| 5341. |
Phi-3 Technical Report (arxiv.org) |
|
411 points by varunvummadi on Apr 23, 2024 | hide | past | pdf | 130 comments
|
|
| 5342. |
FPGA Architecture for Deep Learning: Survey and Future Directions (arxiv.org) |
|
128 points by matt_d on Apr 22, 2024 | hide | past | pdf | 52 comments
|
|
| 5343. |
Analyzing the Performance of Large Language Models on Code Summarization (arxiv.org) |
|
1 point by PaulHoule on Apr 22, 2024 | hide | past | pdf | discuss
|
|
| 5344. |
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing (arxiv.org) |
|
2 points by hnhn34 on Apr 22, 2024 | hide | past | pdf | discuss
|
|
| 5345. |
LLM Agents Can Autonomously Exploit One-Day Vulnerabilities (arxiv.org) |
|
1 point by _____k on Apr 22, 2024 | hide | past | pdf | 1 comment
|
|
| 5346. |
Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs (arxiv.org) |
|
2 points by fatso784 on Apr 22, 2024 | hide | past | pdf | discuss
|
|
| 5347. |
Survey Study on AI Agent Architectures (2024) (arxiv.org) |
|
77 points by jslampe on Apr 22, 2024 | hide | past | pdf | 16 comments
|
|
| 5348. |
YaART: Yet Another Art Rendering Technology (arxiv.org) |
|
2 points by avi_chawla on Apr 22, 2024 | hide | past | pdf | discuss
|
|
| 5349. |
Lossless Acceleration of Long Sequence Generation (arxiv.org) |
|
1 point by eshoyuan on Apr 22, 2024 | hide | past | pdf | discuss
|
|
| 5350. |
Many-Shot In-Context Learning (arxiv.org) |
|
62 points by Anon84 on Apr 22, 2024 | hide | past | pdf | 1 comment
|
|
| 5351. |
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models (arxiv.org) |
|
47 points by CharlesW on Apr 22, 2024 | hide | past | pdf | 3 comments
|
|
| 5352. |
The Illusion of State in State-Space Models (arxiv.org) |
|
2 points by georgehill on Apr 21, 2024 | hide | past | pdf | discuss
|
|
| 5353. |
Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding (arxiv.org) |
|
136 points by PaulHoule on Apr 21, 2024 | hide | past | pdf | 23 comments
|
|
| 5354. |
A Comprehensive Overview of Large Language Models (arxiv.org) |
|
2 points by rbanffy on Apr 21, 2024 | hide | past | pdf | discuss
|
|
| 5355. |
From r to Q∗: Your Language Model is a Q-Function (arxiv.org) |
|
2 points by throwaway71271 on Apr 21, 2024 | hide | past | pdf | discuss
|
|
| 5356. |
Deep Neural Networks via Complex Network Theory: A Perspective (arxiv.org) |
|
1 point by Anon84 on Apr 21, 2024 | hide | past | pdf | discuss
|
|
| 5357. |
Modeling Boundedly Rational Agents with Latent Inference Budgets (arxiv.org) |
|
2 points by danboarder on Apr 21, 2024 | hide | past | pdf | discuss
|
|
| 5358. |
Measuring Multitask Language Understanding (arxiv.org) |
|
1 point by tosh on Apr 20, 2024 | hide | past | pdf | discuss
|
|
| 5359. |
How to avoid machine learning pitfalls (arxiv.org) |
|
7 points by golergka on Apr 20, 2024 | hide | past | pdf | discuss
|
|
| 5360. |
AgentKit: Flow Engineering with Graphs, Not Coding (arxiv.org) |
|
1 point by kjhughes on Apr 20, 2024 | hide | past | pdf | discuss
|
|
| 5361. |
Training-Free Long-Context Scaling of Large Language Models (arxiv.org) |
|
1 point by tosh on Apr 20, 2024 | hide | past | pdf | discuss
|
|
| 5362. |
Trillion-Parameter Sequential Transducers for Generative Recommendations (arxiv.org) |
|
2 points by jonbaer on Apr 20, 2024 | hide | past | pdf | discuss
|
|
| 5363. |
MABC: MultiAgent Blockchain Collab for RC analysis in microservices architecture (arxiv.org) |
|
2 points by panqueca on Apr 19, 2024 | hide | past | pdf | discuss
|
|
| 5364. |
JetMoE: Reaching Llama2 Performance with 0.1M Dollars (arxiv.org) |
|
1 point by PaulHoule on Apr 19, 2024 | hide | past | pdf | discuss
|
|
| 5365. |
Optimizing the Deployment of Tiny Transformers on Low-Power MCUs (arxiv.org) |
|
1 point by PaulHoule on Apr 19, 2024 | hide | past | pdf | discuss
|
|
| 5366. |
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing (arxiv.org) |
|
3 points by milliondreams on Apr 19, 2024 | hide | past | pdf | discuss
|
|
| 5367. |
InstantMesh: Efficient 3D Mesh Generation from a Single Image (arxiv.org) |
|
2 points by rrampage on Apr 19, 2024 | hide | past | pdf | discuss
|
|
| 5368. |
LLM Agents Can Autonomously Exploit One-Day Vulnerabilities with 87% Success (arxiv.org) |
|
2 points by namanyayg on Apr 19, 2024 | hide | past | pdf | discuss
|
|
| 5369. |
Demystifying RCE Vulnerabilities in LLM-Integrated Apps (arxiv.org) |
|
1 point by dytir on Apr 19, 2024 | hide | past | pdf | discuss
|
|
| 5370. |
Forecasting the Future: Advancements in Large Meteorological Models (arxiv.org) |
|
2 points by PaulHoule on Apr 18, 2024 | hide | past | pdf | discuss
|
|
|
| More |
