Causal Discovery via Bayesian Optimization
Comments ICLR 2025
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
Comments Published as a conference paper at ICLR 2025
Towards a unified and verified understanding of group-operation networks
Comments ICLR 2025 camera ready. 32 pages, 11 figures
TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
Comments Published at ICLR 2025
Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge
Comments Accepted at ICLR 2025
StringLLM: Understanding the String Processing Capability of Large Language Models
Comments Accepted to ICLR 2025
Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
Comments ICLR 2025
Binary Losses for Density Ratio Estimation
Journal ref International Conference on Learning Representations (ICLR), 2025
Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems
Comments ICLR 2025. Code is available at https://github.com/jiechenjiechen/GNP. (Important update from v1 to v2: Updated the timing experiments and evaluation metrics for fairer and better results.)
Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers
Comments Published as a conference paper at ICLR 2025
Has the Deep Neural Network learned the Stochastic Process? An Evaluation Viewpoint
Comments Published as a conference paper at ICLR 2025
Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding
Comments Accepted by ICLR 2025
Fat-to-Thin Policy Optimization: Offline RL with Sparse Policies
Comments accepted by ICLR 2025; code available at https://github.com/lingweizhu/fat2thin
DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing
Comments ICLR 2025 Accepted
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
Comments Accepted by ICLR 2025; 92 Pages; Project Repo: https://github.com/Xiaohao-Xu/SLAM-under-Perturbation. arXiv admin note: substantial text overlap with arXiv:2406.16850
Implicit Neural Surface Deformation with Explicit Velocity Fields
Comments ICLR 2025, 10 pages
Transformer-Squared: Self-adaptive LLMs
Comments To appear at the 13th International Conference on Learning Representations (ICLR 2025)
q-exponential family for policy optimization
Comments accepted by ICLR 2025
Adaptive Retention & Correction: Test-Time Training for Continual Learning
Comments Accepted to ICLR 2025
Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
Comments Published as a conference paper at ICLR 2025
ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors
Comments Accepted by ICLR 2025
Exposure Bracketing Is All You Need For A High-Quality Image
Comments ICLR 2025
Coupled Multiwavelet Neural Operator Learning for Coupled Partial Differential Equations
Comments Accepted to ICLR 2023: https://openreview.net/forum?id=kIo_C6QmMOM; This article is alternatively titled: Coupled Multiwavelet Operator Learning for Coupled Differential Equations
Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization
Comments Accepted by ICLR 2025
LLMs Can Plan Only If We Tell Them
Comments ICLR 2025
Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
Comments Accepted to ICLR 2025. Code is available at https://github.com/hmxiong/StreamChat
Truncated Consistency Models
Comments ICLR 2025
Integrative Decoding: Improve Factuality via Implicit Self-consistency
Comments Accepted by ICLR 2025
RegMix: Data Mixture as Regression for Language Model Pre-training
Comments ICLR 2025
ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents
Comments ICLR'25: https://openreview.net/forum?id=kKILfPkhSz
