DeALR: Decoupled Audio-Latent Optimization with Acoustic Backtracking for Test-Time Reasoning
cs.SD
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Qwen2-Audio Technical Report
- Think before you speak: Training Language Models With Pause Tokens
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Training Large Language Models to Reason in a Continuous Latent Space
- Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
- Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
- Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
- Training language models to follow instructions with human feedback
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models
- SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Qwen2.5-Omni Technical Report
- Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
- Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
- Multimodal Chain-of-Thought Reasoning in Language Models
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems