Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires learning a new modality and a wide range of speech-specific instructions in addition to those supported by text LLMs. Existing SLM training approaches largely replicate the text LLM training paradigm by synthesizing large-scale speech pre-training and instruction-tuning datasets. However, this strategy is difficult to scale, since speech sequences are significantly longer than text sequences. In this paper, we propose SpeechCombine, an instruct
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Whisper-Lite →
- PossiblePossibly related (embedding) · 51%Looking for feedback on a small test SLM I built completely from scratch [P] →
- PossiblePossibly related (embedding) · 49%chrisliu298/awesome-llm-unlearning →
- PossiblePossibly related (embedding) · 49%Transformer →
- PossiblePossibly related (embedding) · 49%thu-pacman/chitu →
- LinkedLinked via arxiv author · 85%Congrui Du →
“Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning”
- LinkedLinked via arxiv author · 85%Yang Zhang →
“Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning”
- LinkedLinked via arxiv author · 85%Kaizhi Qian →
“Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning”