CST-Bench: Benchmarking Counterfactual Spatial Transition Reasoning with Causal Transition On-Policy Self-Distillation
cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- Qwen2.5-VL Technical Report
- SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
- Holistic Evaluation of Multimodal LLMs on Spatial Intelligence
- SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
- Counterfactual Samples Synthesizing for Robust Visual Question Answering
- SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
- Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions
- Distilling the Knowledge in a Neural Network
- Sequence-Level Knowledge Distillation
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
- LLaVA-OneVision: Easy Visual Task Transfer
- ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
- Unifying distillation and privileged information
- 3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark
- SQA3D: Situated Question Answering in 3D Scenes
- Counterfactual VQA: A Cause-Effect Look at Language Bias
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents