| 3151. |
A General Theoretical Paradigm to Understand Learning from Human Preferences (arxiv.org) |
|
2 points by yenniejun111 on May 15, 2025 | hide | past | pdf | discuss
|
|
| 3152. |
DeepSeek-V3: Achieving Efficient LLM Scaling with 2,048 GPUs (arxiv.org) |
|
7 points by qtwhat on May 15, 2025 | hide | past | pdf | 1 comment
|
|
| 3153. |
Online Isolation Forest (arxiv.org) |
|
2 points by badmonster on May 15, 2025 | hide | past | pdf | discuss
|
|
| 3154. |
Understanding Perception and Reasoning Through Model Merging (arxiv.org) |
|
2 points by veryluckyxyz on May 15, 2025 | hide | past | pdf | discuss
|
|
| 3155. |
LLMs get lost in multi-turn conversation (arxiv.org) |
|
374 points by simonpure on May 15, 2025 | hide | past | pdf | 259 comments
|
|
| 3156. |
SEM-CTRL: Semantically Controlled Decoding (arxiv.org) |
|
3 points by tough on May 14, 2025 | hide | past | pdf | discuss
|
|
| 3157. |
Bang for the Buck: Vector Search on Cloud CPUs (arxiv.org) |
|
5 points by ashvardanian on May 14, 2025 | hide | past | pdf | discuss
|
|
| 3158. |
Do Words Reflect Beliefs? Evaluating Belief Depth in Large Language Models (arxiv.org) |
|
1 point by PaulHoule on May 14, 2025 | hide | past | pdf | discuss
|
|
| 3159. |
IterGen: Iterative Semantic-Aware Structured LLM Generation with Backtracking (arxiv.org) |
|
1 point by tough on May 14, 2025 | hide | past | pdf | discuss
|
|
| 3160. |
ROCODE: Integrating Backtracking Mechanism and Program Analysis in LLMs for Code (arxiv.org) |
|
1 point by tough on May 14, 2025 | hide | past | pdf | discuss
|
|
| 3161. |
SRLCG: Self-Rectified Large-Scale Code Generation, CoT, Dynamic Backtracking (arxiv.org) |
|
1 point by tough on May 14, 2025 | hide | past | pdf | discuss
|
|
| 3162. |
CRANE: Reasoning with Constrained LLM Generation (arxiv.org) |
|
1 point by tough on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3163. |
Type-constrained code generation with language models (arxiv.org) |
|
257 points by tough on May 13, 2025 | hide | past | pdf | 127 comments
|
|
| 3164. |
AWRS SMC: Fast new algorithm for guiding LLMs as Bayesian inference (arxiv.org) |
|
2 points by benlipkin on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3165. |
Can Third-Parties Read Our Emotions? (arxiv.org) |
|
2 points by PaulHoule on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3166. |
Intellect-2: A Reasoning Model Trained Through Globally Decentralized RL (arxiv.org) |
|
1 point by nkko on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3167. |
Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions (arxiv.org) |
|
5 points by wjSgoWPm5bWAhXB on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3168. |
In-Context Learning can distort the relationship between likelihoods and fitness (arxiv.org) |
|
1 point by PaulHoule on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3169. |
LithOS: An Operating System for Efficient Machine Learning on GPUs (arxiv.org) |
|
3 points by PaulHoule on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3170. |
Base Models Beat Aligned Models at Randomness and Creativity (arxiv.org) |
|
1 point by todsacerdoti on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3171. |
Backslash: Rate Constrained Optimized Training of Large Language Models (arxiv.org) |
|
3 points by PaulHoule on May 13, 2025 | hide | past | pdf | discuss
|
|
| 3172. |
TransMLA: Multi-head latent attention is all you need (arxiv.org) |
|
123 points by ocean_moist on May 13, 2025 | hide | past | pdf | 32 comments
|
|
| 3173. |
Zero-shot forecasting of chaotic systems (arxiv.org) |
|
2 points by wil3 on May 12, 2025 | hide | past | pdf | discuss
|
|
| 3174. |
LLMs Outperform Experts on Challenging Biology Benchmarks (arxiv.org) |
|
1 point by belter on May 12, 2025 | hide | past | pdf | discuss
|
|
| 3175. |
Byte latent transformer: Patches scale better than tokens (2024) (arxiv.org) |
|
107 points by dlojudice on May 12, 2025 | hide | past | pdf | 22 comments
|
|
| 3176. |
Large Language Models Are Autonomous Cyber Defenders (arxiv.org) |
|
1 point by aibrother on May 11, 2025 | hide | past | pdf | discuss
|
|
| 3177. |
Absolute Zero: Reinforced Self-Play Reasoning with Zero Data (arxiv.org) |
|
88 points by leodriesch on May 11, 2025 | hide | past | pdf | 19 comments
|
|
| 3178. |
Learning Adaptive Parallel Reasoning with Language Models (arxiv.org) |
|
2 points by PaulHoule on May 11, 2025 | hide | past | pdf | discuss
|
|
| 3179. |
Generating Physically Stable and Buildable Lego Designs from Text (arxiv.org) |
|
1 point by aibrother on May 11, 2025 | hide | past | pdf | discuss
|
|
| 3180. |
Reasoning Models Don't Always Say What They Think (arxiv.org) |
|
2 points by badmonster on May 10, 2025 | hide | past | pdf | discuss
|
|
|
| More |
