Show newer
arXiv - CSCL

Time-Varying Quasi-Closed-Phase Analysis for Accurate Formant Tracking in Speech Signals. (arXiv:2308.16540v1 [eess.AS]) 

arxiv.org/abs/2308.16540

0
arXiv - CSCL

The Smart Data Extractor, a Clinician Friendly Solution to Accelerate and Improve the Data Collection During Clinical Trials. (arXiv:2308.16537v1 [q-bio.QM]) 

arxiv.org/abs/2308.16537

0
arXiv - CSCL

Generalised Winograd Schema and its Contextuality. (arXiv:2308.16498v1 [cs.CL]) 

arxiv.org/abs/2308.16498

0
arXiv - CSCL

Transformer Compression via Subspace Projection. (arXiv:2308.16475v1 [cs.CL]) 

arxiv.org/abs/2308.16475

0
arXiv - CSCL

Enhancing Subtask Performance of Multi-modal Large Language Model. (arXiv:2308.16474v1 [cs.CL]) 

arxiv.org/abs/2308.16474

0
arXiv - CSCL

Link Prediction for Wikipedia Articles as a Natural Language Inference Task. (arXiv:2308.16469v1 [cs.CL]) 

arxiv.org/abs/2308.16469

0
arXiv - CSCL

Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models. (arXiv:2308.16463v1 [cs.CV]) 

arxiv.org/abs/2308.16463

0
arXiv - CSCL

BioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge. (arXiv:2308.16458v1 [cs.LG]) 

arxiv.org/abs/2308.16458

0
arXiv - CSCL

Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer. (arXiv:2308.16415v1 [cs.CL]) 

arxiv.org/abs/2308.16415

0
arXiv - CSCL

Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations. (arXiv:2308.16349v1 [cs.CL]) 

arxiv.org/abs/2308.16349

0
arXiv - CSCL

ToddlerBERTa: Exploiting BabyBERTa for Grammar Learning and Language Understanding. (arXiv:2308.16336v1 [cs.CL]) 

arxiv.org/abs/2308.16336

0
arXiv - CSCL

FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions. (arXiv:2308.15214v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.15214

0
arXiv - CSCL

SpikeBERT: A Language Spikformer Trained with Two-Stage Knowledge Distillation from BERT. (arXiv:2308.15122v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.15122

0
arXiv - CSCL

Adapting Text-based Dialogue State Tracker for Spoken Dialogues. (arXiv:2308.15053v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.15053

0
arXiv - CSCL

Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks. (arXiv:2308.14359v2 [cs.AI] UPDATED) 

arxiv.org/abs/2308.14359

0
arXiv - CSCL

Evaluating the Robustness to Instructions of Large Language Models. (arXiv:2308.14306v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.14306

0
arXiv - CSCL

EntropyRank: Unsupervised Keyphrase Extraction via Side-Information Optimization for Language Model-based Text Compression. (arXiv:2308.13399v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.13399

0
arXiv - CSCL

Formal specification terminology for demographic agent-based models of fixed-step single-clocked simulations. (arXiv:2308.13081v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.13081

0
arXiv - CSCL

LibriSQA: Advancing Free-form and Open-ended Spoken Question Answering with a Novel Dataset and Framework. (arXiv:2308.10390v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.10390

0
arXiv - CSCL

Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment. (arXiv:2308.09662v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.09662

0
Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.

Trending now

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy