Action editor: Georgios Leontidis openreview.net/forum?id=7yUrnyFgEq #agent #agentic #autonomous

020

TMLR Published Papers @tmlr-pub.bsky.social · 30/09/2026

Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond Weiyu Chen, Baijiong Lin, Xiaoyuan Zhang, Xi Lin, Han Zhao, Qingfu Zhang, James Kwok Action editor: George Trimponias openreview.net/forum?id=eCUcXXH3PS #objective #objectives

010

TMLR Published Papers @tmlr-pub.bsky.social · 30/09/2026

New #Reproducibility Certification: A Reproduction Study of Weight-Based Mechanistic Interpretability in Bilinear MLPs Itay Erlich, May Ben Zion, Jacob Shashoua openreview.net/forum?id=6k7qRdz7rD #autoencoders #interpretability #interpretable

010

TMLR Published Papers @tmlr-pub.bsky.social · 30/09/2026

Efficient Image Restoration with State-Dependent Forward Diffusion Ziwei Luo, Fredrik K. Gustafsson, Jens Sjölund, Thomas B. Schön Action editor: Changyou Chen openreview.net/forum?id=Eq9k6Va3hY #diffusion #restoration #stochastic

010

TMLR Published Papers @tmlr-pub.bsky.social · 29/09/2026

TreeSMOTE: Structure-Aware Data Augmentation for Imbalanced Tabular Learning Peng Wang, Hangting Ye, He Zhao, Jinhan Liu, Dandan Guo, Quan Zhang Action editor: Kenta Oono openreview.net/forum?id=OelOS8cbBY #generative #classifier #classification

000

TMLR Published Papers @tmlr-pub.bsky.social · 29/09/2026

WorldPack: Dynamic Frame Compression for Long-context Video World Modeling Yuta Oshima, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta Action editor: Miguel Bautista openreview.net/forum?id=zJuiG3PiNJ #frames #3d #frame

000

TMLR Published Papers @tmlr-pub.bsky.social · 29/09/2026

TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning Fangxu Yu, Hongyu Zhao, Tianyi Zhou Action editor: Jimin Huang openreview.net/forum?id=d6TD0f2xXq #forecasting #reasoner #reasoning

001

TMLR Published Papers @tmlr-pub.bsky.social · 29/09/2026

New #J2C Certification: Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures Marco Bronzini, Carlo Nicolini, Bruno Lepri, Jacopo Staiano, Andrea Passerini openreview.net/forum?id=WxM7lIoGBb #autoencoders #hypervector #representations

000

TMLR Published Papers @tmlr-pub.bsky.social · 29/09/2026

A Survey on Hallucination in Video Understanding: Taxonomy, Causes, and Mitigation Techniques Jiayi Sheng, Wei Luo, Wotao Yin Action editor: Chen Sun openreview.net/forum?id=qbO71rVrIG #multimodal #captioning #hallucination

000

TMLR Published Papers @tmlr-pub.bsky.social · 29/09/2026

Exploiting Completeness Perception with Diffusion Transformer for Unified 3D MRI Synthesis Junkai Liu, Nay Aung, Theodoros N. Arvanitis et al. Action editor: Mehrtash Harandi openreview.net/forum?id=DCaolE9oBN #generative #mdit3d #mri

000

TMLR Published Papers @tmlr-pub.bsky.social · 29/09/2026

CURE-OOD: Benchmarking Out-of-Distribution Detection for Survival Prediction Wenjie Zhao, Jia Li, Mingrui Liu, Jing Wang, Yunhui Guo Action editor: Seungjin Choi openreview.net/forum?id=fziI7nE1vO #cancer #survival #prediction

000

TMLR Published Papers @tmlr-pub.bsky.social · 28/09/2026

Semantic F1 Scores: Fair Evaluation Under Fuzzy Class Boundaries Georgios Chochlakis, Jackson Trager, Vedant Vipul Jhaveri et al. Action editor: Jingyan Wang openreview.net/forum?id=U0YJpGuFEc #semantic #classification #fuzzy

000

TMLR Published Papers @tmlr-pub.bsky.social · 28/09/2026

From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning Manish Kumar, Anton Frederik Thielmann, Christoph Weisser, Benjamin Säfken Action editor: Sameer Deshpande openreview.net/forum?id=str7wQt9Qc #splines #knots #knot

000

TMLR Published Papers @tmlr-pub.bsky.social · 28/09/2026

SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign Jiarui Lu, Yuyang Wang, Yizhe Zhang et al. Action editor: Tianshu Yu openreview.net/forum?id=wPfw7GkMns #autoencoders #autoencoder #proteins

011

TMLR Published Papers @tmlr-pub.bsky.social · 28/09/2026

LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss Szilvia Ujváry, Louis Béthune, Pierre Ablin, Joao Monteiro, marco cuturi, Michael Kirchhof Action editor: Mengnan Du openreview.net/forum?id=JxVxBa3wO5 #learnability #language #learn

000

TMLR Published Papers @tmlr-pub.bsky.social · 28/09/2026

Understanding and Mitigating Overconfidence in Focus Group Surveys Karush Suri, Konstantinos N. Plataniotis, Yuri Andrew Lawryshyn Action editor: Xuanjing Huang openreview.net/forum?id=NGuOZYQZBq #confidence #feedback #verbalized

000

TMLR Published Papers @tmlr-pub.bsky.social · 28/09/2026

Gradient Heterogeneity Complements Hessian Heterogeneity in Transformer Optimization Akiyoshi Tomihari, Issei Sato Action editor: Konstantin Mishchenko openreview.net/forum?id=wZJcQb5m1e #transformer #optimizers #sgd

000

TMLR Published Papers @tmlr-pub.bsky.social · 27/09/2026

Efficient LLM Collaboration via Planning Byeongchan Lee, Jonghoon Lee, Dongyoung Kim et al. Action editor: Weitong Zhang openreview.net/forum?id=RPzbeL0koP #planner #planning #collaborate

000

TMLR Published Papers @tmlr-pub.bsky.social · 27/09/2026

Compress--Add--Smooth: Fixed-Budget Temporal Compression of Density-Valued Streams Michael Chertkov Action editor: Valentin De Bortoli openreview.net/forum?id=wjoixYG0mC #streams #memory #replay

000

TMLR Published Papers @tmlr-pub.bsky.social · 27/09/2026

FairNVT: Fair Classification via Noise Injection in Vision Transformers Qiaoyue Tang, Sepidehsadat Hosseini, Mengyao Zhai, Thibaut Durand, Greg Mori Action editor: Yani Ioannou openreview.net/forum?id=rzm6gZrYgl #fairnvt #fairness #encoders

000

TMLR Published Papers @tmlr-pub.bsky.social · 27/09/2026

A Benchmark for Vericoding: Formally Verified Program Synthesis Ionel Emilian Chiosa, Sergiu Bursuc, Theodore Ehrenborg et al. Action editor: Serguei Barannikov openreview.net/forum?id=Zgh5kpGAm8 #vericoding #coding #benchmark

000

TMLR Published Papers @tmlr-pub.bsky.social · 27/09/2026

Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and ... Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo, Christina Lioma Action editor: Anirbit Mukherjee openreview.net/forum?id=VxZd6HfMOo #attention #memory #pruning

000

TMLR Published Papers @tmlr-pub.bsky.social · 27/09/2026

New #J2C Certification: Evaluating the evidence trace of NeurIPS 2025 contributions with agentic code auditing Pascal Iversen, Ferdous Nasri, Bernhard Y Renard, Katharina Baum openreview.net/forum?id=xjCJY8Xxcm #auditing #reproducibility #auditowl

000

TMLR Published Papers @tmlr-pub.bsky.social · 27/09/2026

Dynamic Subspace Estimation from Undersampled Data using Grassmannian Geodesics Soo Min Kwon, Cameron James Blocker, Haroon Raja, Jeffrey A Fessler, Laura Balzano Action editor: Mathieu Salzmann openreview.net/forum?id=W0ZNwXoBeh #grassmannian #grassmann #undersampled

000

TMLR Published Papers @tmlr-pub.bsky.social · 26/09/2026

Yose-Ue: A Treap-Based Ensemble Framework for Resource-Efficient Unsupervised Anomaly Detection Eduardo Ortega, Gautam Dasarathy, Krishnendu Chakrabarty Action editor: Chuan Sheng Foo openreview.net/forum?id=17y2ooyemG #anomaly #ensemble #outlier

000

TMLR Published Papers @tmlr-pub.bsky.social · 26/09/2026

A Robust $\widetilde{\mathcal{O}}(1/\sqrt{T})$ Rate for Unprojected TD Learning with Linear Funct... Wei-Cheng Lee, Francesco Orabona Action editor: Yue Wang openreview.net/forum?id=Tj1B5WDyt8 #regularity #approximation #robust

000

TMLR Published Papers @tmlr-pub.bsky.social · 26/09/2026

New #Reproducibility Certification: A Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysis Yehudit Aperstein, Alexander Apartsin openreview.net/forum?id=tmNAKpmSaF #annotate #annotation #annotated

000

TMLR Published Papers @tmlr-pub.bsky.social · 26/09/2026

Density-Scaled Regularization for Offline Reinforcement Learning Jacky Xie, Nan Ye Action editor: Yue Wang openreview.net/forum?id=nDPrzkQTj1 #regularization #regularized #regularizing

010

TMLR Published Papers @tmlr-pub.bsky.social · 26/09/2026

Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control Carles Domingo-Enrich, Jiequn Han Action editor: Arto Klami openreview.net/forum?id=tR5VsdQFhK #stochastic #martingale #optimal

000

TMLR Published Papers @tmlr-pub.bsky.social · 26/09/2026

Benchmarking Transfer Learning: From Simple Baselines to Combined Scorers for Transferability Est... Levy Chaves, Claudio Mayrink Verdun, Eduardo Valle, Sandra Avila Action editor: Dmitry Kangin openreview.net/forum?id=3i2ZRk8GDN #imagenet #transferability #benchmarking

000

TMLR Published Papers @tmlr-pub.bsky.social · 26/09/2026

FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks Syed A Rizvi, Nazreen Pallikkavaliyaveetil MohammedSheriff, David Zhang et al. Action editor: Zhengzhang Chen openreview.net/forum?id=fj7sjOwtXc #attention #graphs #graph

000

TMLR Published Papers @tmlr-pub.bsky.social · 25/09/2026

Detecting Distributional Treatment Responders with False Discovery Rate Control Tzviel Frostig, Bradley P. Carlin, Elad Berkman, Amitay Kamber, Raviv Pryluk Action editor: Arash Mehrjou openreview.net/forum?id=zPt0o32mYn #propensity #causal #outcomes

000

TMLR Published Papers @tmlr-pub.bsky.social · 25/09/2026

EFFEKT: Efficient Federated Knowledge Transfer to Foundation Models Matteo Caligiuri, Francesco Barbato, Pietro Zanuttigh, Francesco Restuccia Action editor: Hsuan-Tien Lin openreview.net/forum?id=jpUDUJfE1K #federated #proxy #privacy

000

TMLR Published Papers @tmlr-pub.bsky.social · 25/09/2026

Optimization as a Dynamical System: Generative Schedules from Latent ODEs Matt L. Sampson, Peter Melchior Action editor: Bruno Loureiro openreview.net/forum?id=SwmzJgB9TA #cnn #prediction #trained

000

TMLR Published Papers @tmlr-pub.bsky.social · 25/09/2026

ImpMIA: Leveraging Implicit Bias for Membership Inference Attack Yuval Golbari, navve wasserman, Gal Vardi, michal Irani Action editor: Jonathan Ullman openreview.net/forum?id=34bnVED6EZ #attacks #attacker #privacy

000

TMLR Published Papers @tmlr-pub.bsky.social · 25/09/2026

Riemannian t-SNE on Several Matrix Manifolds Rui Wang, Bin Shi, Chen Hu, Tianyang Xu, Xiaojun Wu, Nicu Sebe, Ziheng Chen Action editor: Bamdev Mishra openreview.net/forum?id=4EZeC0JwqM #manifolds #manifold #dimensionality

030

TMLR Published Papers @tmlr-pub.bsky.social · 25/09/2026

Centroid-Referenced Mahalanobis Matching (CRM): A Scalable, Representation-Based Framework for Ca... Keming Hu, Yingpei He Action editor: Jiwei Zhao openreview.net/forum?id=z74epfCe3A #matching #mahalanobis #centroid

001

TMLR Published Papers @tmlr-pub.bsky.social · 24/09/2026

New #Reproducibility Certification: Training-Free Modality-Agnostic Concept Sliders: Fine-Grained Control via Diffusion Models of Ima... Rotem Ezra, Hedi Zisling, Nimrod Berman et al. openreview.net/forum?id=m2hpORnHhF #generative #modality #benchmark

000

TMLR Published Papers @tmlr-pub.bsky.social · 24/09/2026

FARM: Enhancing Molecular Representations with Functional Group Awareness Thao Nguyen, Kuan-Hao Huang, Ge Liu, Martin D. Burke, Ying Diao, Heng Ji Action editor: Christopher Morris openreview.net/forum?id=2All12TFlh #farm_molecular_representation #moleculenet #molecular

000

TMLR Published Papers @tmlr-pub.bsky.social · 24/09/2026

Revealing Positive and Negative Role Models to Help People Make Good Decisions Avrim Blum, Keziah Naggita, Matthew Walter, Jingyan Wang Action editor: Shahin Jabbari openreview.net/forum?id=jdcXfoENf0 #welfare #agents #optimal

000

TMLR Published Papers @tmlr-pub.bsky.social · 24/09/2026

New #Featured Certification: OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference Zhuoyuan Wang, Hanjiang Hu, Xiyu Deng, Saviz Mowlavi, Yorie Nakahira openreview.net/forum?id=rCTRgstMr1 #parameterization #pdes #pde

010

TMLR Published Papers @tmlr-pub.bsky.social · 24/09/2026

Missing Value Uncertainty: Could Collecting Missing Values Change the Prediction? David J. Burnett, Surojit Ganguli, Lance M. Kaplan, Devesh Upadhyay, David I. Inouye Action editor: Michele Caprio openreview.net/forum?id=BRWTS5e03Z #prediction #estimation #uncertainty

000

TMLR Published Papers @tmlr-pub.bsky.social · 24/09/2026

OTIS: Learning High-Quality Time Series Features With Tiny Encoders Özgün Turgut, Philip Müller, Martin J. Menten, Daniel Rueckert Action editor: Adín Ramírez Rivera openreview.net/forum?id=WW206A1Tru #encoders #encoder #memory

000