| 3121. |
Questioning Representational Optimism in Deep Learning (arxiv.org) |
|
1 point by artninja1988 on May 20, 2025 | hide | past | pdf | discuss
|
|
| 3122. |
Improving Assembly Code Performance with LLMss via Reinforcement Learning (arxiv.org) |
|
13 points by badmonster on May 20, 2025 | hide | past | pdf | 2 comments
|
|
| 3123. |
Real AI Agents, Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents (arxiv.org) |
|
2 points by gnabgib on May 19, 2025 | hide | past | pdf | discuss
|
|
| 3124. |
Optimization of RAG systems using quantization and dimensionality reduction (arxiv.org) |
|
3 points by PaulHoule on May 19, 2025 | hide | past | pdf | discuss
|
|
| 3125. |
The Evaluation of Engineering Artificial General Intelligence (arxiv.org) |
|
2 points by sirregex1 on May 19, 2025 | hide | past | pdf | discuss
|
|
| 3126. |
Cosmos: Predictable and Cost-Effective Adaptation of LLMs (arxiv.org) |
|
1 point by PaulHoule on May 19, 2025 | hide | past | pdf | discuss
|
|
| 3127. |
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenge (arxiv.org) |
|
2 points by simonpure on May 19, 2025 | hide | past | pdf | discuss
|
|
| 3128. |
Reasoning Models Don't Always Say What They Think (arxiv.org) |
|
1 point by jonbaer on May 19, 2025 | hide | past | pdf | discuss
|
|
| 3129. |
Can You Trust Code Copilots? Evaluating LLMs from a Code Security Perspec (arxiv.org) |
|
11 points by badmonster on May 18, 2025 | hide | past | pdf | 2 comments
|
|
| 3130. |
Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic (arxiv.org) |
|
1 point by badmonster on May 18, 2025 | hide | past | pdf | discuss
|
|
| 3131. |
Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models (arxiv.org) |
|
1 point by PaulHoule on May 18, 2025 | hide | past | pdf | discuss
|
|
| 3132. |
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (arxiv.org) |
|
3 points by tough on May 18, 2025 | hide | past | pdf | discuss
|
|
| 3133. |
LLMs are more persuasive than incentivized human persuaders (arxiv.org) |
|
140 points by flornt on May 17, 2025 | hide | past | pdf | 116 comments
|
|
| 3134. |
Understanding Transformers via N-gram Statistics (arxiv.org) |
|
139 points by pona-a on May 17, 2025 | hide | past | pdf | 16 comments
|
|
| 3135. |
Steepest Descent Density Control for Compact 3D Gaussian Splatting (arxiv.org) |
|
30 points by PaulHoule on May 17, 2025 | hide | past | pdf | discuss
|
|
| 3136. |
Analyzing, Predicting, and Controlling How a Reasoning Model Will Think (arxiv.org) |
|
3 points by simonpure on May 17, 2025 | hide | past | pdf | discuss
|
|
| 3137. |
Open Problems in Mechanistic Interpretability (arxiv.org) |
|
1 point by nill0 on May 17, 2025 | hide | past | pdf | discuss
|
|
| 3138. |
DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures (arxiv.org) |
|
4 points by nsoonhui on May 17, 2025 | hide | past | pdf | discuss
|
|
| 3139. |
Large Language Models Are More Persuasive Than Incentivized Human Persuaders (arxiv.org) |
|
4 points by randomdrake on May 16, 2025 | hide | past | pdf | 1 comment
|
|
| 3140. |
AccLLM: Accelerating Long-Context LLM Inference via Algorithm-Hardware Co-Design (arxiv.org) |
|
2 points by PaulHoule on May 16, 2025 | hide | past | pdf | discuss
|
|
| 3141. |
End-to-End Vision Tokenizer Tuning (arxiv.org) |
|
3 points by t55 on May 16, 2025 | hide | past | pdf | discuss
|
|
| 3142. |
Parallel Scaling Law for Language Models (arxiv.org) |
|
2 points by anerli on May 16, 2025 | hide | past | pdf | 1 comment
|
|
| 3143. |
Visual Image Reconstruction from Brain Activity via Latent Representation (arxiv.org) |
|
2 points by DanielleMolloy on May 16, 2025 | hide | past | pdf | discuss
|
|
| 3144. |
Twist: Teleoperated Whole-Body Imitation System (arxiv.org) |
|
2 points by the-mitr on May 16, 2025 | hide | past | pdf | discuss
|
|
| 3145. |
Superposition of Features Creates Power Law Performance in LLMs (arxiv.org) |
|
3 points by nkko on May 16, 2025 | hide | past | pdf | discuss
|
|
| 3146. |
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think (arxiv.org) |
|
1 point by badmonster on May 15, 2025 | hide | past | pdf | discuss
|
|
| 3147. |
Why do LLMs attend to the first token? (arxiv.org) |
|
2 points by adhi01 on May 15, 2025 | hide | past | pdf | 1 comment
|
|
| 3148. |
Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI (arxiv.org) |
|
1 point by matt_d on May 15, 2025 | hide | past | pdf | discuss
|
|
| 3149. |
Self Rewarding Self Improving: Autonomous LLM Improvement (arxiv.org) |
|
28 points by tamassimond on May 15, 2025 | hide | past | pdf | discuss
|
|
| 3150. |
A General Theoretical Paradigm to Understand Learning from Human Preferences (arxiv.org) |
|
2 points by yenniejun111 on May 15, 2025 | hide | past | pdf | discuss
|
|
|
| More |
