| 4831. |
Is machine learning good or bad for the natural sciences? (arxiv.org) |
|
2 points by privong on Jul 12, 2024 | hide | past | pdf | discuss
|
|
| 4832. |
LoPT: Low-Rank Prompt Tuning for Parameter Efficient Language Models (arxiv.org) |
|
3 points by vinni2 on Jul 12, 2024 | hide | past | pdf | discuss
|
|
| 4833. |
Formal Aspects of Language Modeling (arxiv.org) |
|
2 points by Anon84 on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4834. |
When LLMs Play the Telephone Game: Cumulative Changes and Attractors in Iterated (arxiv.org) |
|
2 points by rcmcintosh on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4835. |
Training a time series model using transformers at Datadog (arxiv.org) |
|
27 points by dbenamy on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4836. |
Facts About Building Retrieval Augmented Generation-Based Chatbots (arxiv.org) |
|
1 point by belter on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4837. |
CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy (arxiv.org) |
|
3 points by aeontech on Jul 11, 2024 | hide | past | pdf | 1 comment
|
|
| 4838. |
Distilling System 2 into System 1 (arxiv.org) |
|
4 points by tosh on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4839. |
OpenDiLoCo: Open-Source Framework for Distributed Low-Communication Training (arxiv.org) |
|
4 points by Mougatine on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4840. |
Cascade Reward Sampling for Efficient Decoding-Time Alignment (arxiv.org) |
|
3 points by Garcia98 on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4841. |
PaliGemma: A versatile 3B VLM for transfer (arxiv.org) |
|
5 points by tosh on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4842. |
Mixture of a Million Experts (arxiv.org) |
|
3 points by quxinxin on Jul 11, 2024 | hide | past | pdf | discuss
|
|
| 4843. |
Abstraction and Reasoning Corpus via Procedural Example Generation (arxiv.org) |
|
1 point by georgehill on Jul 10, 2024 | hide | past | pdf | discuss
|
|
| 4844. |
Dola Decoding by Contrasting Layers Improves Factuality in Large Language Models (arxiv.org) |
|
58 points by johnsutor on Jul 10, 2024 | hide | past | pdf | 43 comments
|
|
| 4845. |
Training of Physical Neural Networks (arxiv.org) |
|
142 points by Anon84 on Jul 10, 2024 | hide | past | pdf | 46 comments
|
|
| 4846. |
Data curation via joint example selection accelerates multimodal learning (arxiv.org) |
|
2 points by quxinxin on Jul 10, 2024 | hide | past | pdf | discuss
|
|
| 4847. |
Can Go AIs be adversarially robust? (arxiv.org) |
|
2 points by programd on Jul 9, 2024 | hide | past | pdf | discuss
|
|
| 4848. |
Teaching Generative Language Models to Reference Answers to Biomedical Questions (arxiv.org) |
|
2 points by nikolamilosevic on Jul 9, 2024 | hide | past | pdf | discuss
|
|
| 4849. |
Mixture of a Million Experts (arxiv.org) |
|
6 points by fofoz on Jul 9, 2024 | hide | past | pdf | discuss
|
|
| 4850. |
An Adaptive Stochastic Gradient Method with Non-Negative Gauss-Newton Stepsizes (arxiv.org) |
|
2 points by fofoz on Jul 9, 2024 | hide | past | pdf | discuss
|
|
| 4851. |
Reasoning or Simply Next Token Prediction? Stress-Testing Large LLMs (arxiv.org) |
|
2 points by PaulHoule on Jul 8, 2024 | hide | past | pdf | discuss
|
|
| 4852. |
Anime Popularity Prediction: A Multimodal Approach Using Deep Learning (arxiv.org) |
|
1 point by PaulHoule on Jul 8, 2024 | hide | past | pdf | discuss
|
|
| 4853. |
An Adaptive Stochastic Gradient Method with Non-Negative Gauss-Newton Stepsizes (arxiv.org) |
|
2 points by georgehill on Jul 8, 2024 | hide | past | pdf | discuss
|
|
| 4854. |
MuMath-Code on ArXiv (arxiv.org) |
|
2 points by pajop on Jul 8, 2024 | hide | past | pdf | discuss
|
|
| 4855. |
Learning to (Learn at Test Time): RNNs with Expressive Hidden States (arxiv.org) |
|
10 points by birriel on Jul 8, 2024 | hide | past | pdf | discuss
|
|
| 4856. |
LLM Critics Help Catch Bugs in Mathematics (arxiv.org) |
|
2 points by quxinxin on Jul 8, 2024 | hide | past | pdf | discuss
|
|
| 4857. |
Agentless: Demystifying LLM-Based Software Engineering Agents (arxiv.org) |
|
4 points by dmezzetti on Jul 8, 2024 | hide | past | pdf | discuss
|
|
| 4858. |
TextGrad – Backpropagation through text feedback (arxiv.org) |
|
2 points by danielhanchen on Jul 7, 2024 | hide | past | pdf | discuss
|
|
| 4859. |
Optimizing Sub-Billion Parameter Language Models for On-Device Use Cases (arxiv.org) |
|
2 points by fzliu on Jul 7, 2024 | hide | past | pdf | discuss
|
|
| 4860. |
Assessing the Quality of Code Generation by ChatGPT (arxiv.org) |
|
3 points by lolinder on Jul 7, 2024 | hide | past | pdf | discuss
|
|
|
| More |
