| 4891. |
A Critical Study of What Code-LLMs (Do Not) Learn (arxiv.org) |
|
2 points by PaulHoule on Jun 30, 2024 | hide | past | pdf | discuss
|
|
| 4892. |
Newswire: A Large-Scale Structured Database of a Century of Historical News (arxiv.org) |
|
2 points by PaulHoule on Jun 29, 2024 | hide | past | pdf | discuss
|
|
| 4893. |
Artificial needles to real haystacks: Improving retrieval capabilities in LLMs (arxiv.org) |
|
101 points by veryluckyxyz on Jun 29, 2024 | hide | past | pdf | 21 comments
|
|
| 4894. |
From Decoding to Meta-Generation: (LLMs) (arxiv.org) |
|
2 points by veryluckyxyz on Jun 29, 2024 | hide | past | pdf | discuss
|
|
| 4895. |
Do LLMs Have Distinct and Consistent Personality? (arxiv.org) |
|
2 points by PaulHoule on Jun 28, 2024 | hide | past | pdf | discuss
|
|
| 4896. |
Context-Augmented Retrieval: A Novel Framework for Fast Information Retrieval (arxiv.org) |
|
4 points by dmezzetti on Jun 28, 2024 | hide | past | pdf | 1 comment
|
|
| 4897. |
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon (arxiv.org) |
|
1 point by famouswaffles on Jun 28, 2024 | hide | past | pdf | discuss
|
|
| 4898. |
OpenAI's GPTs can be abused (arxiv.org) |
|
2 points by titaniumrain on Jun 28, 2024 | hide | past | pdf | discuss
|
|
| 4899. |
The Paradox of Learning to Reason from Data (2022) (arxiv.org) |
|
2 points by PaulHoule on Jun 27, 2024 | hide | past | pdf | 1 comment
|
|
| 4900. |
People cannot distinguish GPT-4 from a human in a Turing test (arxiv.org) |
|
1 point by PaulHoule on Jun 27, 2024 | hide | past | pdf | 2 comments
|
|
| 4901. |
AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval (arxiv.org) |
|
1 point by PaulHoule on Jun 27, 2024 | hide | past | pdf | discuss
|
|
| 4902. |
A Tutorial on Thompson Sampling (arxiv.org) |
|
1 point by sebg on Jun 27, 2024 | hide | past | pdf | discuss
|
|
| 4903. |
A Tutorial on Bayesian Optimization (arxiv.org) |
|
2 points by sebg on Jun 27, 2024 | hide | past | pdf | discuss
|
|
| 4904. |
Towards Robust Detection of AI-Generated Videos (arxiv.org) |
|
2 points by gnabgib on Jun 27, 2024 | hide | past | pdf | discuss
|
|
| 4905. |
Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell (arxiv.org) |
|
3 points by PaulHoule on Jun 27, 2024 | hide | past | pdf | discuss
|
|
| 4906. |
Exploring Design Choices for Building Language-Specific LLMs (arxiv.org) |
|
1 point by PaulHoule on Jun 26, 2024 | hide | past | pdf | discuss
|
|
| 4907. |
Evaluating Reasoning by LLMs Using the New York Times Connections Word Game (arxiv.org) |
|
2 points by PaulHoule on Jun 26, 2024 | hide | past | pdf | discuss
|
|
| 4908. |
Updating Clip to Prefer Descriptions over Captions (arxiv.org) |
|
1 point by PaulHoule on Jun 26, 2024 | hide | past | pdf | discuss
|
|
| 4909. |
Warp: On the Benefits of Weight Averaged Rewarded Policies (arxiv.org) |
|
2 points by veryluckyxyz on Jun 26, 2024 | hide | past | pdf | discuss
|
|
| 4910. |
A Benchmark for Learning to Translate a New Language from One Grammar Book (arxiv.org) |
|
1 point by benbreen on Jun 26, 2024 | hide | past | pdf | discuss
|
|
| 4911. |
How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad (arxiv.org) |
|
6 points by marojejian on Jun 26, 2024 | hide | past | pdf | discuss
|
|
| 4912. |
Driven by Compression Progress (Schmidhuber, 2008) (arxiv.org) |
|
2 points by yamrzou on Jun 25, 2024 | hide | past | pdf | 1 comment
|
|
| 4913. |
Automated Large Language Models Reasoning with Bidirectional Chaining (arxiv.org) |
|
2 points by PaulHoule on Jun 25, 2024 | hide | past | pdf | discuss
|
|
| 4914. |
When Is an Embedding Model More Promising Than Another? (arxiv.org) |
|
1 point by PaulHoule on Jun 25, 2024 | hide | past | pdf | discuss
|
|
| 4915. |
Inference Acceleration for Large Language Models on CPUs (arxiv.org) |
|
3 points by PaulHoule on Jun 25, 2024 | hide | past | pdf | discuss
|
|
| 4916. |
Measuring psychological depth in large language models (arxiv.org) |
|
1 point by dr_dshiv on Jun 25, 2024 | hide | past | pdf | discuss
|
|
| 4917. |
DataComp-LM: In search of the next generation training sets for language models (arxiv.org) |
|
2 points by mji on Jun 25, 2024 | hide | past | pdf | discuss
|
|
| 4918. |
Should AI optimize your code? A studio (arxiv.org) |
|
1 point by silverret on Jun 24, 2024 | hide | past | pdf | discuss
|
|
| 4919. |
Assessing the Emergent Symbolic Reasoning Abilities of LLMs (arxiv.org) |
|
1 point by PaulHoule on Jun 24, 2024 | hide | past | pdf | discuss
|
|
| 4920. |
Self-Supervised Learning from Images with a Joint-Embedding Predictive Archi (arxiv.org) |
|
1 point by ngrilly on Jun 23, 2024 | hide | past | pdf | discuss
|
|
|
| More |
