Show newer
arXiv - CSCL

DiariST: Streaming Speech Translation with Speaker Diarization. (arXiv:2309.08007v2 [eess.AS] UPDATED) 

arxiv.org/abs/2309.08007

0
arXiv - CSCL

SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models. (arXiv:2308.16692v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.16692

0
arXiv - CSCL

Large Language Models Vote: Prompting for Rare Disease Identification. (arXiv:2308.12890v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.12890

0
arXiv - CSCL

Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AI. (arXiv:2308.07213v2 [cs.HC] UPDATED) 

arxiv.org/abs/2308.07213

0
arXiv - CSCL

OWQ: Lessons learned from activation outliers for weight quantization in large language models. (arXiv:2306.02272v3 [cs.CL] UPDATED) 

arxiv.org/abs/2306.02272

0
arXiv - CSCL

Learning to Generate Novel Scientific Directions with Contextualized Literature-based Discovery. (arXiv:2305.14259v4 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14259

0
arXiv - CSCL

SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification. (arXiv:2305.09781v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.09781

0
arXiv - CSCL

Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings. (arXiv:2305.02317v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.02317

0
arXiv - CSCL

Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement. (arXiv:2304.14391v4 [cs.RO] UPDATED) 

arxiv.org/abs/2304.14391

0
arXiv - CSCL

Learning to Generate Questions by Enhancing Text Generation with Sentence Selection. (arXiv:2212.12192v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.12192

0
arXiv - CSCL

AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents. (arXiv:2401.12963v1 [cs.RO]) 

arxiv.org/abs/2401.12963

0
arXiv - CSCL

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding. (arXiv:2401.12954v1 [cs.CL]) 

arxiv.org/abs/2401.12954

0
arXiv - CSCL

Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion. (arXiv:2401.12947v1 [cs.CL]) 

arxiv.org/abs/2401.12947

0
arXiv - CSCL

Multicultural Name Recognition For Previously Unseen Names. (arXiv:2401.12941v1 [cs.CL]) 

arxiv.org/abs/2401.12941

0
arXiv - CSCL

Red Teaming Visual Language Models. (arXiv:2401.12915v1 [cs.AI]) 

arxiv.org/abs/2401.12915

0
arXiv - CSCL

From Understanding to Utilization: A Survey on Explainability for Large Language Models. (arXiv:2401.12874v1 [cs.CL]) 

arxiv.org/abs/2401.12874

0
arXiv - CSCL

Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model. (arXiv:2401.12873v1 [cs.CL]) 

arxiv.org/abs/2401.12873

0
arXiv - CSCL

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning. (arXiv:2401.12863v1 [cs.CL]) 

arxiv.org/abs/2401.12863

0
arXiv - CSCL

Gradient Flow of Energy: A General and Efficient Approach for Entity Alignment Decoding. (arXiv:2401.12798v1 [cs.IR]) 

arxiv.org/abs/2401.12798

0
arXiv - CSCL

Benchmarking LLMs via Uncertainty Quantification. (arXiv:2401.12794v1 [cs.CL]) 

arxiv.org/abs/2401.12794

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