TMLR Published Papers

Approaching the Harm of Gradient Attacks While Only Flipping Labels Abdessamad El-Kabid, El-Mahdi El-Mhamdi Action editor: Sijia Liu https://openreview.net/forum?id=eAqBcljvsU #adversarial #adversary #attacks

Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Pro... Francesca Lanzillotta, Chiara Albisani, Davide Pucci et al. Action editor: Ahmet Alacaoglu https://openreview.net/forum?id=Xi1UWSFooI #constraints #constrained #optimization

From Connectivity to Rewards: Dense Reward Learning with Directed State Graphs Shuyuan Zhang, Zihan Wang, Xiao-Wen Chang, Doina Precup Action editor: Erin Talvitie https://openreview.net/forum?id=F65zrefsjB #reinforcement #planning #reward

Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models Zinan Lin, Tadas Baltrusaitis, Wenyu Wang, Sergey Yekhanin Action editor: Kamalika Chaudhuri https://openreview.net/forum?id=GMoM2QpYuz #simulators #private #privacy

ToolGuard: Red-Teaming Small Language Model Tool Calling on Consumer Hardware Ravitez Dondeti Action editor: Kamalika Chaudhuri https://openreview.net/forum?id=0ct01Da0Ff #toolguard #adversarial #tool

Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms Andreas Boltres, Niklas Freymuth, Benjamin Schichtholz, Michael König, Gerhard Neumann Action editor: Ian Kash https://openreview.net/forum?id=jmk2SoQklg #telemetry #routing #delays

Text2Smell: Emergent Representations of Human Olfactory Perception in Large Language Models Farzaneh Taleb, Shirin Tahmasebi, Miguel Vasco, Danica Kragic Action editor: Xuanjing Huang https://openreview.net/forum?id=zXQWUqMijT #olfactory #smell #perceive

Alignment of Diffusion Model and Flow Matching for Text- to-Image Generation Yidong Ouyang, Liyan Xie, Guang Cheng, Hongyuan Zha Action editor: Changyou Chen https://openreview.net/forum?id=axRaqhyahn #generative #flow #adversarial

VAE-Inf: A Statistically Interpretable Generative Paradigm for Imbalanced Classification Hongfei Wu, Ruijian Han, Yancheng Yuan Action editor: Long Chen https://openreview.net/forum?id=XSgjCi4iCf #generative #autoencoder #encoder

Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing Zeji Yi, Chaoyi Pan, Guanya Shi, Guannan Qu Action editor: Franck Iutzeler https://openreview.net/forum?id=8Nx1ZjfEhd #optimization #optimality #nonconvex

When is More Better? Efficient and Adaptive Modality Acquisition in Multimodal Learning Matthew Peroni, Paul Pu Liang, Dimitris Bertsimas Action editor: Qi Yu https://openreview.net/forum?id=gnJNCIPO6y #multimodal #modality #adaptive

ViDE: Tuning-Free Video Coherence via Temporal Attention Reweighting and Prompt Blending Xingyao Li, Hao Zhang, Fengzhuo Zhang et al. Action editor: Long Chen https://openreview.net/forum?id=A5WZZxglxT #attention #editing #vide

Policy Gradients for Cumulative Prospect Theory in Reinforcement Learning Olivier Lepel, Anas Barakat Action editor: Amir-massoud Farahmand https://openreview.net/forum?id=6iGrtiSCR7 #reinforcement #risk #prospect

New #Reproducibility Certification: Reproducibility study of "Bilinear MLPs enable weight-based mechanistic interpretability" Hamid Reza Ahmadi, Mihnea Andrei Bârsan, Jan Jelínek, Robert-Ștefan Sofroni https://openreview.net/forum?id=Bnx3hf3mWp #imagenet #features #interpretability

A Behavior-first approach to Multi-Intention Inverse Reinforcement Learning Antonio Mone, Frans A Oliehoek, Luciano Cavalcante Siebert Action editor: Mirco Mutti https://openreview.net/forum?id=42kUyc9KGs #learns #reinforcement #generative

ZSQ4MIL: Zero-shot Quantization for Multiple InstanceLearning Fanyi Zeng, Xinrui Chen, Yizhi Wang et al. Action editor: Gang Niu https://openreview.net/forum?id=D1gvKw1397 #instancelearning #quantization #instances

Attention by Synchronization in Coupled Oscillator Networks Fabio Pasqualetti, Taosha Guo Action editor: Christian Keup https://openreview.net/forum?id=T9g7VleXf2 #oscillators #oscillator #attention

[Re] Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning Andrei Gruzitski, Anton Nuzhdin, Balázs Egyed, Aleksandr Raudvee Action editor: Pin-Yu Chen https://openreview.net/forum?id=uPXRBZfkYy #saliency #adversarial #visual

Action-Conditioned Transformers for Decentralized Multi-Agent World Models Victor Augusto Kich, Satoshi Yamamori, Junior Costa De Jesus, Jun Morimoto Action editor: Sebastian Trimpe https://openreview.net/forum?id=99nyrFfTJf #reinforcement #planning #starcraft

Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and... Julien Colin, Lore Goetschalckx, Thomas Fel, Victor Boutin, Thomas Serre, Nuria M Oliver Action editor: Sinead Williamson https://openreview.net/forum?id=vb57jDotru #interpretability

TriScore: Post-Hoc Out-of-Distribution Detection with Energy, Boundary Probes, and Transform Cons... Ege Gursoy, Nicolas Mansard Action editor: Changjian Shui https://openreview.net/forum?id=H5hyDKANup #adversarial #detection #detector

WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation Yu-Hsiang Wang, Olgica Milenkovic Action editor: Peilin Zhao https://openreview.net/forum?id=YSTJ71fDBm #waveletdiff #wavelet #forecasting

On the Expressive Power and Limitations of Multi-Layer SSMs Nikola Zubic, Qian Li, Yuyi Wang, Davide Scaramuzza Action editor: Ellen Vitercik https://openreview.net/forum?id=NQ8IcsIti8 #depth #expressive #hierarchy

Subspace Inference Enables Efficient Active Reward Learning from Preferences Yutai Zhou, Erdem Biyik Action editor: Adam White https://openreview.net/forum?id=ckWRSrY8i4 #bayesian #reinforcement #reward

New #J2C Certification: Compute Optimal Tokenization Tomasz Limisiewicz, Artidoro Pagnoni, Srini Iyer et al. https://openreview.net/forum?id=zLjMDBaOek #tokenization #tokenized #tokenizer

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory Einar Urdshals, Edmund Lau, Jesse Hoogland, Stan van Wingerden, Daniel Murfet Action editor: Marco Mondelli https://openreview.net/forum?id=mJVJ2FcbBC #compressibility #compression

On-Policy Model Error Suffices: An Invariant-Measure Return-Gap Bound for Model-Based Reinforcem... Minh Nhat VU Action editor: Steffen Udluft https://openreview.net/forum?id=qDJ8axLhMa #reinforcement #dynamics #drift

Faithful Image Editing via Degraded Representations Shahin Hakemi, NAVEED AKHTAR, Ghulam Mubashar Hassan, Ajmal Saeed Mian Action editor: Alain Oliviero Durmus https://openreview.net/forum?id=U2fY7u10QY #flow #generative #editing

Review of Reinforcement Learning for Large Language Models: Formulations, Algorithms, and Opportu... Ziniu Li, Pengyuan Wang, Tian Xu, Tian Ding, Ruoyu Sun, Yang Yu Action editor: Kamil Ciosek https://openreview.net/forum?id=ghQQNjSxJc #reinforcement #supervised #language

Bridging the High-Frequency Data Gap: A Millisecond-Resolution Network Dataset for Advancing Time... Subina Khanal, Seshu Tirupathi, Merim Dzaferagic, Marco Ruffini, Torben Bach Pedersen Action editor: Jacek Cyranka https://openreview.net/forum?id=dMlzHYA13f #forecasting #5g

Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distilla... Robert M. Gower, Guillaume Garrigos, Nicolas Loizou et al. Action editor: Bruno Loureiro https://openreview.net/forum?id=lNRBJekTFX #stochastic #optimal #polyak

CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated? Jonathan Sadeghi, Jenny Seidenschwarz, Jesse Allardice et al. Action editor: Chongxuan Li https://openreview.net/forum?id=rWE29rkvDz #benchmark #benchmarks #accuracy

New #J2C Certification: Anomaly-Gym: A Benchmark for Anomaly Detection in Reinforcement Learning Environments Tom Haider, Sven Gronauer, Karsten Roscher, Stephan Günnemann https://openreview.net/forum?id=fDUb0A1DBA #anomaly #reinforcement #anomalies

Build-Bench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software Zehua Zhang, Ati Priya Bajaj, Divij Handa et al. Action editor: Alessandro Sordoni https://openreview.net/forum?id=BxJnz9EqO5 #compilation #builds #compiling

Structured Semantics Meet Uncertain Visuals: A Unified Approach to Calibrated Test-Time Prompt Tu... Hariseetharam Gunduboina, Panav Shah, Mainak Singha et al. Action editor: Tim Rudner https://openreview.net/forum?id=eY1W8h2sWC #visual #conditioned #benchmarks

New #J2C Certification: Neural Boundary Integral Operators: Solver-Consistent Learning Across Geometry, Resolution, and K... Jae Mo Shin https://openreview.net/forum?id=K8fA2QOlV8 #boundary #laplace #helmholtz

DisCoVAE: Disentangling pretrained latent spaces with customized controls using contrastive learning Sarah Nabi, Philippe Esling, Frédéric Bevilacqua, Geoffroy Peeters, Tatsuya Harada Action editor: Andriy Mnih https://openreview.net/forum?id=npPuLfIutr #autoencoder #generative

FedSCM: Federated Domain Adaptation via Sparse Consensus Matching Gita Sarafraz, Amir Najafi, Hamid R. Rabiee Action editor: Konstantin Mishchenko https://openreview.net/forum?id=MXKRLoCi1o #federated #sparse #regularized

Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image C... Kazuki Adachi, Shin'ya Yamaguchi, Tomoki Hamagami Action editor: Massimiliano Mancini https://openreview.net/forum?id=YELPe35KIg #adaptation #trained #uniformity

GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody ... Amit Parekh, Sabrina McCallum, Kareem AlHasan et al. Action editor: Xinrun Wang https://openreview.net/forum?id=BXJlDltbtq #collaborate #collaboratively #collaborative

GhostWord: A Fine-Grained Backdoor Attack on Automatic Speech Recognition Mojtaba Nafez, Mobina Poulaei, Kiarash Kiani Feriz et al. Action editor: Li Li https://openreview.net/forum?id=vngoPfQCJf #ghostword #backdoors #speecht5

Boundary-Consistent Graph Neural Networks for Topological Flux Prediction Haoyang Jiang, Bojian Qu, Xingquan Zhu, Jifu Tan, Yi He Action editor: Xiao Luo https://openreview.net/forum?id=31gTIfhoH0 #flux #boundaries #boundary

New #Reproducibility Certification: Leadership as Coordination Control: Behavioral Signatures and the Recovery-Advantage Boundary in ... Haewoon Kwak https://openreview.net/forum?id=gp77UrXyjT #coordination #leadership #behavioral

Scaling Online Complex Event Detection with Synthetic Supervision and Mamba-Based Neural Algorith... Liying Han, Gaofeng Dong, Xiaomin Ouyang et al. Action editor: Salman Khan https://openreview.net/forum?id=UJwnFHlqEf #semantics #events #event

Revisiting RegressionMSR: A Reproducibility Study Neev Mistry Action editor: Olawale Salaudeen https://openreview.net/forum?id=AzOk6sdMRZ #regressionmsr #reproducibility #reproducible

New #Featured Certification: From Images to Signals: Are Image-Pretrained Vision Models Useful for Time Series Analysis? ChengAo Shen, Hanghang Tong, Dongjin Song, Zhigang Deng, Qingsong Wen, Jingchao Ni https://openreview.net/forum?id=aWVG2rN4OV #forecasting #forecaster #lvms

Longitudinal Evaluation of Large Language Models Sourav Majumdar, Nivedita Bhaktha Action editor: Olawale Salaudeen https://openreview.net/forum?id=INuSvLC7Bq #benchmarks #gpt #benchmark

Open Vocabulary Compositional Explanations for Neuron Alignment Biagio La Rosa, Leilani H. Gilpin Action editor: Martha Lewis https://openreview.net/forum?id=iS38vzTMdd #neuron #neurons #semantic

Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning... Che Shen, Junwei Su, Lingpeng Kong, Chuan Wu Action editor: Martha Lewis https://openreview.net/forum?id=nZCPG2Aarv #embeddings #embedding #attention

Global Sensitivity in Private Policy Selection with Nuisance-Fitted Doubly Robust Scores Yiyan HUANG Action editor: Juba Ziani https://openreview.net/forum?id=7Z9E7axGAT #privacy #private #robust