7 papers
Oilbird: Training-Free Speculative Decoding with Keys the Verifier Already Computes
Tao Jin, Phuong Minh Nguyen, Zhenzhu Yan +2
Training-free speculative decoding drafts by matching an exact suffix of the context against a pool of earlier context. That lookup misses correct drafts already in the pool, most…
X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
Di Cao, Dongjie Fu, Hai Yu +3
While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a sign…
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Xinlei Yu, Zhangquan Chen, Yongbo He +36
Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an inc…
A Certified Higher Order Quantum Framework for CSA and Margin-Aware Collateral Optimization
Tao Jin, Stuart Florescu
Collateral allocation for uncleared derivatives is a legally constrained and operationally discrete optimization problem. Institutions must satisfy margin requirements while respec…
Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
Tao Jin, Phuong Minh Nguyen, Naoya Inoue
Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tre…
Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval
Ruofan Hu, Yan Xia, Minjie Hong +5
Multimodal large language models (MLLMs) have seen substantial progress in recent years. However, their ability to represent multimodal information in the acoustic domain remains u…