| 2311. |
ML Fairness Breaks Under Distribution Shift–Here's the Fix (arxiv.org) |
|
1 point by WASDAai on Oct 1, 2025 | hide | past | pdf | 1 comment
|
|
| 2312. |
Evaluating LLM-Generated Detection Rules in Cybersecurity (arxiv.org) |
|
4 points by bf222 on Oct 1, 2025 | hide | past | pdf | discuss
|
|
| 2313. |
Dragon Hatchling: Missing Link Between the Transformer and Models of the Brain (arxiv.org) |
|
1 point by zby on Oct 1, 2025 | hide | past | pdf | discuss
|
|
| 2314. |
High-resolution efficient image generation from WiFi Mapping (arxiv.org) |
|
143 points by oldfuture on Oct 1, 2025 | hide | past | pdf | 35 comments
|
|
| 2315. |
Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check (arxiv.org) |
|
1 point by momeara on Oct 1, 2025 | hide | past | pdf | discuss
|
|
| 2316. |
Dreamer 4 (arxiv.org) |
|
3 points by theOGognf on Sep 30, 2025 | hide | past | pdf | 1 comment
|
|
| 2317. |
Introduction to Multi-Armed Bandits (2019) (arxiv.org) |
|
143 points by Anon84 on Sep 30, 2025 | hide | past | pdf | 33 comments
|
|
| 2318. |
No Prior, No Leakage: Reconstruction Attacks in Trained Neural Networks (arxiv.org) |
|
1 point by elashri on Sep 30, 2025 | hide | past | pdf | discuss
|
|
| 2319. |
Extract-0: A specialized language model for document information extraction (arxiv.org) |
|
195 points by henriquegodoy on Sep 30, 2025 | hide | past | pdf | 58 comments
|
|
| 2320. |
Sample-Efficient Integration of New Modalities into Large Language Models (arxiv.org) |
|
1 point by PaulHoule on Sep 30, 2025 | hide | past | pdf | discuss
|
|
| 2321. |
BANG: Dividing 3D Assets via Generative Exploded Dynamics (arxiv.org) |
|
3 points by jinqueeny on Sep 30, 2025 | hide | past | pdf | discuss
|
|
| 2322. |
Can LLMs Be Creative? Paper: Combinatorial Creativity: A New Frontier (arxiv.org) |
|
2 points by jdcampolargo on Sep 29, 2025 | hide | past | pdf | discuss
|
|
| 2323. |
What the F*ck Is Artificial General Intelligence? (arxiv.org) |
|
59 points by SweetSoftPillow on Sep 29, 2025 | hide | past | pdf | 45 comments
|
|
| 2324. |
SpinGPT: A Large-Language-Model Approach to Playing Poker Correctly (arxiv.org) |
|
1 point by lucaspauker on Sep 29, 2025 | hide | past | pdf | discuss
|
|
| 2325. |
Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing (arxiv.org) |
|
3 points by amscotti on Sep 29, 2025 | hide | past | pdf | discuss
|
|
| 2326. |
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs (arxiv.org) |
|
1 point by simonpure on Sep 29, 2025 | hide | past | pdf | discuss
|
|
| 2327. |
A Deep Research Agent for Curating Vision Datasets (arxiv.org) |
|
12 points by barthelomew on Sep 29, 2025 | hide | past | pdf | discuss
|
|
| 2328. |
Reasoning LLM Errors Arise from Hallucinating Critical Problem Features (arxiv.org) |
|
2 points by PaulHoule on Sep 29, 2025 | hide | past | pdf | discuss
|
|
| 2329. |
Characterizing the Latency and Power Regimes of Open Text-to-Video Models (arxiv.org) |
|
1 point by bikenaga on Sep 28, 2025 | hide | past | pdf | discuss
|
|
| 2330. |
Fine-Tune Black Box Embedding Models (arxiv.org) |
|
10 points by mingtianzhang on Sep 28, 2025 | hide | past | pdf | 1 comment
|
|
| 2331. |
Metacognitive Reuse: Turning Recurring LLM Reasoning into Concise Behaviors (arxiv.org) |
|
2 points by Anon84 on Sep 28, 2025 | hide | past | pdf | discuss
|
|
| 2332. |
Teaching LLMs to Plan (arxiv.org) |
|
5 points by orixilus on Sep 27, 2025 | hide | past | pdf | discuss
|
|
| 2333. |
The Transparent Earth: A Multimodal Foundation Model for the Earth's Subsurface (arxiv.org) |
|
3 points by PaulHoule on Sep 27, 2025 | hide | past | pdf | discuss
|
|
| 2334. |
Context-Aware Membership Inference Attacks Against Pre-Trained LLMs (arxiv.org) |
|
2 points by felineflock on Sep 27, 2025 | hide | past | pdf | discuss
|
|
| 2335. |
Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models (arxiv.org) |
|
4 points by gok on Sep 27, 2025 | hide | past | pdf | 1 comment
|
|
| 2336. |
Understanding RL for model training, and future directions with GRAPE (arxiv.org) |
|
33 points by sonabinu on Sep 26, 2025 | hide | past | pdf | 1 comment
|
|
| 2337. |
LLM probabilities cannot distinguish between possible and impossible language (arxiv.org) |
|
2 points by foobarqux on Sep 26, 2025 | hide | past | pdf | discuss
|
|
| 2338. |
Qwen3-Omni: first multimodal model with SoTA text, image, audio, and video perf (arxiv.org) |
|
2 points by walterbell on Sep 26, 2025 | hide | past | pdf | discuss
|
|
| 2339. |
Do LLM Modules Generalize? A Study on Motion Generation for Autonomous Driving (arxiv.org) |
|
1 point by PaulHoule on Sep 26, 2025 | hide | past | pdf | discuss
|
|
| 2340. |
Bit is all we need: binary normalized neural networks (arxiv.org) |
|
101 points by PaulHoule on Sep 26, 2025 | hide | past | pdf | 54 comments
|
|
|
| More |
