| 3631. |
Fire-Flyer AI-HPC: Cost-Effective Software-Hardware Co-Design for Deep Learning (arxiv.org) |
|
2 points by doener on Feb 21, 2025 | hide | past | pdf | discuss
|
|
| 3632. |
Performance of Zero-Shot Time Series Foundation Models on Cloud Data (arxiv.org) |
|
4 points by wanderingmind on Feb 21, 2025 | hide | past | pdf | discuss
|
|
| 3633. |
Presumed Cultural Identity: How Names Shape LLM Responses (arxiv.org) |
|
1 point by SerCe on Feb 21, 2025 | hide | past | pdf | discuss
|
|
| 3634. |
Idiosyncrasies in Large Language Models (arxiv.org) |
|
2 points by mfiguiere on Feb 20, 2025 | hide | past | pdf | discuss
|
|
| 3635. |
AI Alignment at Your Discretion (arxiv.org) |
|
3 points by maartenbuyl on Feb 20, 2025 | hide | past | pdf | discuss
|
|
| 3636. |
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models(2023) (arxiv.org) |
|
2 points by martinloretz on Feb 20, 2025 | hide | past | pdf | 1 comment
|
|
| 3637. |
WonderHuman: 3D avatars from single-view video (arxiv.org) |
|
38 points by jinqueeny on Feb 20, 2025 | hide | past | pdf | 6 comments
|
|
| 3638. |
Aide: AI-Driven Exploration in the Space of Code (Arxiv) (arxiv.org) |
|
1 point by WecoAI on Feb 19, 2025 | hide | past | pdf | 1 comment
|
|
| 3639. |
Native Sparse Attention: Hardware-Aligned and Natively Trainable (arxiv.org) |
|
2 points by teepo on Feb 19, 2025 | hide | past | pdf | discuss
|
|
| 3640. |
STT: Stateful Tracking with Transformers for Autonomous Driving [pdf] (arxiv.org) |
|
1 point by lawrenceyan on Feb 19, 2025 | hide | past | pdf | discuss
|
|
| 3641. |
Karatsuba Matrix Multiplication and Its Efficient Hardware Implementations (arxiv.org) |
|
2 points by emacs28 on Feb 19, 2025 | hide | past | pdf | discuss
|
|
| 3642. |
NSA: Hardware-Aligned and Natively Trainable Sparse Attention (arxiv.org) |
|
4 points by unignorant on Feb 19, 2025 | hide | past | pdf | 2 comments
|
|
| 3643. |
Deep Lake: A Lakehouse for Deep Learning (arxiv.org) |
|
2 points by teleforce on Feb 19, 2025 | hide | past | pdf | discuss
|
|
| 3644. |
Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names (arxiv.org) |
|
2 points by famouswaffles on Feb 18, 2025 | hide | past | pdf | 1 comment
|
|
| 3645. |
Tensor evolution: A framework for fast tensor computations using recurrences (arxiv.org) |
|
53 points by matt_d on Feb 18, 2025 | hide | past | pdf | 18 comments
|
|
| 3646. |
DeepSeek Native Sparse Attention (arxiv.org) |
|
16 points by bandwitch on Feb 18, 2025 | hide | past | pdf | 1 comment
|
|
| 3647. |
The Curse of Depth in Large Language Models (arxiv.org) |
|
2 points by jonbaer on Feb 18, 2025 | hide | past | pdf | discuss
|
|
| 3648. |
Mamba-Shedder: Post-Transformer Compression for Efficient SSMs (arxiv.org) |
|
1 point by fovc on Feb 18, 2025 | hide | past | pdf | discuss
|
|
| 3649. |
Native Sparse Attention: Hardware-Aligned, Natively Trainable Sparse Attention (arxiv.org) |
|
15 points by mfiguiere on Feb 18, 2025 | hide | past | pdf | 2 comments
|
|
| 3650. |
SWE-Lancer: a benchmark of freelance software engineering tasks from Upwork (arxiv.org) |
|
111 points by zone411 on Feb 18, 2025 | hide | past | pdf | 74 comments
|
|
| 3651. |
WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction (arxiv.org) |
|
1 point by jinqueeny on Feb 18, 2025 | hide | past | pdf | discuss
|
|
| 3652. |
Zep: A Temporal Knowledge Graph Architecture for Agent Memory (arxiv.org) |
|
1 point by TaurenHunter on Feb 18, 2025 | hide | past | pdf | discuss
|
|
| 3653. |
Pretraining on the Test Set Is All You Need (arxiv.org) |
|
2 points by Poalopat on Feb 17, 2025 | hide | past | pdf | discuss
|
|
| 3654. |
EnigmaEval: A Benchmark of Long Multimodal Reasoning Challenges (arxiv.org) |
|
17 points by apsec112 on Feb 17, 2025 | hide | past | pdf | discuss
|
|
| 3655. |
Matryoshka Quantization (arxiv.org) |
|
1 point by wseqyrku on Feb 17, 2025 | hide | past | pdf | discuss
|
|
| 3656. |
Step-Video-T2V: The Practice, Challenges, and Future of Video Foundation Model (arxiv.org) |
|
41 points by limoce on Feb 17, 2025 | hide | past | pdf | 5 comments
|
|
| 3657. |
ZeroBench: An Impossible Visual Benchmark for Contemporary LMMs (arxiv.org) |
|
9 points by taesiri on Feb 17, 2025 | hide | past | pdf | 3 comments
|
|
| 3658. |
Large Language Diffusion Models (arxiv.org) |
|
2 points by Philpax on Feb 17, 2025 | hide | past | pdf | discuss
|
|
| 3659. |
OpenAI: Competitive Programming with Large Reasoning Models (arxiv.org) |
|
2 points by Anon84 on Feb 16, 2025 | hide | past | pdf | 1 comment
|
|
| 3660. |
Matryoshka Quantization (arxiv.org) |
|
2 points by galeos on Feb 16, 2025 | hide | past | pdf | discuss
|
|
|
| More |
