FailBench: How Reliable are VLMs at Judging Robot Task Success?
Paper • 2609.03611 • Published • 4
Spartak Bughdaryan
bugdaryan
AI & ML interests
Physical AI | VLA/VLM/JEPA | NLP & LLM
Recent Activity
upvoted a paper about 8 hours ago
FailBench: How Reliable are VLMs at Judging Robot Task Success? liked a Space 7 days ago
Metric-AI/ArmBench-LLM updated a Space about 1 month ago
Metric-AI/ArmBench-LLMOrganizations
upvoted a paper about 8 hours ago
upvoted an article about 2 months ago
Article
ArmBench-ASR: A Benchmark for Armenian ASR
Metric-AI
• • 11 upvoted an article 3 months ago
Article
ArmBench-LLM 1.0: Benchmarking LLMs on Armenian Language Tasks
Metric-AI
• • 13 upvoted an article 7 months ago
Article
ATE-2: State-of-the-Art Armenian Text Embeddings and the ArmBench-TextEmbed Benchmark
Metric-AI
• • 10