ICML 2025PastOther
ICML 2025 Workshop on Assessing World Models
ICML 2025 World Models Workshop
- Submission deadline
- May 22, 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 (36)
Fetched from OpenReview (v2) on 2026-06-10.
Adapting Vision-Language Models for Evaluating World Models
APOD: Adaptive PDE-Observation Diffusion for Physics-Constrained Sampling
Aquilon: Towards Building Multimodal Weather LLMs
Are LLM Belief Updates Consistent with Bayes’ Theorem?
Beyond Behavioural Evaluations for Assessing World Models
Cards Against Contamination: TCG-Bench for Difficulty-Scalable Multilingual LLM Reasoning
Contextual Effects in LLM and Human Causal Reasoning
Deep Koopman operator framework for causal discovery in nonlinear dynamical systems
Do Vision Language Models infer human intention without visual perspective-taking? Towards a scalable "One-Image-Probe-All" dataset
Eliminating Discriminative Shortcuts in Multiple Choice Evaluations with Answer Matching
Evaluating Forecasting is More Difficult than Other LLM Evaluations
Evaluating Self-Orienting in Language and Reasoning Models
FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models
GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning
HueManity: Probing Fine-Grained Visual Perception in MLLMs
I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2
Let’s Simulate Frame-by-Frame: In-Context Physical Simulations with Vision-Language Models
Leveraging the Sequential Nature of Language for Interpretability
Measuring Belief Updates in Curious Agents
Measuring Rule-Following in Language Models
MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
Newfluence: Boosting Model Interpretability and Understanding in High Dimensions
On the Emergence of "Useless" Features in Next Token Predictors
Open World Scene Graph Generation using Vision Language Models
Probing the Limits of Mathematical World Models in LLMs
ReviseQA: A Benchmark for Belief Revision in Multi-Turn Logical Reasoning
RMA: Reward Model Alignment with Human preference
Testing LLM Understanding of Scientific Literature through Expert-Driven Question Answering: Insights from High-Temperature Superconductivity
Tracking World States with Language Models: State-Based Evaluation Using Chess
Unbounded Memory and Consistent Imagination via Unified Diffusion–SSM World Models
Uncertainty Quantification for LLM-Based Survey Simulations
Understanding Large Language Models' Ability on Interdisciplinary Research
Virtue Semantics: Probing the Consistency of Moral Values of Large Language Models
What if Othello-Playing Language Models Could See?
World Models and Consistent Mistakes in LLMs
WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning