RefereeBench shows that even the strongest video MLLMs reach only around 60% accuracy on multi-sport refereeing tasks and struggle with rule application and temporal grounding.
Whisperx: Time-accurate speech transcription of long-form audio
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Human-1 is the first open full-duplex spoken dialogue system for Hindi, created by adapting Moshi with a custom tokenizer and training on 26,000 hours of real-world conversations to enable natural interruptions and overlaps.
CineAgents is a multi-agent system that builds hierarchical narrative memory via script reverse-engineering and uses iterative planning to produce instruction-driven cinematic video compilations with better coherence than prior methods.
WhisperPipe delivers 89 ms median latency and 48% lower peak GPU memory than standard Whisper while keeping word error rate within 2% of the offline model.
Continuous diffusion spoken language models follow scaling laws for loss and phoneme divergence and generate emotive multi-speaker speech at 16B scale, though long-form coherence stays difficult.
AudioKV prioritizes audio-critical attention heads identified via ASR analysis and applies spectral score smoothing to evict KV cache tokens, achieving high compression with minimal accuracy loss in LALMs.
Large-print editions of layout-based documents outperform gesture-based magnification by 18% in reading speed and 30% in target location speed while restoring natural reading strategies and reducing workload.
citing papers explorer
-
RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees
RefereeBench shows that even the strongest video MLLMs reach only around 60% accuracy on multi-sport refereeing tasks and struggle with rule application and temporal grounding.
-
Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations
Human-1 is the first open full-duplex spoken dialogue system for Hindi, created by adapting Moshi with a custom tokenizer and training on 26,000 hours of real-world conversations to enable natural interruptions and overlaps.
-
A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation
CineAgents is a multi-agent system that builds hierarchical narrative memory via script reverse-engineering and uses iterative planning to produce instruction-driven cinematic video compilations with better coherence than prior methods.
-
WhisperPipe: A Resource-Efficient Streaming Architecture for Real-Time Automatic Speech Recognition
WhisperPipe delivers 89 ms median latency and 48% lower peak GPU memory than standard Whisper while keeping word error rate within 2% of the offline model.
-
Scaling Properties of Continuous Diffusion Spoken Language Models
Continuous diffusion spoken language models follow scaling laws for loss and phoneme divergence and generate emotive multi-speaker speech at 16B scale, though long-form coherence stays difficult.
-
AudioKV: KV Cache Eviction in Efficient Large Audio Language Models
AudioKV prioritizes audio-critical attention heads identified via ASR analysis and applies spectral score smoothing to evict KV cache tokens, achieving high compression with minimal accuracy loss in LALMs.
-
Quantifying the Cost of Manual Navigation: A Comparison of Gesture-Based Magnification versus Direct Access Reading in Digital Layout-based Documents
Large-print editions of layout-based documents outperform gesture-based magnification by 18% in reading speed and 30% in target location speed while restoring natural reading strategies and reducing workload.