|
|
|
Stories from July 2, 2025 (UTC)
|
| 1. |
Huawei releases an open weight model trained on Huawei Ascend GPUs (arxiv.org) |
|
321 points by buyucu on Jul 2, 2025 | hide | past | pdf | 333 comments
|
|
| 2. |
Large Language Models Don't Make Sense of Word Problems (arxiv.org) |
|
3 points by belter on Jul 2, 2025 | hide | past | pdf | discuss
|
|
| 3. |
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Tree Search (arxiv.org) |
|
3 points by vrm on Jul 2, 2025 | hide | past | pdf | discuss
|
|
| 4. |
Radial Attention: Sparse Attention with Energy Decay for Long Video Generation (arxiv.org) |
|
2 points by yorwba on Jul 2, 2025 | hide | past | pdf | discuss
|
|
| 5. |
Transition Matching: Scalable and Flexible Generative Modeling (arxiv.org) |
|
2 points by lnyan on Jul 2, 2025 | hide | past | pdf | discuss
|
|
| 6. |
Your Language Model Can Handle Non-Canonical Tokenizations (arxiv.org) |
|
2 points by PaulHoule on Jul 2, 2025 | hide | past | pdf | discuss
|
|
| 7. |
Programs as Singularities (arxiv.org) |
|
2 points by etiams on Jul 2, 2025 | hide | past | pdf | discuss
|
|
| 8. |
Red Teaming for Gen. AI, Report on a Copyright-Focused Exercise in Academic Med (arxiv.org) |
|
1 point by jjwen on Jul 2, 2025 | hide | past | pdf | discuss
|
|
| 9. |
Brain2Model Transfer: Training decision AI using the human brain as a teacher (arxiv.org) |
|
1 point by tomasgaquino on Jul 2, 2025 | hide | past | pdf | 1 comment
|
|
| 10. |
MAIR: A Benchmark for Evaluating Instructed Retrieval (2024) (arxiv.org) |
|
1 point by fzliu on Jul 2, 2025 | hide | past | pdf | discuss
|
|
| 11. |
MLE-Star: Machine Learning Engineering Agent via Search and Targeted Refinement (arxiv.org) |
|
1 point by PaulHoule on Jul 2, 2025 | hide | past | pdf | discuss
|
|
|
|
