iiinova — where your digital self keeps evolving

TMLR Published Papers @tmlr-pub.bsky.social · 1h

New #TMLR-Paper-with-Video: E$^2$M: Double Bounded $\alpha$-Divergence Optimization for Tensor-based Discrete Density Estimation Kazu Ghalamkari, Jesper Løve Hinrich, Morten Mørup tmlr.infinite-conf.org/paper_pages/… #tensor #divergence #optimization

$E$^2$M: Double Bounded $\alpha$-Divergence Optimization for Tensor-based Discrete Density Estimation$

000

TMLR Published Papers @tmlr-pub.bsky.social · 1h

carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks Carolin Benjamins, Helena Graf, Sarah Segel et al. Action editor: Kevin Swersky openreview.net/forum?id=AuA8m4I6zI #benchmarking #benchmarks #optimizers

000

TMLR Published Papers @tmlr-pub.bsky.social · 5h

New #TMLR-Paper-with-Video: Variational Visual Question Answering for Uncertainty-Aware Selective Prediction Tobias Jan Wieczorek, Nathalie Daun, Mohammad Emtiyaz Khan, Marcus Rohrbach tmlr.infinite-conf.org/paper_pages/… #variational #visual #multimodal

000

TMLR Published Papers @tmlr-pub.bsky.social · 5h

A Spectral Bound on Effective Sharpness for Fisher- Preconditioned Gradient Descent Abdul Ahad, Napa Lakshmi Action editor: Matthew Holland openreview.net/forum?id=EabuvggEbb #hessian #optimization #fisher

000

TMLR Published Papers @tmlr-pub.bsky.social · 9h

New #TMLR-Paper-with-Video: On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generali... Matteo Vilucchio, Nikolaos Tsilivis, Bruno Loureiro, Julia Kempe tmlr.infinite-conf.org/paper_pages/… #adversarial #regularization

010

TMLR Published Papers @tmlr-pub.bsky.social · 9h

Learning from Missing Values: Encoding Missingness in Representation-Space for LSTM Time Series F... Jason Kemp, Stefan C. Kremer, Genevieve Ali, Daniel Gillis Action editor: Ying Nian Wu openreview.net/forum?id=DMmCMIrrez #missingness #imputation #lstm

000

TMLR Published Papers @tmlr-pub.bsky.social · 13h

New #TMLR-Paper-with-Video: Unlocking [CLS] Features for Continual Post-Training Murat Onur Yildirim, Elif Ceren Gok Yildirim, Joaquin Vanschoren tmlr.infinite-conf.org/paper_pages/… #learning #forgetting #classifier

000

TMLR Published Papers @tmlr-pub.bsky.social · 13h

New #J2C Certification: The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diff... Siyi Chen, Yimeng Zhang, Sijia Liu, Qing Qu openreview.net/forum?id=CwGv55bbj4 #embeddings #embedding #tokens

000

TMLR Published Papers @tmlr-pub.bsky.social · 13h

Large Scale Empirical Bayesian Causal Discovery Using Total Effect Estimates From Intervention Data Seong Woo Han, Daniel Duy Vo, Brielin C. Brown Action editor: Mingming Gong openreview.net/forum?id=yW4T2fsf0l #causal #prior #discovery

000

TMLR Published Papers @tmlr-pub.bsky.social · 17h

New #TMLR-Paper-with-Video: Fuzzy PyTorch: Rapid Numerical Variability Evaluation for Deep Learning Models Inés Gonzalez Pepe, Hiba Akhaddar, Tristan Glatard, Yohan Chatelain tmlr.infinite-conf.org/paper_pages/… #pytorch #numerical #rounding

010

TMLR Published Papers @tmlr-pub.bsky.social · 17h

AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision Brent Kong, Tejas Ram, Tony Yue YU Action editor: Julian Zimmert openreview.net/forum?id=1z0CnFiJKg #games #play #alphazero

021

TMLR Published Papers @tmlr-pub.bsky.social · 21h

New #TMLR-Paper-with-Video: Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processes Kevin Jatin Vora, Yu Zhang tmlr.infinite-conf.org/paper_pages/… #reinforcement #reward #learning

000

TMLR Published Papers @tmlr-pub.bsky.social · 21h

Generalization Measures under Controlled Covariate Shift: A Regime-Aware Benchmark Sora Nakai, Youssef Fadhloun, Kacem Mathlouthi et al. Action editor: Adams Kong openreview.net/forum?id=X4RoujAYnY #cnn #generalization #classifiers

000

TMLR Published Papers @tmlr-pub.bsky.social · 06/10/2026

New #TMLR-Paper-with-Video: One-Bit Distributed Mean Estimation with Unknown Variance Ritesh Kumar, Shashank Vatedka tmlr.infinite-conf.org/paper_pages/… #estimation #estimate #distributed

000

TMLR Published Papers @tmlr-pub.bsky.social · 06/10/2026

Gradient-based Sample Selection for Faster Bayesian Optimization Qiyu Wei, Haowei Wang, Zirui Cao, Songhao Wang, Richard Allmendinger, Mauricio A Álvarez Action editor: Jeff Phillips openreview.net/forum?id=Ysr1zUeuxz #optimization #surrogate #embeddings

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

New #TMLR-Paper-with-Video: Learning and Transferring Physical Models through Derivatives Alessandro Trenta, Andrea Cossu, Davide Bacciu tmlr.infinite-conf.org/paper_pages/… #learning #models #derivatives

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

Conformal Prediction for Generative Models via Adaptive Cluster-Based Density Estimation Qidong Yang, Qianyu Julie Zhu, Jonathan Giezendanner et al. Action editor: Fred Roosta openreview.net/forum?id=goxeVsh9Po #generative #prediction #models

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

New #TMLR-Paper-with-Video: A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation Xinjie Liu, Cyrus Neary, Kushagra Gupta et al. tmlr.infinite-conf.org/paper_pages/… #reinforcement #reinforce #trained

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

Unifying Understanding and Generation in Vision-Language Models: Advances, Challenges, and Opport... Xiaocheng Lu, Ziyue Ma, Jie ZHANG, Jian Liu, Song Guo Action editor: Yu-Xiong Wang openreview.net/forum?id=AIMmeOrVFL #multimodal #visual #representations

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

New #TMLR-Paper-with-Video: Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers M Yashwanth, Sharannya Ghosh, Aditay Tripathi, Anirban Chakraborty tmlr.infinite-conf.org/paper_pages/… #prompts #prompt #contextualized

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

A Moving-Horizon Approximate Branch-and-Reduce Method for Deep Classification Trees Chenxuanyin Zou, Jiayang Ren, Qiangqiang Mao, Jing Liu, Marcus Lai, Yankai Cao Action editor: Taylor Killian openreview.net/forum?id=4Sq5Byd4yS #tree #subtree #trees

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

New #TMLR-Paper-with-Video: Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Alexandros Doumanoglou, Kurt Driessens, Dimitrios Zarpalas tmlr.infinite-conf.org/paper_pages/… #decoding #autoencoder #representations

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

Adapting Vision Foundation Models with Cascaded Semantics Xi Xiao, Xingjian Li, Cheng Han et al. Action editor: Matias Valdenegro-Toro openreview.net/forum?id=SSsobNZJPO #attention #adapting #adaptation

010

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

New #TMLR-Paper-with-Video: Multiscale Training of Convolutional Neural Networks Shadab Ahamed, Niloufar Zakariaei, Eldad Haber, Moshe Eliasof tmlr.infinite-conf.org/paper_pages/… #multiscale #cnn #cnns

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

Auditing GeoFM Evaluation for Field-Extent Segmentation: Label Proxies, Baselines, and When Froze... Santosh Pant Action editor: Simone Scardapane openreview.net/forum?id=qRXVTe1yYp #cropland #land #forest

000

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

New #TMLR-Paper-with-Video: Gaga: Group Any Gausians via 3D-aware Memory Bank Weijie Lyu, Xueting Li, Abhijit Kundu, Yi-Hsuan Tsai, Ming-Hsuan Yang tmlr.infinite-conf.org/paper_pages/… #3d #gaga #scenes

010

TMLR Published Papers @tmlr-pub.bsky.social · 05/10/2026

Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models Vijay Sadashivaiah, George Dasoulas, Judith Mueller, Soumya Ghosh Action editor: Ole Winther openreview.net/forum?id=GxmQsP5CcU #softmax #sigmoid #attention

010

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

New #TMLR-Paper-with-Video: HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs Tin Nguyen, Logan Bolton, Mohammad Reza Taesiri, Trung Bui, Anh Totti Nguyen tmlr.infinite-conf.org/paper_pages/… #prompting #supervised #reasoning

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance Miao Lin, Feng Yu, Rui Ning et al. Action editor: Joonas Jälkö openreview.net/forum?id=WyPkotlgqQ #backdoor #vulnerability #detectability

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

New #TMLR-Paper-with-Video: ECLipsE-Gen-Local: Efficient Compositional Local Lipschitz Estimates for Deep Neural Networks Yuezhu Xu, S Sivaranjani tmlr.infinite-conf.org/paper_pages/… #neural #networks #lipschitz

010

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

New #Reproducibility Certification: Anchored Augmentation: Constructing Training Data for Deep Cellular Deconvolution from Paired Pil... Jason Thomo, Yushan Hu, Alex Thomo, Xuekui Zhang openreview.net/forum?id=FG7PlICeut #rna #2drna #bulk

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

Privacy Leakage via Output Label Space and Differentially Private Continual Learning Marlon Tobaben, Talal Alrawajfeh, Marcus Klasson et al. Action editor: Sanghyun Hong openreview.net/forum?id=ZshFgRQWrm #privacy #private #imagenet

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

New #TMLR-Paper-with-Video: $\texttt{SEM-CTRL}$: Semantically Controlled Decoding Mohammad Albinhassan, Pranava Madhyastha, Alessandra Russo tmlr.infinite-conf.org/paper_pages/… #parsing #semantics #semantic

$$\texttt{SEM-CTRL}$: Semantically Controlled Decoding$

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

FastAvatar: Single-Image 3D Gaussian Face Avatars through Canonical Template and Residual Learning Hao Liang, Zhixuan Ge, Soumendu Majee et al. Action editor: Zhixiang Wang openreview.net/forum?id=4WnbCj0v0K #face #avatars #3d

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

New #TMLR-Paper-with-Video: Towards Online Multimodal Social Interaction Understanding Xinpeng Li, Shijian Deng, Bolin Lai, Weiguo Pian, James Matthew Rehg, Yapeng Tian tmlr.infinite-conf.org/paper_pages/… #multimodal #conversation #conversational

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

On the Scaling Flaws of Verifier-Guided Beam Search in Mathematical Reasoning Fei Yu, Yingru Li, Benyou Wang Action editor: Geoff Pleiss openreview.net/forum?id=D5VKbIzlrR #benchmarks #scaling #reasoning

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

New #TMLR-Paper-with-Video: Model-Free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach Han Wang, Leonardo Felipe Toso, Aritra Mitra, James Anderson tmlr.infinite-conf.org/paper_pages/… #agents #federated #agent

020

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence Xuanle Zhao, Qiushi Sun, Jingyu Xiao et al. Action editor: Alessandro Sordoni openreview.net/forum?id=pn2sdu3Vrf #visual #multimodal #visually

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

New #TMLR-Paper-with-Video: When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models Raphaël Razafindralambo, Rémy Sun, Damien Garreau et al. tmlr.infinite-conf.org/paper_pages/… #score_diffusion_ensemble #ensembles #ensembling

000

TMLR Published Papers @tmlr-pub.bsky.social · 04/10/2026

Legal Retrieval for Public Defenders Dominik Stammbach, Kylie Zhang, Patty Liu et al. Action editor: Huaxiu Yao openreview.net/forum?id=HnbKQGRnDt #appellate #retrieval #law

000

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

New #TMLR-Paper-with-Video: GraphGini: Fostering Individual and Group Fairness in Graph Neural Networks Anuj Kumar Sirohi, Anjali Gupta, Sandeep Kumar, Amitabha Bagchi, Sayan Ranu tmlr.infinite-conf.org/paper_pages/… #graphgini #fairness #networks

000

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

Aletheia: What Makes RLVR For Code Verifiers Tick? Vatsal Venkatkrishna, Indraneil Paul, Iryna Gurevych Action editor: Hugo Touvron openreview.net/forum?id=3rVrBGp0mr #rlvr #trained #verifier

001

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

New #TMLR-Paper-with-Video: SaFARi: State-Space Models for Frame-Agnostic Representation Hossein Babaei, Mel White, Sina Alemohammad, Richard Baraniuk tmlr.infinite-conf.org/paper_pages/… #frame #basis #representation

000

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

Auditing Closed-Loop Learning in Recurrent Neural Networks: Reproduction, Robustness, and General... Aarav Sinha Action editor: Nadav Cohen openreview.net/forum?id=e0pSqIqwXO #rnns #rnn #reproducibility

000

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

New #TMLR-Paper-with-Video: Node Duplication Improves Cold-start Link Prediction Zhichun Guo, Tong Zhao, Yozen Liu et al. tmlr.infinite-conf.org/paper_pages/… #nodedup #nodes #node

000

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

DeGLIF for Label Noise Robust Node Classification using GNNs Pintu Kumar, Nandyala Hemachandra Action editor: Yu Yao openreview.net/forum?id=pcs5DmBtUJ #graph #denoising #denoise

000

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

New #TMLR-Paper-with-Video: Explaining with trees: interpreting CNNs using hierarchies Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman tmlr.infinite-conf.org/paper_pages/… #cnns #interpretability #explanations

042

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

Decomposable Neural Symbolic Regression Giorgio Morales, John Sheppard Action editor: Shiyu Chang openreview.net/forum?id=54EL928uCf #regression #symbolic #prediction

010

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

New #TMLR-Paper-with-Video: CXAD: Contrastive Explanations for Anomaly Detection: Algorithms, Complexity Results and Experiments Ian Davidson, Nicolás Kennedy, S. S. Ravi tmlr.infinite-conf.org/paper_pages/… #outliers #explanations #outlier

000

TMLR Published Papers @tmlr-pub.bsky.social · 03/10/2026

Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory Zhaotian Gu, Jie SU, Weiwei Wang, Chang Liu, Tianyi Qian, Dahui Wang Action editor: Gitta Kutyniok openreview.net/forum?id=a43l19lyfC #rnns #normalization #backpropagation

000