| 3091. |
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models (arxiv.org) |
|
3 points by jonbaer on May 22, 2025 | hide | past | pdf | 1 comment
|
|
| 3092. |
Your Fine-Tuning Data Could Be Stolen (arxiv.org) |
|
2 points by 50kIters on May 22, 2025 | hide | past | pdf | discuss
|
|
| 3093. |
SUS backprop: linear backpropagation algorithm for long inputs in transformers (arxiv.org) |
|
9 points by brandonb on May 22, 2025 | hide | past | pdf | discuss
|
|
| 3094. |
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization (arxiv.org) |
|
2 points by badmonster on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3095. |
Reinforcement Learning for Symbolic Mathematics (arxiv.org) |
|
7 points by MarcoDewey on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3096. |
µPC: Scaling Predictive Coding to 100 Layer Networks (arxiv.org) |
|
32 points by frozenseven on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3097. |
Insights into DeepSeek-V3: Scaling Challenges on Hardware for AI Architectures (arxiv.org) |
|
2 points by tanelpoder on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3098. |
Harnessing the Universal Geometry of Embeddings (arxiv.org) |
|
123 points by jxmorris12 on May 21, 2025 | hide | past | pdf | 40 comments
|
|
| 3099. |
Emerging Properties in Unified Multimodal Pretraining (arxiv.org) |
|
1 point by buildbot on May 21, 2025 | hide | past | pdf | 1 comment
|
|
| 3100. |
Measuring General Intelligence with Generated Games (arxiv.org) |
|
1 point by jonbaer on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3101. |
The Unreasonable Effectiveness of Reasonless Intermediate Tokens (arxiv.org) |
|
4 points by YeGoblynQueenne on May 21, 2025 | hide | past | pdf | 1 comment
|
|
| 3102. |
Training-Free Acceleration for Diffusion Transformers (arxiv.org) |
|
3 points by badmonster on May 21, 2025 | hide | past | pdf | 1 comment
|
|
| 3103. |
Alfred: Ask a Large-Language Model for Reliable ECG Diagnosis (arxiv.org) |
|
3 points by PaulHoule on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3104. |
A Method for the Architecture of a Medical Vertical LLM Based on Deepseek R1 (arxiv.org) |
|
1 point by PaulHoule on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3105. |
Scalable Quantification of User Attention in Multi-Slot Sponsored Search (arxiv.org) |
|
1 point by PaulHoule on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3106. |
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models (arxiv.org) |
|
3 points by s-macke on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3107. |
Show HN: Phare: A Safety Probe for Large Language Models (arxiv.org) |
|
4 points by dberenstein1957 on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3108. |
Pperformance of a large language model on the reasoning tasks of a physician (arxiv.org) |
|
1 point by ibobev on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3109. |
Dark LLMs: The Growing Threat of Unaligned AI Models (arxiv.org) |
|
1 point by uxhacker on May 21, 2025 | hide | past | pdf | 1 comment
|
|
| 3110. |
Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking (arxiv.org) |
|
45 points by favoboa on May 21, 2025 | hide | past | pdf | 46 comments
|
|
| 3111. |
Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents (arxiv.org) |
|
2 points by Fake4d on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3112. |
Griffin: Towards a Graph-Centric Relational Database Foundation Model (arxiv.org) |
|
3 points by PaulHoule on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3113. |
The Dangers of Browsing AI Agents (arxiv.org) |
|
2 points by walterbell on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3114. |
Model Merging in Pre-Training of Large Language Models (arxiv.org) |
|
2 points by veryluckyxyz on May 21, 2025 | hide | past | pdf | discuss
|
|
| 3115. |
Frontier Models are Capable of In-context Scheming (arxiv.org) |
|
3 points by sonabinu on May 20, 2025 | hide | past | pdf | discuss
|
|
| 3116. |
Text Embeddings are All Alike (arxiv.org) |
|
5 points by jxmorris12 on May 20, 2025 | hide | past | pdf | discuss
|
|
| 3117. |
Evaluation of Engineering Artificial General Intelligence (arxiv.org) |
|
2 points by nkko on May 20, 2025 | hide | past | pdf | discuss
|
|
| 3118. |
Ultra-Low-Power Spiking Neurons in 7 Nm FinFET Technology (arxiv.org) |
|
1 point by PaulHoule on May 20, 2025 | hide | past | pdf | discuss
|
|
| 3119. |
Robin: A multi-agent system for automating scientific discovery (arxiv.org) |
|
151 points by nopinsight on May 20, 2025 | hide | past | pdf | 20 comments
|
|
| 3120. |
Grounded in Context: Retrieval-Based Method for Hallucination Detection (arxiv.org) |
|
1 point by AsDivyansh on May 20, 2025 | hide | past | pdf | discuss
|
|
|
| More |
