DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?
Paper • 2605.29615 • Published • 2
Mosaic90
Mosaic90
AI & ML interests
None yet
Recent Activity
new activity about 1 month ago
tencent/DiffSpot:DiffSpot: can your VLM spot a single CSS-level change between two screenshots? upvoted a paper about 1 month ago
DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces? upvoted a paper about 1 month ago
Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMsOrganizations
upvoted 2
papers about 1 month ago
upvoted 3
papers 9 months ago
RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Paper • 2509.16198 • Published • 129
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
Paper • 2509.22220 • Published • 66
WildSpeech-Bench: Benchmarking Audio LLMs in Natural Speech Conversation
Paper • 2506.21875 • Published • 1