| 2491. |
Speed Always Wins: A Survey on Efficient Architectures for LLMs (arxiv.org) |
|
2 points by Anon84 on Aug 27, 2025 | hide | past | pdf | discuss
|
|
| 2492. |
Audio-Visual Contact Classification for Tree Structures in Agriculture (arxiv.org) |
|
3 points by PaulHoule on Aug 27, 2025 | hide | past | pdf | discuss
|
|
| 2493. |
2-D Sparse Parallelism for Deep Learning Recommendation Model Training (arxiv.org) |
|
1 point by PaulHoule on Aug 26, 2025 | hide | past | pdf | discuss
|
|
| 2494. |
Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents (arxiv.org) |
|
2 points by fzliu on Aug 26, 2025 | hide | past | pdf | discuss
|
|
| 2495. |
LLM Speed Up Breakthrough? (arxiv.org) |
|
2 points by bilsbie on Aug 26, 2025 | hide | past | pdf | discuss
|
|
| 2496. |
Logit-Gap Steering: Efficient Short-Suffix Jailbreaks for Aligned LLMs (arxiv.org) |
|
1 point by rntn on Aug 26, 2025 | hide | past | pdf | discuss
|
|
| 2497. |
Sequence Parallelism: Long Sequence Training from System Perspective (2021) (arxiv.org) |
|
2 points by jxmorris12 on Aug 26, 2025 | hide | past | pdf | discuss
|
|
| 2498. |
Memento: Fine-tuning LLM Agents without Fine-tuning LLMs (arxiv.org) |
|
1 point by vincirufus on Aug 26, 2025 | hide | past | pdf | 1 comment
|
|
| 2499. |
AnalogSeeker: An Open-Source Foundation Language Model for Analog Circuit Design (arxiv.org) |
|
3 points by by_Seeing on Aug 25, 2025 | hide | past | pdf | discuss
|
|
| 2500. |
AlphaAgents: LLM Based Multi-Agents for Equity Portfolio Constructions (arxiv.org) |
|
1 point by rbanffy on Aug 25, 2025 | hide | past | pdf | discuss
|
|
| 2501. |
AetherCode: Evaluating LLMs' Ability to Win in Premier Programming Competitions (arxiv.org) |
|
2 points by pella on Aug 25, 2025 | hide | past | pdf | 1 comment
|
|
| 2502. |
Alvorada-Bench: Can Language Models Solve Brazilian University Entrance Exams? (arxiv.org) |
|
1 point by henriquegodoy on Aug 25, 2025 | hide | past | pdf | discuss
|
|
| 2503. |
EvoGit: Decentralized multi-agent framework for software development (arxiv.org) |
|
3 points by manualwise on Aug 25, 2025 | hide | past | pdf | 1 comment
|
|
| 2504. |
Hardwired-Neurons LPUs as General-Purpose Cognitive Substrates (arxiv.org) |
|
1 point by chrsw on Aug 25, 2025 | hide | past | pdf | discuss
|
|
| 2505. |
Reinforcement learning and VR for personalized arachnophobia treatment (arxiv.org) |
|
2 points by Kye on Aug 25, 2025 | hide | past | pdf | 1 comment
|
|
| 2506. |
Exploring LLM Confidence in Code Completion (arxiv.org) |
|
2 points by Hard_Space on Aug 25, 2025 | hide | past | pdf | discuss
|
|
| 2507. |
AetherCode: Evaluating LLMs' Ability to Win in Premier Programming Competitions (arxiv.org) |
|
1 point by limoce on Aug 25, 2025 | hide | past | pdf | discuss
|
|
| 2508. |
Zero-Shot Retrieval for Scalable Visual Search in a Two-Sided Marketplace (arxiv.org) |
|
2 points by PaulHoule on Aug 24, 2025 | hide | past | pdf | discuss
|
|
| 2509. |
Evaluating Long-Term Conversational Memory of LLM Agents (arxiv.org) |
|
1 point by handfuloflight on Aug 24, 2025 | hide | past | pdf | discuss
|
|
| 2510. |
BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-Scale Pretraining (arxiv.org) |
|
4 points by circuithunter on Aug 23, 2025 | hide | past | pdf | discuss
|
|
| 2511. |
Algorithmic Fairness Amid Social Determinants (arxiv.org) |
|
2 points by PaulHoule on Aug 23, 2025 | hide | past | pdf | discuss
|
|
| 2512. |
LNS-Madam: Low-Precision Training in Log Using Multiplicative Weight Update (arxiv.org) |
|
2 points by nabla9 on Aug 23, 2025 | hide | past | pdf | 1 comment
|
|
| 2513. |
Modeling Annotator Disagreement with Demographic-Aware Experts (arxiv.org) |
|
2 points by PaulHoule on Aug 23, 2025 | hide | past | pdf | discuss
|
|
| 2514. |
Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing (arxiv.org) |
|
130 points by omarsar on Aug 22, 2025 | hide | past | pdf | 28 comments
|
|
| 2515. |
How Random Is Random? Evaluating Randomness and Humaness of LLM Coin Flip (2024) (arxiv.org) |
|
2 points by walterbell on Aug 22, 2025 | hide | past | pdf | discuss
|
|
| 2516. |
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning (arxiv.org) |
|
1 point by Anon84 on Aug 22, 2025 | hide | past | pdf | discuss
|
|
| 2517. |
Is GPT-OSS Good? A Comprehensive Evaluation (arxiv.org) |
|
2 points by dloss on Aug 22, 2025 | hide | past | pdf | discuss
|
|
| 2518. |
Intern-S1: A Scientific Multimodal Foundation Model (arxiv.org) |
|
4 points by anothermathbozo on Aug 22, 2025 | hide | past | pdf | 1 comment
|
|
| 2519. |
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization (arxiv.org) |
|
1 point by simonpure on Aug 22, 2025 | hide | past | pdf | discuss
|
|
| 2520. |
FormalGrad: Integrating Formal Methods with Gradient-Based LLM Refinement (arxiv.org) |
|
2 points by PaulHoule on Aug 21, 2025 | hide | past | pdf | discuss
|
|
|
| More |
