| 5671. |
Tropical Geometry of Deep Neural Networks (arxiv.org) |
|
1 point by michelpp on Mar 9, 2024 | hide | past | pdf | discuss
|
|
| 5672. |
Algorithmic Complexities in Backpropagation and Tropical Neural Networks (arxiv.org) |
|
2 points by michelpp on Mar 9, 2024 | hide | past | pdf | discuss
|
|
| 5673. |
Self-Retrieval: Building an information retrieval system with one LLM (arxiv.org) |
|
200 points by PaulHoule on Mar 9, 2024 | hide | past | pdf | 29 comments
|
|
| 5674. |
Data Contamination and Evaluation Malpractices in Closed-Source LLMs (arxiv.org) |
|
2 points by adrianhoward on Mar 8, 2024 | hide | past | pdf | discuss
|
|
| 5675. |
Bootstrapping Cognitive Agents with a Large Language Model (arxiv.org) |
|
1 point by PaulHoule on Mar 8, 2024 | hide | past | pdf | discuss
|
|
| 5676. |
Gradient Low-Rank Projection (GaLore) reduces LLM training memory usage by 63% (arxiv.org) |
|
1 point by apsec112 on Mar 8, 2024 | hide | past | pdf | discuss
|
|
| 5677. |
Yi: Open Foundation Models (arxiv.org) |
|
1 point by tosh on Mar 8, 2024 | hide | past | pdf | discuss
|
|
| 5678. |
Can Large Language Models Reason and Plan? (arxiv.org) |
|
2 points by Jimmc414 on Mar 8, 2024 | hide | past | pdf | 1 comment
|
|
| 5679. |
The Unreasonable Effectiveness of Eccentric Automatic Prompts (arxiv.org) |
|
1 point by Jimmc414 on Mar 8, 2024 | hide | past | pdf | discuss
|
|
| 5680. |
Exposing Systemic Vulnerabilities of LLMs Through a Prompt Hacking Competition (arxiv.org) |
|
2 points by sohkamyung on Mar 8, 2024 | hide | past | pdf | discuss
|
|
| 5681. |
Machine learning and information theory concepts towards an AI Mathematician (arxiv.org) |
|
3 points by carlossouza on Mar 8, 2024 | hide | past | pdf | 1 comment
|
|
| 5682. |
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for Text-to-Image (arxiv.org) |
|
1 point by artninja1988 on Mar 8, 2024 | hide | past | pdf | discuss
|
|
| 5683. |
PersonaLLM: Investigating the Ability of LLMs to Express Personality Traits (arxiv.org) |
|
1 point by swyx on Mar 7, 2024 | hide | past | pdf | discuss
|
|
| 5684. |
Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers (arxiv.org) |
|
2 points by PaulHoule on Mar 7, 2024 | hide | past | pdf | discuss
|
|
| 5685. |
Large language models surpass human experts in predicting neuroscience results (arxiv.org) |
|
2 points by MauranKilom on Mar 7, 2024 | hide | past | pdf | discuss
|
|
| 5686. |
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection (arxiv.org) |
|
6 points by victormustar on Mar 7, 2024 | hide | past | pdf | discuss
|
|
| 5687. |
RepairLLaMA: Efficient Representations and Fine-Tuned Adapter for Program Repair (arxiv.org) |
|
2 points by andre15silva on Mar 7, 2024 | hide | past | pdf | discuss
|
|
| 5688. |
Learning to Decode Collaboratively with Multiple Language Models (arxiv.org) |
|
2 points by padolsey on Mar 7, 2024 | hide | past | pdf | discuss
|
|
| 5689. |
SaulLM-7B: A Pioneering Large Language Model for Law (arxiv.org) |
|
3 points by telmop on Mar 7, 2024 | hide | past | pdf | discuss
|
|
| 5690. |
Curious Decline of Linguistic Diversity: Training LLMs on Synthetic Text (2023) (arxiv.org) |
|
2 points by 1vuio0pswjnm7 on Mar 7, 2024 | hide | past | pdf | 1 comment
|
|
| 5691. |
How Do LLMs Answer Multiple-Choice Questions Without the Question? (arxiv.org) |
|
2 points by smusamashah on Mar 6, 2024 | hide | past | pdf | discuss
|
|
| 5692. |
MacGyver: Are Large Language Models Creative Problem Solvers? (arxiv.org) |
|
1 point by ulrischa on Mar 6, 2024 | hide | past | pdf | 1 comment
|
|
| 5693. |
LDB: A Large Language Model Debugger via Verifying Runtime Execution (arxiv.org) |
|
1 point by dmarchand90 on Mar 6, 2024 | hide | past | pdf | 1 comment
|
|
| 5694. |
Design2Code: How Far Are We from Automating Front-End Engineering? (arxiv.org) |
|
1 point by victormustar on Mar 6, 2024 | hide | past | pdf | discuss
|
|
| 5695. |
Sora: Review on Background, Tech, Limits, and Opportunities of Vision Models (arxiv.org) |
|
33 points by shinryudbz on Mar 6, 2024 | hide | past | pdf | 2 comments
|
|
| 5696. |
If in a Crowdsourced Data Annotation Pipeline, a GPT-4 (arxiv.org) |
|
1 point by fatso784 on Mar 5, 2024 | hide | past | pdf | discuss
|
|
| 5697. |
StarCoder 2 and the Stack v2 (arxiv.org) |
|
1 point by tosh on Mar 5, 2024 | hide | past | pdf | discuss
|
|
| 5698. |
Dialect prejudice predicts AI decisions about people's character (arxiv.org) |
|
4 points by saassiopeia on Mar 5, 2024 | hide | past | pdf | 2 comments
|
|
| 5699. |
Why do tree-based models still outperform deep learning on tabular data? (2022) (arxiv.org) |
|
212 points by tosh on Mar 5, 2024 | hide | past | pdf | 111 comments
|
|
| 5700. |
LLM Ensemble Prediction Capabilities Match Human Crowd Accuracy (arxiv.org) |
|
1 point by SchoeneggerP on Mar 5, 2024 | hide | past | pdf | 2 comments
|
|
|
| More |
