Show newer
arXiv - CSCL

Context Matters: Data-Efficient Augmentation of Large Language Models for Scientific Applications. (arXiv:2312.07069v2 [cs.CL] UPDATED) 

arxiv.org/abs/2312.07069

0
arXiv - CSCL

ConSequence: Synthesizing Logically Constrained Sequences for Electronic Health Record Generation. (arXiv:2312.05964v2 [cs.LG] UPDATED) 

arxiv.org/abs/2312.05964

0
arXiv - CSCL

RLHF and IIA: Perverse Incentives. (arXiv:2312.01057v2 [cs.LG] UPDATED) 

arxiv.org/abs/2312.01057

0
arXiv - CSCL

Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation. (arXiv:2311.18260v3 [eess.IV] UPDATED) 

arxiv.org/abs/2311.18260

0
arXiv - CSCL

Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models. (arXiv:2311.07919v2 [eess.AS] UPDATED) 

arxiv.org/abs/2311.07919

0
arXiv - CSCL

3M-TRANSFORMER: A Multi-Stage Multi-Stream Multimodal Transformer for Embodied Turn-Taking Prediction. (arXiv:2310.14859v3 [cs.CV] UPDATED) 

arxiv.org/abs/2310.14859

0
arXiv - CSCL

FedJudge: Federated Legal Large Language Model. (arXiv:2309.08173v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.08173

0
arXiv - CSCL

From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery. (arXiv:2309.05203v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.05203

0
arXiv - CSCL

Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum. (arXiv:2308.14034v2 [cs.AI] UPDATED) 

arxiv.org/abs/2308.14034

0
arXiv - CSCL

Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis. (arXiv:2308.12466v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.12466

0
arXiv - CSCL

An Empirical Study of CLIP for Text-based Person Search. (arXiv:2308.10045v2 [cs.CV] UPDATED) 

arxiv.org/abs/2308.10045

0
arXiv - CSCL

Universal and Transferable Adversarial Attacks on Aligned Language Models. (arXiv:2307.15043v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.15043

0
arXiv - CSCL

Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers. (arXiv:2307.14367v2 [q-bio.QM] UPDATED) 

arxiv.org/abs/2307.14367

0
arXiv - CSCL

Layer-wise Representation Fusion for Compositional Generalization. (arXiv:2307.10799v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.10799

0
arXiv - CSCL

Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations. (arXiv:2307.05722v2 [cs.AI] UPDATED) 

arxiv.org/abs/2307.05722

0
arXiv - CSCL

Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study. (arXiv:2304.06762v3 [cs.CL] UPDATED) 

arxiv.org/abs/2304.06762

0
arXiv - CSCL

BloombergGPT: A Large Language Model for Finance. (arXiv:2303.17564v3 [cs.LG] UPDATED) 

arxiv.org/abs/2303.17564

0
arXiv - CSCL

DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4. (arXiv:2303.11032v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.11032

0
arXiv - CSCL

AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning. (arXiv:2303.10512v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.10512

0
arXiv - CSCL

Contrastive variational information bottleneck for aspect-based sentiment analysis. (arXiv:2303.02846v3 [cs.CL] UPDATED) 

arxiv.org/abs/2303.02846

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