| 2461. |
Large Language Models and Emergence: A Complex Systems Perspective (arxiv.org) |
|
1 point by tjr on Sep 3, 2025 | hide | past | pdf | discuss
|
|
| 2462. |
Learned Perceptive Forward Dynamics Model for Safe Robotic Navigation (arxiv.org) |
|
2 points by rbanffy on Sep 3, 2025 | hide | past | pdf | discuss
|
|
| 2463. |
Request-Only Optimization for Recommendation Systems (arxiv.org) |
|
3 points by PaulHoule on Sep 3, 2025 | hide | past | pdf | discuss
|
|
| 2464. |
Towards Agentic OS: An LLM Agent Framework for Linux Schedulers (arxiv.org) |
|
3 points by Hard_Space on Sep 3, 2025 | hide | past | pdf | discuss
|
|
| 2465. |
Promptware Attacks Against LLM-Powered Assistants Are Practical and Dangerous (arxiv.org) |
|
1 point by speckx on Sep 3, 2025 | hide | past | pdf | discuss
|
|
| 2466. |
The wall confronting large language models (arxiv.org) |
|
172 points by PaulHoule on Sep 3, 2025 | hide | past | pdf | 200 comments
|
|
| 2467. |
Factors of Convergence Between Brains and Computer Vision Models (arxiv.org) |
|
1 point by gmays on Sep 2, 2025 | hide | past | pdf | discuss
|
|
| 2468. |
Attention is a smoothed cubic spline (arxiv.org) |
|
11 points by amai on Sep 1, 2025 | hide | past | pdf | discuss
|
|
| 2469. |
SparseLoCo: Communication-Efficient LLM Training (arxiv.org) |
|
19 points by synapz_org on Sep 1, 2025 | hide | past | pdf | 1 comment
|
|
| 2470. |
Adaptive LLM routing under budget constraints (arxiv.org) |
|
206 points by tdchaitanya on Sep 1, 2025 | hide | past | pdf | 78 comments
|
|
| 2471. |
LLM4ES: Learning User Embeddings from Event Sequences via Large Language Models (arxiv.org) |
|
1 point by PaulHoule on Sep 1, 2025 | hide | past | pdf | discuss
|
|
| 2472. |
Benchmarking Large Language Models for Geolocating Colonial Virginia Land Grants (arxiv.org) |
|
1 point by PaulHoule on Sep 1, 2025 | hide | past | pdf | discuss
|
|
| 2473. |
Motif 2.6B Technical Report (arxiv.org) |
|
1 point by PaulHoule on Sep 1, 2025 | hide | past | pdf | discuss
|
|
| 2474. |
Navigating the Latent Space Dynamics of Neural Models (arxiv.org) |
|
5 points by felineflock on Aug 31, 2025 | hide | past | pdf | discuss
|
|
| 2475. |
Reusing Computation in Text-to-Image Diffusion for Efficient Image Generation (arxiv.org) |
|
41 points by gidellav on Aug 29, 2025 | hide | past | pdf | 2 comments
|
|
| 2476. |
A multi-task neural network for atypical mitosis recognition under domain shift (arxiv.org) |
|
1 point by gidellav on Aug 29, 2025 | hide | past | pdf | discuss
|
|
| 2477. |
Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation (arxiv.org) |
|
4 points by gidellav on Aug 29, 2025 | hide | past | pdf | discuss
|
|
| 2478. |
The Theoretical Limitations of Embedding-Based Retrieval (arxiv.org) |
|
151 points by fzliu on Aug 29, 2025 | hide | past | pdf | 38 comments
|
|
| 2479. |
Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data (arxiv.org) |
|
2 points by liliumregale on Aug 29, 2025 | hide | past | pdf | 1 comment
|
|
| 2480. |
Fisher-Orthogonal Projection Methods for Gradient Descent with Large Batches (arxiv.org) |
|
2 points by sorenjan on Aug 29, 2025 | hide | past | pdf | discuss
|
|
| 2481. |
Semantic Structure in Large Language Model Embeddings (arxiv.org) |
|
7 points by PaulHoule on Aug 29, 2025 | hide | past | pdf | discuss
|
|
| 2482. |
AiXiv: A Platform for AI Researchers (arxiv.org) |
|
4 points by shashkingregory on Aug 29, 2025 | hide | past | pdf | 2 comments
|
|
| 2483. |
CCPS: Calibrating LLM Confidence via Perturbation Stability – EMNLP 2025 (arxiv.org) |
|
3 points by erfan_mhi on Aug 28, 2025 | hide | past | pdf | 1 comment
|
|
| 2484. |
LMAR: Language Model Augmented Retriever for Domain-Specific Knowledge Indexing (arxiv.org) |
|
2 points by PaulHoule on Aug 28, 2025 | hide | past | pdf | discuss
|
|
| 2485. |
Monte Carlo Gradient Estimation in Machine Learning (arxiv.org) |
|
1 point by sebg on Aug 28, 2025 | hide | past | pdf | discuss
|
|
| 2486. |
Pretraining on the Test Set Is All You Need (arxiv.org) |
|
1 point by felineflock on Aug 28, 2025 | hide | past | pdf | discuss
|
|
| 2487. |
Automatic and Universal Prompt Injection Attacks Against Large Language Models (arxiv.org) |
|
1 point by felineflock on Aug 28, 2025 | hide | past | pdf | discuss
|
|
| 2488. |
Predicting the Order of Upcoming Tokens Improves Language Modeling (arxiv.org) |
|
7 points by wavelander on Aug 28, 2025 | hide | past | pdf | 2 comments
|
|
| 2489. |
Learning Facts at Scale with Active Reading (arxiv.org) |
|
7 points by Anon84 on Aug 28, 2025 | hide | past | pdf | discuss
|
|
| 2490. |
Omni Geometry Representation Learning vs. LLMs for Geospatial Entity Resolution (arxiv.org) |
|
2 points by PaulHoule on Aug 27, 2025 | hide | past | pdf | discuss
|
|
|
| More |
