RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging The-Hai Nguyen, Dang Huu-Tien, Takeshi Suzuki, Le-Minh Nguyen Action editor: Mohammad Emtiyaz Khan https://openreview.net/forum?id=H5lDsSCS9i #merges #merging #regression

ADAPT: Adaptive Prompt Tuning for Vision-Language Models Zhenhan Huang, Tejaswini Pedapati, Pin-Yu Chen, Jianxi Gao Action editor: Ying Nian Wu https://openreview.net/forum?id=3uVAA3ckxT #saliency #trained #context

You Only Train Once: Differentiable Subset Selection for Omics Data Daphné Chopard, Jorge da Silva Gonçalves, Irene Cannistraci et al. Action editor: Pan Xu https://openreview.net/forum?id=xQiXlADW5v #yoto #transcriptomic #predicts

New #Reproducibility Certification: Towards Representation Backdoor on CLIP via Concept Confusion Junchi Liao, Weimin Lyu, Lijie Hu, Shaopeng Fu, Tianhao Huang, Shu Yang, Jie Li, Di Wang https://openreview.net/forum?id=jQ91DETUIr #backdoors #backdoor #ai

Joint Embedding Variational Bayes Amin Oji, Paul W. Fieguth Action editor: Ole Winther https://openreview.net/forum?id=4cbPJ5jLtr #embeddings #embedding #representations

VidHal: Benchmarking Hallucinations in Vision LLMs Wey Yeh Choong, Yangyang Guo, Mohan Kankanhalli Action editor: Ali Etemad https://openreview.net/forum?id=7ccWCDbdM1 #captions #caption #videos

Transitioning Heads Conundrum: The Hidden Bottleneck in Long-Tailed Class-Incremental Learning Rahul Vigneswaran, Hari Chandana Kuchibhotla, Vineeth N. Balasubramanian Action editor: Hanwang Zhang https://openreview.net/forum?id=Hb2Jvi5M7X #forgetting #memory #retention

CLIP-SVD: Efficient and Interpretable Vision–Language Adaptation via Singular Values Taha Koleilat, Hassan Rivaz, Yiming Xiao Action editor: Hanwang Zhang https://openreview.net/forum?id=XYy8pwqwMR #adapting #adaptation #svd

Properties and limitations of geometric tempering for gradient flow dynamics Francesca Romana Crucinio, Sahani Pathiraja Action editor: Trevor Campbell https://openreview.net/forum?id=IP0w5LdcxC #rao #fisher #discretisations

A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection James Enouen, Mahito Sugiyama Action editor: Jean Barbier https://openreview.net/forum?id=DxUXI15C38 #boltzmann #sparse #models

Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNs Amirreza Shiralinasab Langari, Leila Yeganeh, Kim Khoa Nguyen Action editor: Vicenç Gomez https://openreview.net/forum?id=oD3qWXgB4e #adjacency #topological #grothendieck

Test-Time Adaptation for Unsupervised Combinatorial Optimization Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh Action editor: Xi Lin https://openreview.net/forum?id=VVyGfRp4fG #optimized #generalization #optimizing

Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models Vinith Menon Suriyakumar, Rohan Alur, Ayush Sekhari, Manish Raghavan, Ashia C. Wilson Action editor: Venkatesh Babu Radhakrishnan https://openreview.net/forum?id=Vj0Z2wspQ5 #unlearning #adversarial

Wasserstein Bounds for generative diffusion models with Gaussian tail targets WANG XIXIAN, Zhongjian Wang Action editor: Omar Rivasplata https://openreview.net/forum?id=QbQ4DtP5vS #wasserstein #diffusion #bound

$\texttt{LucidAtlas}$: Learning Uncertainty-Aware, Covariate-Disentangled, Individualized Atlas ... Yining Jiao, Sreekalyani Bhamidi, Carlton Jude ZDANSKI et al. Action editor: Sameer Deshpande https://openreview.net/forum?id=3FbNwC8ua8 #models #modeling #atlas

Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning Ziyu Cheng, Jinsheng Ren, Jun Yang, Zhouxian Jiang, Chenzhihang Li, Rongye Shi, Bin Liang Action editor: Chicheng Zhang https://openreview.net/forum?id=8Fo2AwQE9z #cooperation #collaborative

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning Yixuan Even Xu, Yash Savani, Fei Fang, J Zico Kolter Action editor: Binhang Yuan https://openreview.net/forum?id=MfHOmgqVXM #reinforcement #memory #rewards

Contrastive VQ Priors for Multi-Class Plaque Segmentation via SAM Adaptation Ruan Yizhe, Yusuke Kurose, JUNICHI IHO et al. Action editor: Chenyu You https://openreview.net/forum?id=5P7HfuejgL #plaque #attention #angiography

FedLog: Personalized Federated Classification with Less Communication and More Flexibility Haolin Yu, Guojun Zhang, Hongliang Li, Pascal Poupart Action editor: Alberto Bietti https://openreview.net/forum?id=7Hwk0bvvKn #fedlog #federated #privacy

SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models Sebastiano Monti, Carlo Nicolini, Giovanni Pellegrini, Jacopo Staiano, Bruno Lepri Action editor: Marc Lanctot https://openreview.net/forum?id=pLosAkOoGU #planning #language #reasoning

Continuous Treatment Effect Estimation with Cauchy-Schwarz Divergence Information Bottleneck Louk van Remmerden, Shiqin Tang, Shujian Yu Action editor: Arto Klami https://openreview.net/forum?id=9SvY0mMr2u #generalization #regularization #bottleneck

Influence Estimation in Statistical Models Using the Fisher Information Matrix Omri Lev, Ashia C. Wilson Action editor: Mohammad Emtiyaz Khan https://openreview.net/forum?id=1kYIBaXCG8 #influence #hampel_influence #hessian

DRAW: Domain Weight Randomization with Bayesian Updating for LLM Pre-Training Ruonan Wang, Yongqi Qiao, Zhonglin Xie, Kun Yuan Action editor: Marwa El Halabi https://openreview.net/forum?id=tc8TyD7ZyD #randomization #priors #weights

On the Conditioning Consistency Gap in Conditional Neural Processes Robin Young Action editor: Manuel Haussmann https://openreview.net/forum?id=rLJ5Hm5vbG #conditioned #encoders #cnps

MixTraining: A Better Trade-Off Between Compute and Performance Zexin Li, Jiancheng Zhang, Yufei Li, Yinglun Zhu, Cong Liu Action editor: Yannis Kalantidis https://openreview.net/forum?id=NVpS2g9KRo #mixtraining #training #supervised

Preference-Based Gradient Estimation for ML-Guided Approximate Combinatorial Optimization Arman Mielke, Uwe Bauknecht, Thilo Strauss, Mathias Niepert Action editor: Guillaume Dalle https://openreview.net/forum?id=2S224XC378 #optimization #heuristics #supervised

α-OCC: Uncertainty-Aware Camera-based 3D Semantic Occupancy Prediction Sanbao Su, Nuo Chen, Chenchen Lin, Felix Juefei-Xu, Chen Feng, Fei Miao Action editor: Weijian Deng https://openreview.net/forum?id=bUv25gBLlV #3d #depth #robotics

Task-Specific Exploration in Meta-Reinforcement Learning via Task Reconstruction Radu Stoican, Angelo Cangelosi, Christian Goerick, Thomas H Weisswange Action editor: Dileep Kalathil https://openreview.net/forum?id=VRRapVcaJH #learns #reinforcement #reward

Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power Yuzhu Chen, Tian Qin, Xinmei Tian, Fengxiang He, Dacheng Tao Action editor: Joonas Jälkö https://openreview.net/forum?id=z5bJ44Brc4 #equivariance #generalizability #intrinsic

ABCDE: Agentic-Based Controlled Dynamic Erasure for Intent-Aware Safety Reasoning Ping Liu, CHI ZHANG Action editor: Bo Han https://openreview.net/forum?id=IFjPhMcXJB #intent #erasure #agentic

DOME: Distributed Online Learning based Multi-Estimate Fusion for Cooperative Predictive Target T... Shubhankar Gupta, Saksham Sharma, Suresh Sundaram Action editor: Sai Aparna Aketi https://openreview.net/forum?id=aF5PHD6vll #fusion #prediction #collaborative

CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning Amirhosein Javadi, Tuomas Oikarinen, Tara Javidi, Tsui-Wei Weng Action editor: Dmitry Kangin https://openreview.net/forum?id=Wf6OpLgj2i #forgetting #continual #incremental

Anytime Verified Agents: Adaptive Compute Allocation for Reliable LLM Reasoning under Budget Cons... Dipkumar Patel Action editor: Weiyang Liu https://openreview.net/forum?id=JMDCMf7mlF #planning #computational #agents

Differentially Private and Scalable Estimation of the Network Principal Component Alireza Khayatian, Anil Vullikanti, Aritra Konar Action editor: Jonathan Ullman https://openreview.net/forum?id=V0BjWbrAYC #privacy #privately #private

Boosting Text Encoder for Personalized Text-to-Image Generation NaHyeon Park, Kunhee Kim, Hyunjung Shim Action editor: Hadi J. Rad https://openreview.net/forum?id=hiZzk1nHuV #textboost #attention #embeddings

Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji Action editor: Kangwook Lee https://openreview.net/forum?id=mKlW68i2Ig #sampling #maskgit #samplers

Explainable Error Detection in Integrated Circuits Image Segmentation via Graph Neural Networks MA XIAOYU, Jingyang Dai, Feng Ji, Deruo Cheng, Yiqiong Shi, Bah-Hwee Gwee Action editor: C.V. Jawahar https://openreview.net/forum?id=q68B9mTom5 #cnn #segmentation #faults

On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Gener... Matteo Vilucchio, Nikolaos Tsilivis, Bruno Loureiro, Julia Kempe Action editor: Alberto Bietti https://openreview.net/forum?id=vkmvuranbm #adversarial #regularization #regularized

Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG Yufeng Wang, Lu Wei, Haibin Ling Action editor: Simone Scardapane https://openreview.net/forum?id=L8gYtUZfVU #retrieval #gating #draft

CatScreen: A Large MultiModal Benchmark Dataset for Cataract Screening Mahapara Khurshid, Sonam Kumar, Dr Anusuya Bhattacharyya et al. Action editor: Eric Eaton https://openreview.net/forum?id=cF7tSNAVQ6 #cataract #ophthalmologist #eye

LinMU: Multimodal Understanding Made Linear Hongjie Wang, Niraj Jha Action editor: Yuhang Zang https://openreview.net/forum?id=6BYdTSNrab #attention #multimodal #decoder

ClimateAgent: Multi-Agent Orchestration for Complex Climate Data Science Workflows Chenyue Li, Hyeonjae Kim, Wen Deng, Mengxi Jin, HUANG Wen, Mengqian Lu, Binhang Yuan Action editor: Hongsheng Li https://openreview.net/forum?id=XLWvXNumGa #climateagent #agent #automated

Dimension-free error estimate for diffusion model and optimal scheduling Valentin De Bortoli, Romuald Elie, Anna Kazeykina, Zhenjie Ren, Jiacheng Zhang Action editor: Julius Berner https://openreview.net/forum?id=uArYtsvW8o #wasserstein #diffusion #generative

LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking Yifan Zeng, Ojas Tendolkar, Raymond Baartmans, Qingyun Wu, Lizhong Chen, Huazheng Wang Action editor: Shiyu Chang https://openreview.net/forum?id=VUY0j74Yes #ranking #sorting #sort

Incremental3D: Real-time Incremental 3D Scene Generation with Scene Graphs Penggang GAO, Yonas Teodros Tefera, Darwin G. Caldwell, Nikhil Deshpande Action editor: Matthew Walter https://openreview.net/forum?id=am8Zv3R8GW #incremental3d #3d #scene

Conformal Calibration of Statistical Confidence Sets Luben Miguel Cruz Cabezas, Guilherme Soares, Thiago Ramos et al. Action editor: Sameer Deshpande https://openreview.net/forum?id=J4lK62PVE6 #likelihoods #likelihood #confidence

New #Featured Certification, #Reproducibility Certification, #Survey Certification: Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines Ziyao Wang, Bingying Wang, Hanrong Zhang et al. https://openreview.net/forum?id=tAaWFpvnmm #embodied #structured

Revisit, Extend, and Enhance Hessian-Free Influence Functions Ziao Yang, Han Yue, Jian Chen, Hongfu Liu Action editor: Jeremias Sulam https://openreview.net/forum?id=ijL2681Tau #hessian #adversarial #ensemble

Data Compressibility Quantifies LLM Memorization Yizhan Huang, Zhe YANG, Meifang Chen, HUANG Nianchen, Jianping Zhang, Michael R. Lyu Action editor: Blake Richards https://openreview.net/forum?id=6L4UXc7P3h #memorization #memorize #verbatim

Multimodal Deception in Explainable AI: Concept-Level Backdoor Attacks on Concept Bottleneck Models Songning Lai, Jiayu Yang, Yu Huang et al. Action editor: Adín Ramírez Rivera https://openreview.net/forum?id=bntZBG9fBY #backdoor #threats #deception