Show newer
arXiv - CSCL

Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions. (arXiv:2310.03016v1 [cs.LG]) 

arxiv.org/abs/2310.03016

0
arXiv - CSCL

From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference. (arXiv:2310.03003v1 [cs.CL]) 

arxiv.org/abs/2310.03003

0
arXiv - CSCL

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models. (arXiv:2310.02998v1 [cs.CV]) 

arxiv.org/abs/2310.02998

0
arXiv - CSCL

Kosmos-G: Generating Images in Context with Multimodal Large Language Models. (arXiv:2310.02992v1 [cs.CV]) 

arxiv.org/abs/2310.02992

0
arXiv - CSCL

xVal: A Continuous Number Encoding for Large Language Models. (arXiv:2310.02989v1 [stat.ML]) 

arxiv.org/abs/2310.02989

0
arXiv - CSCL

Scaling Laws for Associative Memories. (arXiv:2310.02984v1 [stat.ML]) 

arxiv.org/abs/2310.02984

0
arXiv - CSCL

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors. (arXiv:2310.02980v1 [cs.LG]) 

arxiv.org/abs/2310.02980

0
arXiv - CSCL

T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation. (arXiv:2310.02977v1 [cs.CV]) 

arxiv.org/abs/2310.02977

0
arXiv - CSCL

UniverSLU: Universal Spoken Language Understanding for Diverse Classification and Sequence Generation Tasks with a Single Network. (arXiv:2310.02973v1 [cs.CL]) 

arxiv.org/abs/2310.02973

0
arXiv - CSCL

Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model. (arXiv:2310.02971v1 [eess.AS]) 

arxiv.org/abs/2310.02971

0
arXiv - CSCL

DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning. (arXiv:2310.02954v1 [cs.CL]) 

arxiv.org/abs/2310.02954

0
arXiv - CSCL

JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning. (arXiv:2310.02953v1 [cs.CL]) 

arxiv.org/abs/2310.02953

0
arXiv - CSCL

Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models. (arXiv:2310.02949v1 [cs.CL]) 

arxiv.org/abs/2310.02949

0
arXiv - CSCL

LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models. (arXiv:2310.02943v1 [cs.CL]) 

arxiv.org/abs/2310.02943

0
arXiv - CSCL

Assessing Large Language Models on Climate Information. (arXiv:2310.02932v1 [cs.CL]) 

arxiv.org/abs/2310.02932

0
arXiv - CSCL

Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transformers. (arXiv:2310.02905v1 [cs.LG]) 

arxiv.org/abs/2310.02905

0
arXiv - CSCL

Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation. (arXiv:2310.02876v1 [cs.CL]) 

arxiv.org/abs/2310.02876

0
arXiv - CSCL

Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation. (arXiv:2310.02842v1 [cs.CL]) 

arxiv.org/abs/2310.02842

0
arXiv - CSCL

DOMINO: A Dual-System for Multi-step Visual Language Reasoning. (arXiv:2310.02804v1 [cs.CL]) 

arxiv.org/abs/2310.02804

0
arXiv - CSCL

Low Resource Summarization using Pre-trained Language Models. (arXiv:2310.02790v1 [cs.CL]) 

arxiv.org/abs/2310.02790

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.

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy