| 3991. |
Tokenisation Is NP-Complete (arxiv.org) |
|
117 points by belter on Dec 22, 2024 | hide | past | pdf | 24 comments
|
|
| 3992. |
Specification-Driven Code Translation Powered by LLMs: How Far Are We? (arxiv.org) |
|
4 points by PaulHoule on Dec 22, 2024 | hide | past | pdf | discuss
|
|
| 3993. |
Syzygy: Dual Code-Test C to Rust Translation Using LLMs and Dynamic Analysis (arxiv.org) |
|
4 points by slimshetty on Dec 22, 2024 | hide | past | pdf | discuss
|
|
| 3994. |
Chatting with Logs: An Exploratory Study on Finetuning LLMs for LogQL (arxiv.org) |
|
1 point by PaulHoule on Dec 21, 2024 | hide | past | pdf | discuss
|
|
| 3995. |
Relational inductive biases, deep learning, and graph networks (arxiv.org) |
|
2 points by sonabinu on Dec 21, 2024 | hide | past | pdf | discuss
|
|
| 3996. |
On the Measure of Intelligence (arxiv.org) |
|
2 points by liuliu on Dec 21, 2024 | hide | past | pdf | discuss
|
|
| 3997. |
Posterior Mean Matching: Generative Modeling Through Online Bayesian Inference (arxiv.org) |
|
3 points by gradientgoose on Dec 20, 2024 | hide | past | pdf | discuss
|
|
| 3998. |
Apollo: SGD-like Memory, AdamW-level Performance (arxiv.org) |
|
2 points by PaulHoule on Dec 20, 2024 | hide | past | pdf | discuss
|
|
| 3999. |
SpikeFI: A Fault Injection Framework for Spiking Neural Networks (arxiv.org) |
|
1 point by PaulHoule on Dec 20, 2024 | hide | past | pdf | discuss
|
|
| 4000. |
Video Representation Learning with Joint-Embedding Predictive Architectures (arxiv.org) |
|
2 points by fofoz on Dec 20, 2024 | hide | past | pdf | discuss
|
|
| 4001. |
Monolith: Real Time Recommendation System with Collisionless Embedding Table (arxiv.org) |
|
2 points by mpweiher on Dec 20, 2024 | hide | past | pdf | discuss
|
|
| 4002. |
Glider: Small model beats GPT on eval tasks (arxiv.org) |
|
2 points by rebeccatqian on Dec 19, 2024 | hide | past | pdf | discuss
|
|
| 4003. |
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale (arxiv.org) |
|
3 points by Anon84 on Dec 19, 2024 | hide | past | pdf | discuss
|
|
| 4004. |
ModernBERT (arxiv.org) |
|
3 points by fzliu on Dec 19, 2024 | hide | past | pdf | 1 comment
|
|
| 4005. |
Lightweight Safety Classification Using Pruned Language Models (arxiv.org) |
|
19 points by sandijean90 on Dec 19, 2024 | hide | past | pdf | 3 comments
|
|
| 4006. |
Study: Better Large Language Models Process Text More Like Human Brains Do (arxiv.org) |
|
2 points by nopinsight on Dec 19, 2024 | hide | past | pdf | discuss
|
|
| 4007. |
Design choices made by LLM-based test generators prevent them from finding bugs (arxiv.org) |
|
1 point by ingve on Dec 19, 2024 | hide | past | pdf | discuss
|
|
| 4008. |
Pattern Matching in AI Compilers and Its Formalization (Extended Version) (arxiv.org) |
|
2 points by matt_d on Dec 19, 2024 | hide | past | pdf | discuss
|
|
| 4009. |
Rethinking the Combination of Graph Neural Network and Large Language Model (arxiv.org) |
|
2 points by PaulHoule on Dec 18, 2024 | hide | past | pdf | discuss
|
|
| 4010. |
Selfish Evolution: Making Discoveries in Extreme Label Noise (arxiv.org) |
|
2 points by PaulHoule on Dec 18, 2024 | hide | past | pdf | discuss
|
|
| 4011. |
Cultural Evolution of Cooperation Among LLM Agents (arxiv.org) |
|
246 points by Anon84 on Dec 18, 2024 | hide | past | pdf | 131 comments
|
|
| 4012. |
Meshtron: High-fidelity 3D mesh generation from point clouds (arxiv.org) |
|
3 points by werediver on Dec 18, 2024 | hide | past | pdf | 1 comment
|
|
| 4013. |
No More Adam: Learning Rate Scaling at Initialization Is All You Need (arxiv.org) |
|
91 points by jinqueeny on Dec 18, 2024 | hide | past | pdf | 28 comments
|
|
| 4014. |
Rethinking Emotion Annotations in the Era of Large Language Models (arxiv.org) |
|
1 point by PaulHoule on Dec 18, 2024 | hide | past | pdf | discuss
|
|
| 4015. |
GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting (arxiv.org) |
|
1 point by PaulHoule on Dec 17, 2024 | hide | past | pdf | discuss
|
|
| 4016. |
Superhuman performance of an LLM on the reasoning tasks of a physician (arxiv.org) |
|
4 points by wumeow on Dec 17, 2024 | hide | past | pdf | discuss
|
|
| 4017. |
NewsEdits 2.0: Learning the Intentions Behind Updating News (arxiv.org) |
|
1 point by PaulHoule on Dec 17, 2024 | hide | past | pdf | discuss
|
|
| 4018. |
Undecidability of Underfitting in Learning Algorithms (arxiv.org) |
|
2 points by pizza on Dec 17, 2024 | hide | past | pdf | discuss
|
|
| 4019. |
Meta's new Video Understanding Multimodal Model used Qwen model for training (arxiv.org) |
|
7 points by BUFU on Dec 16, 2024 | hide | past | pdf | 1 comment
|
|
| 4020. |
DeepSeek-VL2 (arxiv.org) |
|
1 point by omarsar on Dec 16, 2024 | hide | past | pdf | discuss
|
|
|
| More |
