VSpark: Speculative Decoding for Autoregressive Vision-Language-Action Models Paper • 2611.22666 • Published 2 days ago • 5 • 1
Out of Sight, Still in Mind: Token Compression for Omni-LLMs Paper • 2607.21179 • Published 2 days ago • 1
VSpark: Speculative Decoding for Autoregressive Vision-Language-Action Models Paper • 2611.22666 • Published 2 days ago • 5
Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs Paper • 2606.18924 • Published Sep 4
OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents Paper • 2609.32569 • Published Sep 26
On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs Paper • 2603.14337 • Published Oct 18
VSpark: Speculative Decoding for Autoregressive Vision-Language-Action Models Paper • 2611.22666 • Published 2 days ago • 5
Out of Sight, Still in Mind: Token Compression for Omni-LLMs Paper • 2607.21179 • Published 2 days ago • 1
Speculative End-Turn Detector for Efficient Speech Chatbot Assistant Paper • 2503.23439 • Published Mar 30, 2025
AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing? Paper • 2509.17641 • Published Sep 22, 2025 • 3