| 5011. |
Creativity Has Left the Chat: The Price of Debiasing Language Models (arxiv.org) |
|
6 points by behnamoh on Jun 11, 2024 | hide | past | pdf | discuss
|
|
| 5012. |
The Geometry of Categorical and Hierarchical Concepts in Large Language Models (arxiv.org) |
|
123 points by Anon84 on Jun 10, 2024 | hide | past | pdf | 15 comments
|
|
| 5013. |
Semantically Diverse Language Generation for Uncertainty Estimation in LLMs (arxiv.org) |
|
2 points by tosh on Jun 10, 2024 | hide | past | pdf | discuss
|
|
| 5014. |
LLM Agents Can Autonomously Exploit One-Day Vulnerabilities (arxiv.org) |
|
3 points by mikerg87 on Jun 10, 2024 | hide | past | pdf | 1 comment
|
|
| 5015. |
Machine Learning Without Processor: Emergent Learning in Electronic Metamaterial (arxiv.org) |
|
2 points by T-A on Jun 9, 2024 | hide | past | pdf | discuss
|
|
| 5016. |
Teams of LLM Agents Can Exploit Zero-Day Vulnerabilities (arxiv.org) |
|
105 points by belter on Jun 9, 2024 | hide | past | pdf | 75 comments
|
|
| 5017. |
Language Models Are Few-Shot Learners (arxiv.org) |
|
2 points by doener on Jun 9, 2024 | hide | past | pdf | discuss
|
|
| 5018. |
Scalable MatMul-Free Language Modeling (arxiv.org) |
|
205 points by lykahb on Jun 9, 2024 | hide | past | pdf | 30 comments
|
|
| 5019. |
The Geometry of Categorical and Hierarchical Concepts in Large Language Models (arxiv.org) |
|
7 points by convexstrictly on Jun 8, 2024 | hide | past | pdf | discuss
|
|
| 5020. |
Air Gap: Protecting Privacy-Conscious Conversational Agents (arxiv.org) |
|
1 point by skilled on Jun 8, 2024 | hide | past | pdf | discuss
|
|
| 5021. |
Scalable MatMul-Free Language Modeling (arxiv.org) |
|
3 points by throwaway71271 on Jun 8, 2024 | hide | past | pdf | discuss
|
|
| 5022. |
Improving Alignment and Robustness with Short Circuiting (arxiv.org) |
|
2 points by mji on Jun 8, 2024 | hide | past | pdf | discuss
|
|
| 5023. |
Breaking Sabre with a one line change (arxiv.org) |
|
2 points by sohom_datta on Jun 8, 2024 | hide | past | pdf | discuss
|
|
| 5024. |
Scalable Detection of Salient Entities in News Articles (arxiv.org) |
|
2 points by PaulHoule on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5025. |
Benchmarking the Energy Costs of Large Language Model Inference (2023) (arxiv.org) |
|
2 points by mcguire on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5026. |
Will we run out of data? Limits of LLM scaling based on human-generated data (arxiv.org) |
|
1 point by Smith42 on Jun 7, 2024 | hide | past | pdf | 1 comment
|
|
| 5027. |
Open-Endedness Is Essential for Artificial Superhuman Intelligence (arxiv.org) |
|
7 points by artninja1988 on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5028. |
Ask LLMs Directly, "What shapes your bias?" (arxiv.org) |
|
2 points by belter on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5029. |
σ-GPTs: A new approach to autoregressive models (arxiv.org) |
|
293 points by mehulashah on Jun 7, 2024 | hide | past | pdf | 93 comments
|
|
| 5030. |
Potential Field Based Deep Metric Learning (arxiv.org) |
|
2 points by PaulHoule on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5031. |
The illusion of state in state-space models (arxiv.org) |
|
60 points by canjobear on Jun 7, 2024 | hide | past | pdf | 59 comments
|
|
| 5032. |
Scalable MatMul-Free Language Modeling (arxiv.org) |
|
3 points by optimalsolver on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5033. |
Vision-LSTM: xLSTM as Generic Vision Backbone (arxiv.org) |
|
5 points by tosh on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5034. |
Graph Convolutional Branch and Bound (arxiv.org) |
|
6 points by lorenzos98 on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5035. |
Open-Endedness Is Essential for Artificial Superhuman Intelligence (arxiv.org) |
|
5 points by tzury on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5036. |
The Impacts of Data, Ordering, and Intrinsic Dimensionality on Recall in HNSW (arxiv.org) |
|
3 points by jn2clark on Jun 7, 2024 | hide | past | pdf | discuss
|
|
| 5037. |
Reconstructing Training Data from Document Understanding Models (arxiv.org) |
|
1 point by belter on Jun 6, 2024 | hide | past | pdf | 1 comment
|
|
| 5038. |
FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models (arxiv.org) |
|
1 point by gagan30 on Jun 6, 2024 | hide | past | pdf | 1 comment
|
|
| 5039. |
The Geometry of Categorical and Hierarchical Concepts in Large Language Models (arxiv.org) |
|
3 points by dataminer on Jun 6, 2024 | hide | past | pdf | discuss
|
|
| 5040. |
Large Language Models for Scientific Synthesis, Inference and Explanation (arxiv.org) |
|
5 points by rntn on Jun 5, 2024 | hide | past | pdf | discuss
|
|
|
| More |
