ICLR 2025PastOther
I Can't Believe It's Not Better: Challenges in Applied Deep Learning
ICLR 2025 Workshop ICBINB
- Submission deadline
- Feb 7, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (28)
Fetched from OpenReview (v2) on 2026-06-10.
An Integrated YOLO and VLM System for Fire Detection in Enclosed Environments
Are We Really Unlearning? The Presence of Residual Knowledge in Machine Unlearning
Bridging the Language Gap: Evaluating Machine Translation for Animal Health in Low-Resource Settings
Challenges of Decomposing Tools in Surgical Scenes Through Disentangling The Latent Representations
Challenges of Multi-Modal Coreset Selection for Depth Prediction
Data Mixing can Induce Phase Transitions in Knowledge Acquisition
Do Not Overestimate Black-box Attacks
Fantastic Allosteric Binding Sites and Why Deep Learning Cannot Find Them
From Fog to Failure: The Unintended Consequences of Dehazing on Object Detection in Clear Images
Graph Networks Struggle With Variable Scale
How Effective Are AI Models in Translating English Scientific Texts to Nigerian Pidgin: A Low-resource Language?
Impact of Task Phrasing on Presumptions in Large Language Models
In Search of Forgotten Domain Generalization
Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges
Last Layer Empirical Bayes
Lost-in-distance: Impact of Contextual Proximity on LLM Performance in Graph Tasks
Modeling speech emotion with label variance and analyzing performance across speakers and unseen acoustic conditions
Not constructing Ramsey Graphs using Deep Reinforcement Learning
On the Limitations of LLM-Synthesized Social Media Misinformation Moderation
On the Limitations of Neural Networks for Option Pricing: Analysis of Volatility Regime Sensitivity
On the Limits of Applying Graph Transformers for Brain Connectome Classification
On the Power of Heuristics in Temporal Graphs
On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysis
On the Role of Structure in Hierarchical Graph Neural Networks
Overtrained Language Models Are Harder to Fine-Tune
Performance of Zero-Shot Time Series Foundation Models on Cloud Data
Possibility for Proactive Anomaly Detection
Rethinking Evaluation for Temporal Link Prediction through Counterfactual Analysis