Latest Research in Computation and Language

Top Research Topics in Computation and Language

• Computer Vision and Pattern Recognition — 79 papers
• Artificial Intelligence — 35 papers
• Machine Learning — 11 papers
• Computation and Language — 9 papers
• Robotics — 8 papers
• Multimodal Machine Learning Applications — 5 papers
• Embedded Systems Design Techniques — 2 papers
• Human-Computer Interaction — 1 papers
• Aesthetic Perception and Analysis — 1 papers
• Multiagent Systems — 1 papers

Highest-Cited Papers

1. Prompt-Driven Exploration
2. DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum
3. Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models
4. Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning
5. Learning from Success and Failure: Acquiring Adaptive Dialogue Strategies for Social Robots
6. EmbodiedMind: Adaptive Data Curation and Prefix-Tree Reinforcement Learning for Efficient Embodied Intelligence
7. SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnership
8. RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection
9. Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
10. LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition
11. Visual Input and Its Framing Affect Attribute-based Descriptions Produced by Large Vision-Language Models
12. MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education
13. AMIGO: Agentic Multi-Image Grounding Oracle Benchmark
14. Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning
15. Using OCR Heads to Verbalize Image Semantics
16. Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognition
17. A Survey of Visual Question Answering for Embodied Robots: Tasks, Methods, and Future Directions
18. MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action
19. GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing
20. StackTok: Accelerating VLMs Inference with Budget-Adaptive Visual Token Selection