Cohere's Zero-Shot SLAM-ASR Spoken Language Understanding Paper Featured at EMNLP
Cohere_Labs · x · 2026-10-29
Cohere Labs' work was highlighted at the Impact Speech Conference at EMNLP 2026: Zero-Shot Spoken Language Understanding with SLAM-ASR: What Do Monolingual ASR-Trained Projectors Enable? by Edwin Arkel Rios, Jocelyn Zaruma, Sneh Sourabh, Girish Ewoorkar, Julian Mack, and Bo-Cheng Lai. The paper explores how projectors trained only on monolingual ASR enable zero-shot spoken language understanding.
More from Research
- AI Now Discovers Faster Than Institutions Can Verify: The 200M-Protein Integrity Paradox — mikeflache · 2026-10-29
- FrontierCS 2 reshuffles rankings: Claude Opus 5.5 tops FCI as DeepSeek 1017 degrades — teortaxesTex · 2026-10-29
- Constitutional grafting: character training for open models under $500, skipping $440k of compute — voooooogel · 2026-10-29
- Transformer layers turned into a full-fledged symbolic CPU — yshan2u · 2026-10-29
- NanoDreamer: A 750K-parameter world-model agent trained on a MacBook M5 Pro plays 5 MinAtar games — CatAstro_Piyush · 2026-10-29
- Why You Can't Just Remove Positional Embeddings: Self-Attention Is Permutation Equivariant — cneuralnetwork · 2026-10-29