| 4111. |
Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversation (arxiv.org) |
|
2 points by sandwichsphinx on Nov 29, 2024 | hide | past | pdf | discuss
|
|
| 4112. |
Physics-Informed Machine Learning: A Survey (arxiv.org) |
|
3 points by nickpsecurity on Nov 29, 2024 | hide | past | pdf | 1 comment
|
|
| 4113. |
Navigating Extremes: Dynamic Sparsity in Large Output Space (arxiv.org) |
|
1 point by PaulHoule on Nov 29, 2024 | hide | past | pdf | discuss
|
|
| 4114. |
AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Dataset (arxiv.org) |
|
2 points by PaulHoule on Nov 29, 2024 | hide | past | pdf | discuss
|
|
| 4115. |
Physics in Next-Token Prediction (arxiv.org) |
|
28 points by Anon84 on Nov 29, 2024 | hide | past | pdf | 4 comments
|
|
| 4116. |
Arithmetic Without Algorithms: LLMs Solve Math with a Bag of Heuristics (arxiv.org) |
|
1 point by jsenn on Nov 28, 2024 | hide | past | pdf | 1 comment
|
|
| 4117. |
Laser: Attention with Exponential Transformation (arxiv.org) |
|
13 points by PaulHoule on Nov 28, 2024 | hide | past | pdf | discuss
|
|
| 4118. |
A Survey of LLM-Brained GUI Agents (arxiv.org) |
|
2 points by omarsar on Nov 28, 2024 | hide | past | pdf | discuss
|
|
| 4119. |
Cautious Optimizers: Improving Training with One Line of Code (arxiv.org) |
|
1 point by kz919 on Nov 28, 2024 | hide | past | pdf | 1 comment
|
|
| 4120. |
Automated Design of Agentic Systems (arxiv.org) |
|
2 points by handfuloflight on Nov 28, 2024 | hide | past | pdf | discuss
|
|
| 4121. |
Deep Learning Scaling Is Predictable, Empirically (arxiv.org) |
|
1 point by Anon84 on Nov 27, 2024 | hide | past | pdf | discuss
|
|
| 4122. |
Towards Optimizing SQL Generation via LLM Routing (arxiv.org) |
|
11 points by PaulHoule on Nov 27, 2024 | hide | past | pdf | 1 comment
|
|
| 4123. |
Pruning a single weight in an LLM can destroy its output (arxiv.org) |
|
1 point by cjrd on Nov 27, 2024 | hide | past | pdf | discuss
|
|
| 4124. |
ShowUI: One Vision-Language-Action Model for GUI Visual Agent (arxiv.org) |
|
2 points by BUFU on Nov 27, 2024 | hide | past | pdf | discuss
|
|
| 4125. |
A Survey on Employing Large Language Models for Text-to-SQL Tasks (arxiv.org) |
|
2 points by PaulHoule on Nov 27, 2024 | hide | past | pdf | discuss
|
|
| 4126. |
Inference Scaling FLaws: The Limits of LLM Resampling with Imperfect Verifiers (arxiv.org) |
|
3 points by randomwalker on Nov 27, 2024 | hide | past | pdf | discuss
|
|
| 4127. |
Gradient Boosting Trees and LLMs for Tabular Data Few-Shot Learning (arxiv.org) |
|
2 points by PaulHoule on Nov 27, 2024 | hide | past | pdf | discuss
|
|
| 4128. |
Teuken-7B-Base and Teuken-7B-Instruct: Towards European LLMs (arxiv.org) |
|
7 points by Tepix on Nov 27, 2024 | hide | past | pdf | discuss
|
|
| 4129. |
RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications (arxiv.org) |
|
1 point by luu on Nov 26, 2024 | hide | past | pdf | discuss
|
|
| 4130. |
Simple synthetic data reduces sycophancy in large language models (arxiv.org) |
|
2 points by pr337h4m on Nov 26, 2024 | hide | past | pdf | discuss
|
|
| 4131. |
A No Free Lunch Theorem for Human-AI Collaboration [pdf] (arxiv.org) |
|
1 point by bikenaga on Nov 26, 2024 | hide | past | pdf | discuss
|
|
| 4132. |
A Survey on LLM-as-a-Judge (arxiv.org) |
|
3 points by omarsar on Nov 26, 2024 | hide | past | pdf | discuss
|
|
| 4133. |
Scaling Laws for Precision (arxiv.org) |
|
2 points by sva_ on Nov 26, 2024 | hide | past | pdf | discuss
|
|
| 4134. |
Accelerated AI Inference via Dynamic Execution Methods (arxiv.org) |
|
67 points by PaulHoule on Nov 25, 2024 | hide | past | pdf | 3 comments
|
|
| 4135. |
Crystal: Illuminating LLM Abilities on Language and Code (arxiv.org) |
|
1 point by PaulHoule on Nov 25, 2024 | hide | past | pdf | discuss
|
|
| 4136. |
Automating Code Reviews Using Large Language Models (arxiv.org) |
|
3 points by aravindputrevu on Nov 25, 2024 | hide | past | pdf | 1 comment
|
|
| 4137. |
DynaSaur: Large Language Agents Beyond Predefined Actions (arxiv.org) |
|
1 point by simonpure on Nov 24, 2024 | hide | past | pdf | discuss
|
|
| 4138. |
Generative Agent Simulations of 1k People [pdf] (arxiv.org) |
|
2 points by elsewhen on Nov 24, 2024 | hide | past | pdf | 1 comment
|
|
| 4139. |
Ask, and it shall be given: Turing completeness of prompting (arxiv.org) |
|
1 point by simonpure on Nov 24, 2024 | hide | past | pdf | discuss
|
|
| 4140. |
Four Steps Towards Robust Artificial Intelligence (2020) (arxiv.org) |
|
2 points by subvertify on Nov 24, 2024 | hide | past | pdf | 1 comment
|
|
|
| More |
