Show newer
arXiv - CSCL

GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation. (arXiv:2303.14655v2 [cs.CV] UPDATED) 

arxiv.org/abs/2303.14655

0
arXiv - CSCL

Towards Inferential Reproducibility of Machine Learning Research. (arXiv:2302.04054v6 [cs.LG] UPDATED) 

arxiv.org/abs/2302.04054

0
arXiv - CSCL

Large-scale investigation of weakly-supervised deep learning for the fine-grained semantic indexing of biomedical literature. (arXiv:2301.09350v2 [cs.CL] UPDATED) 

arxiv.org/abs/2301.09350

0
arXiv - CSCL

Two-stage LLM Fine-tuning with Less Specialization and More Generalization. (arXiv:2211.00635v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.00635

0
arXiv - CSCL

Latent Diffusion Energy-Based Model for Interpretable Text Modeling. (arXiv:2206.05895v4 [cs.LG] UPDATED) 

arxiv.org/abs/2206.05895

0
arXiv - CSCL

Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training. (arXiv:2110.14883v3 [cs.LG] UPDATED) 

arxiv.org/abs/2110.14883

0
arXiv - CSCL

Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars. (arXiv:2109.04939v3 [cs.CL] UPDATED) 

arxiv.org/abs/2109.04939

0
arXiv - CSCL

Text as Environment: A Deep Reinforcement Learning Text Readability Assessment Model. (arXiv:1912.05957v3 [cs.CL] UPDATED) 

arxiv.org/abs/1912.05957

0
arXiv - CSCL

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning. (arXiv:2310.03731v1 [cs.CL]) 

arxiv.org/abs/2310.03731

0
arXiv - CSCL

Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer. (arXiv:2310.03724v1 [cs.CL]) 

arxiv.org/abs/2310.03724

0
arXiv - CSCL

A Long Way to Go: Investigating Length Correlations in RLHF. (arXiv:2310.03716v1 [cs.CL]) 

arxiv.org/abs/2310.03716

0
arXiv - CSCL

DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines. (arXiv:2310.03714v1 [cs.CL]) 

arxiv.org/abs/2310.03714

0
arXiv - CSCL

Agent Instructs Large Language Models to be General Zero-Shot Reasoners. (arXiv:2310.03710v1 [cs.CL]) 

arxiv.org/abs/2310.03710

0
arXiv - CSCL

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!. (arXiv:2310.03693v1 [cs.CL]) 

arxiv.org/abs/2310.03693

0
arXiv - CSCL

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers. (arXiv:2310.03686v1 [cs.CL]) 

arxiv.org/abs/2310.03686

0
arXiv - CSCL

GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction. (arXiv:2310.03668v1 [cs.CL]) 

arxiv.org/abs/2310.03668

0
arXiv - CSCL

MapperGPT: Large Language Models for Linking and Mapping Entities. (arXiv:2310.03666v1 [cs.CL]) 

arxiv.org/abs/2310.03666

0
arXiv - CSCL

TRAM: Bridging Trust Regions and Sharpness Aware Minimization. (arXiv:2310.03646v1 [cs.LG]) 

arxiv.org/abs/2310.03646

0
arXiv - CSCL

Evaluating Self-Supervised Speech Representations for Indigenous American Languages. (arXiv:2310.03639v1 [cs.CL]) 

arxiv.org/abs/2310.03639

0
arXiv - CSCL

CLEVRER-Humans: Describing Physical and Causal Events the Human Way. (arXiv:2310.03635v1 [cs.AI]) 

arxiv.org/abs/2310.03635

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