| 4171. |
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning (arxiv.org) |
|
3 points by diwank on Nov 19, 2024 | hide | past | pdf | discuss
|
|
| 4172. |
Generative Agent Simulations of 1k People (arxiv.org) |
|
4 points by sun-dried on Nov 18, 2024 | hide | past | pdf | 1 comment
|
|
| 4173. |
That Chip Has Sailed: Critique of Unfounded Skepticism Around AI for Chip Design (arxiv.org) |
|
10 points by foweltschmerz on Nov 18, 2024 | hide | past | pdf | 9 comments
|
|
| 4174. |
The Dawn of GUI Agent (arxiv.org) |
|
3 points by omarsar on Nov 18, 2024 | hide | past | pdf | discuss
|
|
| 4175. |
Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis (arxiv.org) |
|
2 points by PaulHoule on Nov 18, 2024 | hide | past | pdf | discuss
|
|
| 4176. |
Test-Time Training on Nearest Neighbors for Large Language Models (arxiv.org) |
|
1 point by trott on Nov 18, 2024 | hide | past | pdf | discuss
|
|
| 4177. |
Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations (arxiv.org) |
|
2 points by xavaki on Nov 18, 2024 | hide | past | pdf | discuss
|
|
| 4178. |
LLaVA-O1: Let Vision Language Models Reason Step-by-Step (arxiv.org) |
|
177 points by lnyan on Nov 18, 2024 | hide | past | pdf | 32 comments
|
|
| 4179. |
What Makes Rotary Positional Encodings Useful? (arxiv.org) |
|
1 point by veryluckyxyz on Nov 18, 2024 | hide | past | pdf | discuss
|
|
| 4180. |
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks (arxiv.org) |
|
54 points by amai on Nov 16, 2024 | hide | past | pdf | 22 comments
|
|
| 4181. |
HtmlRAG: HTML is Better than Plain Text (arxiv.org) |
|
3 points by omarsar on Nov 16, 2024 | hide | past | pdf | discuss
|
|
| 4182. |
Fine-Tuning Multimodal Models with Knowledge-Adapted Captions (arxiv.org) |
|
3 points by sandwichsphinx on Nov 16, 2024 | hide | past | pdf | discuss
|
|
| 4183. |
Convolutional Differentiable Logic Gate Networks (arxiv.org) |
|
26 points by lnyan on Nov 16, 2024 | hide | past | pdf | 4 comments
|
|
| 4184. |
The Geometry of Concepts: Sparse Autoencoder Feature Structure (arxiv.org) |
|
2 points by Anon84 on Nov 16, 2024 | hide | past | pdf | discuss
|
|
| 4185. |
Jailbreaking LLM-Controlled Robots (arxiv.org) |
|
2 points by rntn on Nov 16, 2024 | hide | past | pdf | discuss
|
|
| 4186. |
GazeGen: Gaze-Driven User Interaction for Visual Content Generation (arxiv.org) |
|
1 point by PaulHoule on Nov 16, 2024 | hide | past | pdf | discuss
|
|
| 4187. |
A Comprehensive Study on Quantization Techniques for Large Language Models (arxiv.org) |
|
1 point by PaulHoule on Nov 15, 2024 | hide | past | pdf | discuss
|
|
| 4188. |
WiFlexFormer: Efficient WiFi-Based Person-Centric Sensing (arxiv.org) |
|
2 points by PaulHoule on Nov 15, 2024 | hide | past | pdf | discuss
|
|
| 4189. |
LLMs Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level (arxiv.org) |
|
2 points by radku on Nov 15, 2024 | hide | past | pdf | discuss
|
|
| 4190. |
1-Bit AI Infrastructure (arxiv.org) |
|
157 points by galeos on Nov 15, 2024 | hide | past | pdf | 30 comments
|
|
| 4191. |
Are Large Language Models Consistent over Value-Laden Questions? (arxiv.org) |
|
1 point by rntn on Nov 14, 2024 | hide | past | pdf | discuss
|
|
| 4192. |
Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space (arxiv.org) |
|
2 points by famouswaffles on Nov 14, 2024 | hide | past | pdf | discuss
|
|
| 4193. |
Language agents achieve superhuman synthesis of scientific knowledge (arxiv.org) |
|
54 points by rntn on Nov 14, 2024 | hide | past | pdf | 22 comments
|
|
| 4194. |
Large Language Models Can Self-Improve in Long-Context Reasoning (arxiv.org) |
|
1 point by victormustar on Nov 14, 2024 | hide | past | pdf | discuss
|
|
| 4195. |
GPT or BERT: why not both? (arxiv.org) |
|
2 points by woadwarrior01 on Nov 14, 2024 | hide | past | pdf | discuss
|
|
| 4196. |
How AI is beating VCs in their own game (arxiv.org) |
|
10 points by yihlamur on Nov 14, 2024 | hide | past | pdf | 12 comments
|
|
| 4197. |
BERTs Are Generative In-Context Learners (arxiv.org) |
|
141 points by fzliu on Nov 14, 2024 | hide | past | pdf | 46 comments
|
|
| 4198. |
RedCode: Risky Code Execution and Generation Benchmark for Code Agents (arxiv.org) |
|
2 points by abelanger on Nov 13, 2024 | hide | past | pdf | discuss
|
|
| 4199. |
UniGAD: Unifying Multi-Level Graph Anomaly Detection (arxiv.org) |
|
2 points by sonabinu on Nov 13, 2024 | hide | past | pdf | discuss
|
|
| 4200. |
Efficient Machine Translation with a BiLSTM-Attention Approach (arxiv.org) |
|
1 point by PaulHoule on Nov 13, 2024 | hide | past | pdf | discuss
|
|
|
| More |
