SPHINX: A Synthetic Environment for Visual Perception and Reasoning

Documenti analoghi

• Beyond Perception Errors: Semantic Fixation in Large Vision-Language Models
  di: Alam, Md Tanvirul
  Pubblicazione: (2026)
• Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing
  di: Bhusal, Dipkamal, et al.
  Pubblicazione: (2026)
• Towards Understanding Self-play for LLM Reasoning
  di: Chae, Justin Yang, et al.
  Pubblicazione: (2025)
• Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence
  di: Suwal, Sanish, et al.
  Pubblicazione: (2025)
• Orion: A Unified Visual Agent for Multimodal Perception, Advanced Visual Reasoning and Execution
  di: Reddy, N Dinesh, et al.
  Pubblicazione: (2025)