Show newer
arXiv - CSCL

Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding. (arXiv:2306.02858v4 [cs.CL] UPDATED) 

arxiv.org/abs/2306.02858

0
arXiv - CSCL

Training Priors Predict Text-To-Image Model Performance. (arXiv:2306.01755v2 [cs.CV] UPDATED) 

arxiv.org/abs/2306.01755

0
arXiv - CSCL

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction. (arXiv:2306.01439v2 [cs.LG] UPDATED) 

arxiv.org/abs/2306.01439

0
arXiv - CSCL

Natural Language Decompositions of Implicit Content Enable Better Text Representations. (arXiv:2305.14583v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14583

0
arXiv - CSCL

Is a Prestigious Job the same as a Prestigious Country? A Case Study on Multilingual Sentence Embeddings and European Countries. (arXiv:2305.14482v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14482

0
arXiv - CSCL

Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach. (arXiv:2305.14410v2 [cs.CV] UPDATED) 

arxiv.org/abs/2305.14410

0
arXiv - CSCL

Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality. (arXiv:2305.13812v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13812

0
arXiv - CSCL

Asking Clarification Questions to Handle Ambiguity in Open-Domain QA. (arXiv:2305.13808v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13808

0
arXiv - CSCL

A Diachronic Analysis of Paradigm Shifts in NLP Research: When, How, and Why?. (arXiv:2305.12920v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12920

0
arXiv - CSCL

Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation. (arXiv:2305.12786v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12786

0
arXiv - CSCL

TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks. (arXiv:2305.11430v2 [cs.AI] UPDATED) 

arxiv.org/abs/2305.11430

0
arXiv - CSCL

DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining. (arXiv:2305.10429v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.10429

0
arXiv - CSCL

FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy. (arXiv:2305.10307v4 [cs.CL] UPDATED) 

arxiv.org/abs/2305.10307

0
arXiv - CSCL

StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure. (arXiv:2305.05588v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.05588

0
arXiv - CSCL

API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs. (arXiv:2304.08244v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.08244

0
arXiv - CSCL

Goal Driven Discovery of Distributional Differences via Language Descriptions. (arXiv:2302.14233v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.14233

0
arXiv - CSCL

Knowledge Distillation $\approx$ Label Smoothing: Fact or Fallacy?. (arXiv:2301.12609v4 [cs.LG] UPDATED) 

arxiv.org/abs/2301.12609

0
arXiv - CSCL

JASMINE: Arabic GPT Models for Few-Shot Learning. (arXiv:2212.10755v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10755

0
arXiv - CSCL

Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval. (arXiv:2212.10526v3 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10526

0
arXiv - CSCL

Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks. (arXiv:2212.09912v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.09912

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