| 5101. |
SWE-Agent: Agent-Computer Interfaces Enable Automated Software Engineering (arxiv.org) |
|
1 point by broyojo on May 28, 2024 | hide | past | pdf | discuss
|
|
| 5102. |
Transformers Can Do Arithmetic with the Right Embeddings (arxiv.org) |
|
207 points by byt3h3ad on May 28, 2024 | hide | past | pdf | 211 comments
|
|
| 5103. |
Grokked Transformers Are Implicit Reasoners (arxiv.org) |
|
239 points by jasondavies on May 27, 2024 | hide | past | pdf | 61 comments
|
|
| 5104. |
Extracting Prompts by Inverting LLM Outputs (arxiv.org) |
|
2 points by xcccube on May 27, 2024 | hide | past | pdf | 1 comment
|
|
| 5105. |
AstroPT: Scaling Large Observation Models for Astronomy (arxiv.org) |
|
2 points by Smith42 on May 27, 2024 | hide | past | pdf | 1 comment
|
|
| 5106. |
Neuromorphic dreaming: A pathway to efficient learning in artificial agents (arxiv.org) |
|
2 points by belter on May 27, 2024 | hide | past | pdf | discuss
|
|
| 5107. |
Kolmogorov-Arnold Networks (KANs) for Time Series Analysis (arxiv.org) |
|
3 points by jasondavies on May 27, 2024 | hide | past | pdf | discuss
|
|
| 5108. |
Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4 (arxiv.org) |
|
2 points by belter on May 27, 2024 | hide | past | pdf | discuss
|
|
| 5109. |
Models That Prove Their Own Correctness (arxiv.org) |
|
4 points by laybak on May 27, 2024 | hide | past | pdf | discuss
|
|
| 5110. |
Look Once to Hear: Target Speech Hearing with Noisy Examples (arxiv.org) |
|
1 point by jasondavies on May 26, 2024 | hide | past | pdf | discuss
|
|
| 5111. |
How Far Are We from AGI (arxiv.org) |
|
5 points by RafelMri on May 26, 2024 | hide | past | pdf | 4 comments
|
|
| 5112. |
Exploring Autonomous Agents Through the Lens of Large Language Models (arxiv.org) |
|
2 points by sabrina_ramonov on May 26, 2024 | hide | past | pdf | discuss
|
|
| 5113. |
Feather: Data Reordering for On-Chip Dataflow Switching (arxiv.org) |
|
1 point by breck on May 26, 2024 | hide | past | pdf | discuss
|
|
| 5114. |
Attention as an RNN (arxiv.org) |
|
2 points by RafelMri on May 26, 2024 | hide | past | pdf | discuss
|
|
| 5115. |
Some models are useful, but for how long?: When to refit prediction models (arxiv.org) |
|
1 point by nequo on May 26, 2024 | hide | past | pdf | discuss
|
|
| 5116. |
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning (arxiv.org) |
|
3 points by jasondavies on May 25, 2024 | hide | past | pdf | discuss
|
|
| 5117. |
A Prefrontal Cortex-Inspired Architecture for Planning in Large Language Models (arxiv.org) |
|
2 points by rntn on May 25, 2024 | hide | past | pdf | 1 comment
|
|
| 5118. |
Evaluation of the Programming Skills of Large Language Models (arxiv.org) |
|
3 points by belter on May 25, 2024 | hide | past | pdf | discuss
|
|
| 5119. |
Not All Language Model Features Are Linear (arxiv.org) |
|
1 point by belter on May 25, 2024 | hide | past | pdf | discuss
|
|
| 5120. |
A Case Study in CUDA Kernel Fusion (arxiv.org) |
|
1 point by veryluckyxyz on May 25, 2024 | hide | past | pdf | discuss
|
|
| 5121. |
Lessons from the trenches on reproducible evaluation of language models (arxiv.org) |
|
42 points by veryluckyxyz on May 25, 2024 | hide | past | pdf | 3 comments
|
|
| 5122. |
A ConvNet for the 2020s (arxiv.org) |
|
18 points by laybak on May 25, 2024 | hide | past | pdf | discuss
|
|
| 5123. |
Bird's-Eye View to Street-View: A Survey (arxiv.org) |
|
1 point by PaulHoule on May 24, 2024 | hide | past | pdf | discuss
|
|
| 5124. |
"Yes I Would Recommend Calling the Police":Norm Inconsistency in LLM Decisions (arxiv.org) |
|
1 point by belter on May 24, 2024 | hide | past | pdf | discuss
|
|
| 5125. |
Lessons from the Trenches on Reproducible Evaluation of Language Models (arxiv.org) |
|
1 point by tosh on May 24, 2024 | hide | past | pdf | discuss
|
|
| 5126. |
YOLOv10: Real-Time End-to-End Object Detection (arxiv.org) |
|
2 points by zerojames on May 24, 2024 | hide | past | pdf | discuss
|
|
| 5127. |
Thermodynamic Natural Gradient Descent (arxiv.org) |
|
200 points by jasondavies on May 24, 2024 | hide | past | pdf | 32 comments
|
|
| 5128. |
A Declarative System for Optimizing AI Workloads (arxiv.org) |
|
2 points by zerojames on May 24, 2024 | hide | past | pdf | discuss
|
|
| 5129. |
Representation noising effectively prevents harmful fine-tuning on LLMs (arxiv.org) |
|
1 point by darosati on May 24, 2024 | hide | past | pdf | discuss
|
|
| 5130. |
You Only Cache Once: Decoder-Decoder Architectures for Language Models (arxiv.org) |
|
3 points by belter on May 24, 2024 | hide | past | pdf | discuss
|
|
|
| More |
