| 2731. |
Strategic Intelligence in LLMs: Evidence from Evolutionary Game Theory (arxiv.org) |
|
2 points by ArmageddonIt on Jul 14, 2025 | hide | past | pdf | discuss
|
|
| 2732. |
One Token to Fool LLM-as-a-Judge (arxiv.org) |
|
2 points by simonpure on Jul 14, 2025 | hide | past | pdf | discuss
|
|
| 2733. |
MemOS is a breakthrough "memory operating system" for AI (arxiv.org) |
|
2 points by amirkabbara on Jul 14, 2025 | hide | past | pdf | discuss
|
|
| 2734. |
Persona Features Control Emergent Misalignment (arxiv.org) |
|
6 points by Bluestein on Jul 14, 2025 | hide | past | pdf | discuss
|
|
| 2735. |
Cats Confuse LLM: Query Agnostic Adversarial Triggers for Reasoning Models (arxiv.org) |
|
1 point by DyslexicAtheist on Jul 14, 2025 | hide | past | pdf | discuss
|
|
| 2736. |
ASK HN: Why Google's Gemini 2.5 paper has 3295 authors? (arxiv.org) |
|
2 points by tzury on Jul 14, 2025 | hide | past | pdf | 4 comments
|
|
| 2737. |
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs (arxiv.org) |
|
181 points by martythemaniak on Jul 13, 2025 | hide | past | pdf | 48 comments
|
|
| 2738. |
Defending Against Prompt Injection with a Few DefensiveTokens (arxiv.org) |
|
2 points by belter on Jul 13, 2025 | hide | past | pdf | discuss
|
|
| 2739. |
LLMs for Drug-Drug Interaction Prediction: A Comprehensive Comparison (arxiv.org) |
|
2 points by stacktrust on Jul 13, 2025 | hide | past | pdf | discuss
|
|
| 2740. |
Large Language Models Are Not Stable Recommender Systems (2023) (arxiv.org) |
|
4 points by wslh on Jul 13, 2025 | hide | past | pdf | discuss
|
|
| 2741. |
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling (arxiv.org) |
|
10 points by fzliu on Jul 13, 2025 | hide | past | pdf | discuss
|
|
| 2742. |
ZipNN: Lossless Compression for AI Models (2024) (arxiv.org) |
|
4 points by sandwichsphinx on Jul 13, 2025 | hide | past | pdf | discuss
|
|
| 2743. |
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling (arxiv.org) |
|
4 points by simonpure on Jul 12, 2025 | hide | past | pdf | discuss
|
|
| 2744. |
Humans overrely on overconfident language models, across languages (arxiv.org) |
|
7 points by softwaredoug on Jul 11, 2025 | hide | past | pdf | discuss
|
|
| 2745. |
Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs (arxiv.org) |
|
1 point by layer8 on Jul 11, 2025 | hide | past | pdf | discuss
|
|
| 2746. |
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling (arxiv.org) |
|
5 points by Anon84 on Jul 11, 2025 | hide | past | pdf | discuss
|
|
| 2747. |
Impact of Pretraining Word Co-Occurrence on Compositional Generalization In (arxiv.org) |
|
2 points by badmonster on Jul 11, 2025 | hide | past | pdf | 1 comment
|
|
| 2748. |
Human-Like Forgetting Curves in Deep Neural Networks (arxiv.org) |
|
2 points by PaulHoule on Jul 11, 2025 | hide | past | pdf | discuss
|
|
| 2749. |
Strategic Intelligence in Large Language Models (arxiv.org) |
|
1 point by RansomStark on Jul 11, 2025 | hide | past | pdf | discuss
|
|
| 2750. |
Adaptive Two Sided Laplace Transforms as a Replacement for Self-Attention (arxiv.org) |
|
2 points by PaulHoule on Jul 11, 2025 | hide | past | pdf | 1 comment
|
|
| 2751. |
Foundation Models of Behavioral Data from Wearables Improve Health Predictions (arxiv.org) |
|
1 point by tosh on Jul 11, 2025 | hide | past | pdf | discuss
|
|
| 2752. |
Extreme Low-Bit Clustering for Large Language Models via Knowledge Distillation (arxiv.org) |
|
2 points by PaulHoule on Jul 11, 2025 | hide | past | pdf | discuss
|
|
| 2753. |
Violent Tendencies in LLMs: Analysis via Behavioral Vignettes (arxiv.org) |
|
3 points by PaulHoule on Jul 10, 2025 | hide | past | pdf | discuss
|
|
| 2754. |
HRM: 27M parameters, 1000 training samples, no pre-training required (arxiv.org) |
|
2 points by mountainview on Jul 10, 2025 | hide | past | pdf | discuss
|
|
| 2755. |
Stochastic Interpolants (arxiv.org) |
|
2 points by gone35 on Jul 10, 2025 | hide | past | pdf | discuss
|
|
| 2756. |
Amazon gets serious with AI Safety (arxiv.org) |
|
3 points by prizeon on Jul 10, 2025 | hide | past | pdf | discuss
|
|
| 2757. |
An analytic theory of creativity in convolutional diffusion models (arxiv.org) |
|
7 points by foltik on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2758. |
Generative Blocks World: Moving Things Around in Pictures (arxiv.org) |
|
3 points by PaulHoule on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2759. |
Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program (arxiv.org) |
|
6 points by Bluestein on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2760. |
Hi-SQL: Optimizing Text-to-SQL Systems Through Dynamic Hint Integration (arxiv.org) |
|
1 point by PaulHoule on Jul 9, 2025 | hide | past | pdf | discuss
|
|
|
| More |
