| 3421. |
Orion: A Homomorphic Encryption Framework for Deep Learning [pdf] (arxiv.org) |
|
2 points by bikenaga on Mar 30, 2025 | hide | past | pdf | 2 comments
|
|
| 3422. |
Matrix Calculus (For Machine Learning and Beyond) (arxiv.org) |
|
183 points by ibobev on Mar 29, 2025 | hide | past | pdf | 30 comments
|
|
| 3423. |
Benchmarking Large Language Models for Handwritten Text Recognition (arxiv.org) |
|
1 point by PaulHoule on Mar 29, 2025 | hide | past | pdf | discuss
|
|
| 3424. |
UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation (arxiv.org) |
|
2 points by gnabgib on Mar 29, 2025 | hide | past | pdf | discuss
|
|
| 3425. |
Industrial-Grade Sensor Simulation via Gaussian Splatting (arxiv.org) |
|
2 points by PaulHoule on Mar 29, 2025 | hide | past | pdf | discuss
|
|
| 3426. |
Video-R1: Reinforcing Video Reasoning in MLLMs (arxiv.org) |
|
1 point by chrsw on Mar 29, 2025 | hide | past | pdf | discuss
|
|
| 3427. |
Analyzing Modern NVIDIA GPU cores (arxiv.org) |
|
2 points by matt_d on Mar 29, 2025 | hide | past | pdf | discuss
|
|
| 3428. |
Self-Supervised Learning from Images with JEPA (2023) (arxiv.org) |
|
40 points by Brysonbw on Mar 29, 2025 | hide | past | pdf | 10 comments
|
|
| 3429. |
Passive Heart Rate Monitoring During Smartphone Use in Everyday Life (arxiv.org) |
|
1 point by PaulHoule on Mar 29, 2025 | hide | past | pdf | discuss
|
|
| 3430. |
Trusted ML Models Unlock Private Inference for Infeasible Cryptographic Problems (arxiv.org) |
|
1 point by gnabgib on Mar 28, 2025 | hide | past | pdf | discuss
|
|
| 3431. |
Examples as the Prompt: A Scalable Approach for LLM Adaptation in E-Commerce (arxiv.org) |
|
1 point by PaulHoule on Mar 28, 2025 | hide | past | pdf | discuss
|
|
| 3432. |
Physics-Based Deep Learning v4 (arxiv.org) |
|
5 points by __rito__ on Mar 28, 2025 | hide | past | pdf | 1 comment
|
|
| 3433. |
FFN Fusion: Rethinking Sequential Computation in Large Language Models (arxiv.org) |
|
5 points by Dezash on Mar 28, 2025 | hide | past | pdf | discuss
|
|
| 3434. |
UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation (arxiv.org) |
|
2 points by gnabgib on Mar 27, 2025 | hide | past | pdf | discuss
|
|
| 3435. |
Parameter-free KV cache compression for memory-efficient long-context LLMs (arxiv.org) |
|
65 points by PaulHoule on Mar 27, 2025 | hide | past | pdf | 19 comments
|
|
| 3436. |
RGL: Graph-Centric,Framework for Efficient RAG on Graphs (arxiv.org) |
|
2 points by kiyanwang on Mar 27, 2025 | hide | past | pdf | discuss
|
|
| 3437. |
More Economical Context-Augmented LLM Generation by Reusing Stored KV Cache (arxiv.org) |
|
3 points by PaulHoule on Mar 27, 2025 | hide | past | pdf | discuss
|
|
| 3438. |
All That Glitters Is Not Novel: Plagiarism in AI Generated Research (arxiv.org) |
|
3 points by jdale27 on Mar 27, 2025 | hide | past | pdf | discuss
|
|
| 3439. |
Training Plug-N-Play Knowledge Modules with Deep Context Distillation (arxiv.org) |
|
2 points by PaulHoule on Mar 27, 2025 | hide | past | pdf | discuss
|
|
| 3440. |
DeepSeek-V3 Technical Report (arxiv.org) |
|
132 points by signa11 on Mar 27, 2025 | hide | past | pdf | 34 comments
|
|
| 3441. |
LLM-Guided Compositional Program Synthesis (arxiv.org) |
|
2 points by PaulHoule on Mar 26, 2025 | hide | past | pdf | discuss
|
|
| 3442. |
Defeating Prompt Injections by Design (arxiv.org) |
|
1 point by kyrra on Mar 26, 2025 | hide | past | pdf | discuss
|
|
| 3443. |
Stealthy Cross-Origin Context Poisoning Attacks Against AI Coding Assistants (arxiv.org) |
|
1 point by dtartarotti on Mar 26, 2025 | hide | past | pdf | discuss
|
|
| 3444. |
SplitQuantV2: Enhancing Low-Bit Quantization of LLMs Without GPUs (arxiv.org) |
|
34 points by PaulHoule on Mar 26, 2025 | hide | past | pdf | 9 comments
|
|
| 3445. |
Scaling a 300B Mixture-of-Experts LING LLM Without Premium GPUs (arxiv.org) |
|
2 points by PaulHoule on Mar 25, 2025 | hide | past | pdf | discuss
|
|
| 3446. |
Optimizing ML training with metagradient descent (arxiv.org) |
|
83 points by ladberg on Mar 25, 2025 | hide | past | pdf | 13 comments
|
|
| 3447. |
Graph Masked Language Models (arxiv.org) |
|
1 point by PaulHoule on Mar 25, 2025 | hide | past | pdf | discuss
|
|
| 3448. |
Communication-Efficient Language Model Training Scales Reliably and Robustly (arxiv.org) |
|
1 point by PaulHoule on Mar 25, 2025 | hide | past | pdf | discuss
|
|
| 3449. |
SQLCritic: Correcting Text-to-SQL Generation via Clause-Wise Critic (arxiv.org) |
|
1 point by PaulHoule on Mar 25, 2025 | hide | past | pdf | discuss
|
|
| 3450. |
Accurate INT8 Training Through Dynamic Block-Level Fallback (arxiv.org) |
|
3 points by PaulHoule on Mar 24, 2025 | hide | past | pdf | discuss
|
|
|
| More |
