Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning
Journal ref ICLR 2025
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
Comments Accepted by ICLR 2025
OMG: Opacity Matters in Material Modeling with Gaussian Splatting
Comments Published as a conference paper at ICLR 2025
TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction
Comments Accepted by ICLR 2025, code and demos are available at https://tinyurl.com/TEASER-project
An Empirical Analysis of Uncertainty in Large Language Model Evaluations
Comments ICLR 2025
Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
Comments Accepted by ICLR 2025
Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons
Comments To appear in ICLR 2025
ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
Comments Accepted to ICLR 2025
StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces
Comments Project page: https://stochsync.github.io/ (ICLR 2025)
Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
Comments ICLR 2025
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Comments ICLR 2025; 22 pages, 13 figures, 7 tables; Project page at https://llm-multiagent-ft.github.io/
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Comments Accepted to ICLR 2025. Code: https://github.com/ictnlp/LLaVA-Mini Model: https://huggingface.co/ICTNLP/llava-mini-llama-3.1-8b
Autoregressive Video Generation without Vector Quantization
Comments Accepted to ICLR 2025. Project page at https://github.com/baaivision/NOVA
Stiefel Flow Matching for Moment-Constrained Structure Elucidation
Comments ICLR 2025
The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
Comments Accepted to ICLR 2025
Exact Certification of (Graph) Neural Networks Against Label Poisoning
Comments Published as a spotlight presentation at ICLR 2025
HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
Comments Accepted in ICLR 2025
ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy
Comments Accept to ICLR 2025
Compositional simulation-based inference for time series
Comments To be published in the proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025), Singapore, 2025
Learning General-Purpose Biomedical Volume Representations using Randomized Synthesis
Comments ICLR 2025: International Conference on Learning Representations. Code and model weights available at https://github.com/neel-dey/anatomix. Keywords: synthetic data, representation learning, medical image analysis, image registration, image segmentation
Breaking the Reclustering Barrier in Centroid-based Deep Clustering
Comments Accepted at ICLR 2025 (Camera-ready version)
SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
Comments Accepted to ICLR 2025
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
Comments ICLR 2025 Oral. The first two authors contributed equally. Project page located at: https://kinetix-env.github.io/
First-Person Fairness in Chatbots
Comments In ICLR 2025, 59 pages, 27 figures
Can Knowledge Editing Really Correct Hallucinations?
Comments ICLR 2025. Main paper: 10 pages; total: 34 pages (including appendix). The first two authors contributed equally to this work. Code, data, results, and additional resources are available on the project website: https://llm-editing.github.io
LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics
Comments 39 pages, ICLR 2025
Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment
Comments Accepted as ICLR 2025 conference paper
Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
Comments ICLR 2025
Diffusing States and Matching Scores: A New Framework for Imitation Learning
Comments Accepted at ICLR 2025
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
Comments ICLR 2025
