Tag
This paper proposes a causal model for understanding and counteracting sandbagging in AI models, using interventions like reference grafting and context grafting to restore capabilities in open-weight models.
The paper introduces BF1, a causal dyadic sparse-attention retrofit designed to improve the efficiency of transformers for long-context processing.
X2Streaming-TTS presents a causal token-level text-to-speech framework for true streaming synthesis, using causal commitment and speech-state inheritance to handle uncertain text prefixes and maintain acoustic continuity in low-latency spoken dialogue systems.
The paper proposes Super Star, a real-time framework for online co-speech gesture generation in digital humans using a causal multimodal autoregressive model with streaming speech and user feedback for continual adaptation.
A Columbia University paper introduces a strictly causal Hidden Markov Model that adapts to changing market regimes, achieving a 2.18 Sharpe ratio vs 1.18 for SPX buy & hold and reducing max drawdown from -14.62% to -5.43% during the 2025 selloff.
StreamForce is a causal, unified video generation model that provides real-time, physically grounded responses to time-varying forces through a distillation pipeline and autoregressive architecture, achieving state-of-the-art performance in force adherence and motion realism.