New #TMLR-Paper-with-Video: On the Role of Discrete Representation in Sparse Mixture of Experts Giang Do, Kha Pham, Hung Le, Truyen Tran https://tmlr.infinite-conf.org/paper_pages/GTWKmojpI7 #quantization #sparse #representations

VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents Rui Meng, Ziyan Jiang, Ye Liu et al. Action editor: C.V. Jawahar https://openreview.net/forum?id=TpU38jbKIJ #embeddings #embedding #multimodal

New #TMLR-Paper-with-Video: Node-Level Data Valuation on Graphs Simone Antonelli, Aleksandar Bojchevski https://tmlr.infinite-conf.org/paper_pages/tNyApIqDSJ #supervised #nodes #graphs

LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks Dominik J. Mühlematter, Michelle Halbheer, Alexander Becker et al. Action editor: Lee Zamparo https://openreview.net/forum?id=yhXXmOMpSQ #ensemble #attention #ensembling

New #TMLR-Paper-with-Video: Do Think Tags Really Help LLMs Plan? A Critical Evaluation of ReAct-Style Prompting Siddhant Bhambri, Mudit Verma, Subbarao Kambhampati https://tmlr.infinite-conf.org/paper_pages/aFAMPSmNHR #reasoning #prompting #prompts

DiffKGW: Stealthy and Robust Diffusion Model Watermarking Tianxin Wei, Ruizhong Qiu, Yifan Chen et al. Action editor: Ju Sun https://openreview.net/forum?id=OXi9vcIOgD #watermarking #watermark #watermarks

New #TMLR-Paper-with-Video: Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models Jan Wehner, Sahar Abdelnabi, Daniel Tan, David Krueger, Mario Fritz https://tmlr.infinite-conf.org/paper_pages/2U1KIfmaU9 #representation #representations

New #Featured Certification: Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips Ido Galil, Moshe Kimhi, Ran El-Yaniv https://openreview.net/forum?id=kN1s53X3zl #imagenet #flips #flipping

Graph Coarsening using Game Theoretic Approach Sonali Raj, Manoj Kumar, Sumit Kumar, Ruchir Gupta, Amit Kumar Jaiswal Action editor: Moshe Eliasof https://openreview.net/forum?id=5vLBjQJCln #coarsening #graph #coarsened

New #TMLR-Paper-with-Video: NeoBERT: A Next Generation BERT Lola Le Breton, Quentin Fournier, John Xavier Morris, Mariam El Mezouar, Sarath Chandar https://tmlr.infinite-conf.org/paper_pages/TJRyDi7mwH #bert #encoder #encoders

MiniGPT-Med: A Unified Vision-Language Model for Radiology Image Understanding Asma Alkhaldi, Raneem Alnajim, Layan Alabdullatef et al. Action editor: Jan-Willem van de Meent https://openreview.net/forum?id=NenHFEg1Di #radiology #med #medical

New #TMLR-Paper-with-Video: SR-Reward: Taking The Path More Traveled Seyed Mahdi B. Azad, Zahra Padar, Gabriel Kalweit, Joschka Boedecker https://tmlr.infinite-conf.org/paper_pages/bzk1sV1svm #reinforcement #reward #rewards

Augmenting Molecular Graphs with Geometries via Machine Learning Interatomic Potentials Cong Fu, Yuchao Lin, Zachary Krueger et al. Action editor: Ole Winther https://openreview.net/forum?id=JwxhHTISJL #molecular #molecules #geometries

New #TMLR-Paper-with-Video: Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspect... Senmiao Wang, Yupeng Chen, Yushun Zhang, Ruoyu Sun, Tian Ding https://tmlr.infinite-conf.org/paper_pages/6Aj0aNXfRy #networks #deepen #gcns

From Feature Visualization to Visual Circuits: Effect of Model Perturbation geraldin nanfack, Michael Eickenberg, Eugene Belilovsky Action editor: Satoshi Hara https://openreview.net/forum?id=x6ZwuyTy65 #adversarial #visual #visualizing

New #TMLR-Paper-with-Video: LLM-Guided Self-Supervised Tabular Learning With Task-Specific Pre-text Tasks Sungwon Han, Seungeon Lee, Meeyoung Cha, Sercan O Arik, Jinsung Yoon https://tmlr.infinite-conf.org/paper_pages/jXcx2oAIbw #supervised #tasks #text

GenAI vs. Human Creators: Procurement Mechanism Design in Two-/Three-Layer Markets Rui Ai, David Simchi-Levi, Haifeng Xu Action editor: Hongyang R. Zhang https://openreview.net/forum?id=Eukf4TBHS7 #procurement #incentives #creators

New #TMLR-Paper-with-Video: Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via ... Naoki Yoshida, Shogo Nakakita, Masaaki Imaizumi https://tmlr.infinite-conf.org/paper_pages/RPtKkNx9ZK #sgd #stochastic #learning

GraphMERT: Efficient and Scalable Distillation of Reliable Knowledge Graphs from Unstructured Data Margarita Belova, Jiaxin Xiao, Shikhar Tuli, Niraj Jha Action editor: Junchi Yan https://openreview.net/forum?id=tnXSdDhvqc #graphmert #neurosymbolic #semantic

New #TMLR-Paper-with-Video: Metamorphic Forward Adaptation Network: Dynamically Adaptive and Modular Multi-layer Learning Yu Sun, Vijja Wichitwechkarn, Ronald Clark, Mirko Kovac, Basaran Bahadir Kocer https://tmlr.infinite-conf.org/paper_pages/6RCs2tLsHq #metamorphic #adaptive

Sociodynamics of Reinforcement Learning Yann Bouteiller, Karthik Soma, Giovanni Beltrame Action editor: Marlos C. Machado https://openreview.net/forum?id=Ro6Ylnx8se #reinforcement #games #agents

New #TMLR-Paper-with-Video: Illustrated Landmark Graphs for Long-horizon Policy Learning Christopher Watson, Arjun Krishna, Rajeev Alur, Dinesh Jayaraman https://tmlr.infinite-conf.org/paper_pages/0AOUWC4ss8 #reinforcement #planning #maze

Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters Xingjian Zhang, Tianhong Gao, Suliang Jin, Tianhao Wang, Teng Ye, Eytan Adar, Qiaozhu Mei Action editor: Ilia Sucholutsky https://openreview.net/forum?id=1jLQ629Yps #annotations #annotation #judgments

New #TMLR-Paper-with-Video: Mind the truncation gap: challenges of learning on dynamic graphs with recurrent architectures João Bravo, Jacopo Bono, Hugo Ferreira, Pedro Saleiro, Pedro Bizarro https://tmlr.infinite-conf.org/paper_pages/QezxDgd5hf #networks #backpropagation #neural

The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning Wenqian Ye, Luyang Jiang, Eric Xie et al. Action editor: Yu Yao https://openreview.net/forum?id=kIuqPmS1b1 #generative #ai #generalization

New #TMLR-Paper-with-Video: GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Repres... Md Ferdous Alam, Faez Ahmed https://tmlr.infinite-conf.org/paper_pages/e817c1wEZ6 #cad #meshes #generative

Reproducibility Study: Understanding multi-agent LLM cooperation in the GovSim framework Alessio Silverio, Carmen Michaela Chezan, Mathijs van Sprang, Tom Cappendijk, Martin Smit Action editor: Yaodong Yang https://openreview.net/forum?id=ON8EMrNwww #agent #govsim #agents

New #TMLR-Paper-with-Video: TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis Sabera J Talukder, Yisong Yue, Georgia Gkioxari https://tmlr.infinite-conf.org/paper_pages/QlTLkH6xRC #tokenizing #tokenization #embeddings

A Multilevel Low-Rank Newton Method with Super-linear Convergence Rate and its Application to Non... Nick Tsipinakis, Panagiotis Tigas, Panos Parpas Action editor: Stephen Becker https://openreview.net/forum?id=PKakPzVVja #optimization #convex #randomization

New #TMLR-Paper-with-Video: Interactive Task Planning with Language Models Boyi Li, Philipp Wu, Pieter Abbeel, Jitendra Malik https://tmlr.infinite-conf.org/paper_pages/VmfWywWuYQ #planning #interactive #robot

From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffu... Zefan Cai, Haoyi Qiu, Haozhe Zhao et al. Action editor: Yonatan Bisk https://openreview.net/forum?id=C0yxuS6jty #bias #biases #videobiaseval

New #TMLR-Paper-with-Video: MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection Kemal Oksuz, Selim Kuzucu, Tom Joy, Puneet K. Dokania https://tmlr.infinite-conf.org/paper_pages/fJEsas1z8J #detectors #detection #detector

Semi-Supervised Cross-Domain Imitation Learning Li-Min Chu, Kai-Siang Ma, Ming-Hong Chen, Ping-Chun Hsieh Action editor: Arnob Ghosh https://openreview.net/forum?id=WARXnbJawZ #imitation #supervised #knowledge

New #TMLR-Paper-with-Video: Explaining Node Embeddings Zohair Shafi, Ayan Chatterjee, Tina Eliassi-Rad https://tmlr.infinite-conf.org/paper_pages/QQZ8uPxFb3 #embeddings #embedding #nodes

Exploring Perceptual Limitations of Multimodal LLMs on Small Visual Objects Jiarui Zhang, Jinyi Hu, Mahyar Khayatkhoei, Filip Ilievski, Maosong Sun Action editor: Changyou Chen https://openreview.net/forum?id=D8MjYW8m35 #multimodal #distractors #visual

New #TMLR-Paper-with-Video: Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Bal... Chiu-Chou Lin, Yu-Wei Shih, Kuei-Ting Kuo et al. https://tmlr.infinite-conf.org/paper_pages/2D36otXvBE #games #players #gameplay

Probabilistic Pretraining for Improved Neural Regression Boris N. Oreshkin, Shiv Kumar Tavker, Dmitry Efimov Action editor: Andres Masegosa https://openreview.net/forum?id=F6BTATGXaf #datasets #tabpfn #regression

New #TMLR-Paper-with-Video: PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off Sachit Kuhar, Yash Jain, Alexey Tumanov https://tmlr.infinite-conf.org/paper_pages/IEKtMMSblm #quantization #imagenet #neural

CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning Yexin Li Action editor: Marcello Restelli https://openreview.net/forum?id=54MOD02xC2 #exploration #bandit #reinforcement

New #TMLR-Paper-with-Video: Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building Jaedong Hwang, Zhang-Wei Hong, Eric R Chen, Akhilan Boopathy, Pulkit Agrawal, Ila R Fiete https://tmlr.infinite-conf.org/paper_pages/cT8oOJ6Q6F #maps #exploration #map

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation Shanda Li, Tanya Marwah, Junhong Shen et al. Action editor: Yi Zhou https://openreview.net/forum?id=eG3Qy5Oux6 #solvers #solver #codepde

Watermarking Degrades Alignment in Language Models: Analysis and Mitigation Apurv Verma, Hai Phan, Shubhendu Trivedi Action editor: Zhouxing Shi https://openreview.net/forum?id=w2ATKQcfWx #watermarking #watermark #watermarked

From Link Prediction to Forecasting: Addressing Challenges in Batch-based Temporal Graph Learning Moritz Lampert, Christopher Blöcker, Ingo Scholtes Action editor: Xiaofeng Cao https://openreview.net/forum?id=iZPAykLE3l #forecasting #prediction #batches

New #J2C Certification: In-context Learning in Presence of Spurious Correlations Hrayr Harutyunyan, Rafayel Darbinyan, Samvel Karapetyan, Hrant Khachatrian https://openreview.net/forum?id=C9CSaTR1iA #learners #learn #training

Towards Scalable Language-Image Pre-training for 3D Medical Imaging Chenhui Zhao, Yiwei Lyu, Asadur Zaman Chowdury et al. Action editor: Nicolas THOME https://openreview.net/forum?id=WxHf4EcBWA #imaging #scans #attention

TABASCO: A Fast, Simplified Model for Molecular Generation with Improved Physical Quality Carlos Vonessen, Charles Harris, Miruna Cretu, Pietro Lio Action editor: Miguel Bautista https://openreview.net/forum?id=Kg6CSrbXl4 #molecule #models #molecular

Fuzzy PyTorch: Rapid Numerical Variability Evaluation for Deep Learning Models Inés Gonzalez Pepe, Hiba Akhaddar, Tristan Glatard, Yohan Chatelain Action editor: Jasper Snoek https://openreview.net/forum?id=0ogq232VGP #pytorch #numerical #rounding

A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation Xinjie Liu, Cyrus Neary, Kushagra Gupta et al. Action editor: Adam White https://openreview.net/forum?id=zAo0L7Dcqt #reinforcement #reinforce #trained

Proc-to-Spec: A Functorial Map of Network Processes Shanfeng Hu Action editor: Mauricio A Álvarez https://openreview.net/forum?id=pT84Ii6igG #spectral #spectrum #invariants

Topological Inductive Bias fosters Multiple Instance Learning in Data-Scarce Scenarios Salome Kazeminia, Carsten Marr, Bastian Rieck Action editor: Adín Ramírez Rivera https://openreview.net/forum?id=1hZy9ZjjCc #supervised #classification #classifiers